CN119183162A

CN119183162A - Method, device, apparatus and storage medium for selecting target cell

Info

Publication number: CN119183162A
Application number: CN202310747768.4A
Authority: CN
Inventors: 麻晓宁; 胡军辉; 李天宬; 梁小雨; 寇会如; 刘蓉
Original assignee: Datang Mobile Communications Equipment Co Ltd
Current assignee: Datang Mobile Communications Equipment Co Ltd
Priority date: 2023-06-21
Filing date: 2023-06-21
Publication date: 2024-12-24

Abstract

The embodiment of the application provides a method, equipment, a device and a storage medium for selecting a target cell, wherein the method comprises the steps that source network equipment obtains a parameter prediction result, the parameter prediction result comprises performance parameters and/or optimal neighbor cell identifiers corresponding to terminals after the terminals are switched to neighbor cells, the performance parameters and/or the optimal neighbor cell identifiers are predicted to be obtained through the parameter prediction result, the target cell is switched to by the terminals, the parameter prediction result is based on a sample parameter information training, and the sample parameter information at least comprises parameters for representing uplink capacity and/or downlink capacity of a sample terminal on the sample neighbor cells. The method for selecting the target cell provided by the embodiment of the application can select the cell with the largest uplink and downlink capacity as the target cell, thereby improving the user performance.

Description

Method, device, apparatus and storage medium for selecting target cell

Technical Field

The present application relates to the field of wireless communications technologies, and in particular, to a method, an apparatus, a device, and a storage medium for selecting a target cell.

Background

In the existing cell switching mechanism, the source cell cannot obtain the uplink and downlink capacity (such as uplink and downlink spectrum efficiency and/or user experience parameters) of the neighboring cell, so that the uplink and downlink capacity of the neighboring cell cannot be considered when the target cell is selected, and the source cell may not select the target cell with the maximum uplink and downlink capacity, and the user performance cannot reach the optimum.

Disclosure of Invention

Aiming at the problems existing in the prior art, the embodiment of the application provides a method, equipment, a device and a storage medium for selecting a target cell.

In a first aspect, an embodiment of the present application provides a method for selecting a target cell, which is applied to a source network device, including:

The method comprises the steps of obtaining a parameter prediction result, wherein the parameter prediction result comprises performance parameters and/or an optimal neighbor cell identifier corresponding to a terminal after the terminal is switched to a neighbor cell, which is predicted based on a parameter prediction model;

Selecting a target cell to which the terminal is switched based on the parameter prediction result;

The parameter prediction model is trained based on sample parameter information, and the sample parameter information at least comprises parameters for representing uplink capacity and/or downlink capacity of a sample terminal on a sample adjacent cell.

In a second aspect, an embodiment of the present application further provides a method for selecting a target cell, which is applied to a second network device, including:

Receiving switching optimization request information sent by source network equipment;

According to the switching optimization request information, one or more of the following are sent to the source network equipment:

sample parameter information for training a parameter prediction model;

the parameter prediction model;

Feedback information after the terminal is switched to the target cell;

and the parameter prediction result comprises performance parameters and/or an optimal neighbor cell identifier corresponding to the terminal after the terminal is switched to the neighbor cell, wherein the performance parameters and/or the optimal neighbor cell identifier are/is predicted based on the parameter prediction model.

In a third aspect, an embodiment of the present application further provides a source network device, including a memory, a transceiver, and a processor;

the system comprises a memory for storing a computer program, a transceiver for receiving and transmitting data under the control of the processor, and a processor for reading the computer program in the memory and performing the following operations:

In a fourth aspect, an embodiment of the present application further provides a second network device, including a memory, a transceiver, and a processor;

sample parameter information for training a parameter prediction model;

the parameter prediction model;

Feedback information after the terminal is switched to the target cell;

In a fifth aspect, an embodiment of the present application further provides an apparatus for selecting a target cell, including

The system comprises an acquisition unit, a parameter prediction unit and a control unit, wherein the acquisition unit is used for acquiring a parameter prediction result, and the parameter prediction result comprises performance parameters obtained by switching a terminal into a neighboring cell based on a parameter prediction model and/or an optimal neighboring cell identifier corresponding to the terminal;

A selecting unit, configured to select a target cell to which the terminal is switched, based on the parameter prediction result;

In a sixth aspect, an embodiment of the present application further provides an apparatus for selecting a target cell, including a second receiving unit, configured to receive handover optimization request information sent by a source network device;

The second sending unit is used for sending one or more of the following to the source network equipment according to the switching optimization request information:

sample parameter information for training a parameter prediction model;

the parameter prediction model;

Feedback information after the terminal is switched to the target cell;

In a seventh aspect, embodiments of the present application further provide a computer-readable storage medium storing a computer program for causing a computer to perform the method for selecting a target cell as described in the first aspect or the method for selecting a target cell as described in the second aspect.

In an eighth aspect, an embodiment of the present application further provides a communication device, where a computer program is stored, where the computer program is configured to cause the communication device to perform the method for selecting a target cell according to the first aspect, or perform the method for selecting a target cell according to the second aspect.

In a ninth aspect, embodiments of the present application further provide a processor-readable storage medium storing a computer program for causing a processor to perform the method for selecting a target cell as described in the first aspect or the method for selecting a target cell as described in the second aspect.

In a tenth aspect, embodiments of the present application further provide a chip product, where a computer program is stored, where the computer program is configured to cause the chip product to perform the method for selecting a target cell according to the first aspect, or perform the method for selecting a target cell according to the second aspect.

The method, the device, the apparatus and the storage medium for selecting the target cell provided by the embodiment of the application are characterized in that the parameter prediction result is obtained by using a parameter prediction model to infer, sample parameter information for training the parameter prediction model comprises parameters for representing the uplink capacity and/or the downlink capacity of the sample terminal on a sample neighbor cell, and the parameter prediction result comprises performance parameters after the terminal is switched to the neighbor cell and/or optimal neighbor cell identifiers corresponding to the terminal. Therefore, the cell with the largest uplink and downlink capacity can be selected as the target cell, and the user performance is improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described, and it is apparent that the drawings in the following descriptions are some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort for those skilled in the art.

Fig. 1 is a schematic flow chart of a method for selecting a target cell according to an embodiment of the present application;

Fig. 2 is a flow chart of an uplink and downlink effective bandwidth estimation method of a neighboring cell according to an embodiment of the present application;

Fig. 3 is a second flowchart of a method for selecting a target cell according to an embodiment of the present application;

fig. 4 is a third flowchart of a method for selecting a target cell according to an embodiment of the present application;

fig. 5 is a schematic flow chart of estimating uplink and downlink capacities of neighboring cells and selecting a target cell according to a parameter prediction result provided in an embodiment of the present application;

FIG. 6 is a schematic flow chart of a method for obtaining information by a node sending a handover optimization request message to a node II according to an embodiment of the present application;

fig. 7 is a schematic flow chart of a gNB1 requiring a gNB2 to provide sample information according to an embodiment of the present application;

Fig. 8 is a schematic flow chart of selecting a target cell for a UE by using a parameter prediction model by the gNB3 according to an embodiment of the present application;

Fig. 9 is a flowchart of an algorithm for selecting a target cell using a parameter prediction result according to an embodiment of the present application;

FIG. 10 is a schematic flow chart of a node three-way node four-sending parameter prediction result according to an input parameter of a parameter prediction model provided by the embodiment of the application;

FIG. 11 is a schematic flow chart of acquiring a parameter prediction model from a node six by a node five according to an embodiment of the present application;

fig. 12 is a schematic structural diagram of a source network device according to an embodiment of the present application;

fig. 13 is a schematic structural diagram of a second network device according to an embodiment of the present application;

Fig. 14 is a schematic structural diagram of an apparatus for selecting a target cell according to an embodiment of the present application;

fig. 15 is a second schematic structural diagram of an apparatus for selecting a target cell according to an embodiment of the present application.

Detailed Description

In the embodiment of the application, the term "and/or" describes the association relation of the association objects, which means that three relations can exist, for example, A and/or B, and can mean that A exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship.

The term "plurality" in embodiments of the present application means two or more, and other adjectives are similar.

The terms "first," "second," and the like in embodiments of the present application are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments of the application are capable of operation in sequences other than those illustrated or otherwise described herein, and that the "first" and "second" distinguishing between objects generally are not limited in number to the extent that the first object may, for example, be one or more.

The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

Fig. 1 is a flow chart of a method for selecting a target cell according to an embodiment of the present application, as shown in fig. 1, where the method is applied to a source network device, and includes the following steps:

And 100, acquiring a parameter prediction result, wherein the parameter prediction result comprises performance parameters and/or an optimal neighbor cell identifier corresponding to the terminal after the terminal is switched to the neighbor cell, which are predicted based on the parameter prediction model.

And step 101, selecting a target cell to which the terminal is switched based on the parameter prediction result.

The parameter prediction model is obtained based on sample parameter information, and the sample parameter information at least comprises parameters for representing the uplink capacity and/or the downlink capacity of the sample terminal on a sample adjacent cell.

Specifically, when the source network device needs to switch the serving cell for the terminal (for example, the signal strength of the source cell measured by the terminal is smaller than a preset threshold, the traffic volume of the terminal is larger, or the terminal needs to switch the serving cell is determined by an existing mechanism), the parameter prediction result predicted by the parameter prediction model may be obtained first, and then the target cell to which the terminal is switched is selected based on the parameter prediction result.

The source network device may be any one of a 5G base station (gNB) in a 5G network architecture (next generation system), an evolved network device (evolutional Node B, eNB), an evolved network device (next generation system-evolutional Node B, ng-eNB) in a 5G network architecture, a 5G base station (E-UTRAN New Radio-gNB, en-gNB) in an evolved universal mobile telecommunications system terrestrial Radio access network, a Centralized Unit (CU) of the gNB, a Centralized Unit Control Plane (CU-CP) of the gNB, a Centralized Unit User Plane (CU-UP) of the gNB, a Distributed Unit (DU) of the gNB, or a wireless network intelligent resource Control (RAN INTELLIGENT Controller, RIC).

The parameter prediction result may include a performance parameter after the terminal is switched to the neighboring cell and/or an optimal neighboring cell identifier corresponding to the terminal. The performance parameter after the terminal is handed over to the neighboring cell may be a parameter for characterizing the performance of the user after the terminal is handed over to the neighboring cell, for example, a parameter for characterizing the channel quality, the service performance, and the like.

In some embodiments, the performance parameters of the terminal after handover to the neighboring cell included in the parameter prediction result may include one or more of the following:

(1) And measuring results of the neighbor cell for measuring the terminal.

The measurement result of the neighbor cell to the terminal may include at least one of a measurement result of the neighbor cell to a Sounding reference signal (Sounding REFERENCE SIGNAL, SRS) of the terminal, a measurement result of the neighbor cell to other uplink reference signals of the terminal, and a measurement result of the neighbor cell to a new air interface (New Radio in Unlicensed Spectrum, NR-U) channel of an unlicensed spectrum used by the terminal.

The measurement results include at least one of reference signal received Power (REFERENCE SIGNAL RECEIVING Power, RSRP), reference signal received Quality (REFERENCE SINGNAL RECEIVED Quality, RSRQ), signal-to-interference-plus-noise ratio (Signal to Interference plus Noise Ratio, SINR), received signal strength indication (RECEIVED SIGNAL STRENGTH Indicator, RSSI), and channel usage time ratio (Channel occupancy, CO) of cell measurements.

In case the measurement result comprises CO of a cell measurement, an energy detection threshold (Energy Detection Threshold, EDT) may also be included in the measurement result.

(2) Channel quality indication (Channel Quality Indication, CQI) and/or downlink modulation coding scheme Index (Modulation and Coding Scheme Index, MCS Index) of the terminal.

(3) Uplink MCS Index of the terminal.

(4) And the downlink spectrum efficiency parameters of the terminal on the adjacent cell.

The spectrum efficiency parameter may be a spectrum efficiency parameter corresponding to all or part of resources of the cell, for example, may be at least one of a spectrum efficiency parameter of all bandwidths of the cell, a spectrum efficiency parameter of a Physical downlink shared channel (Physical Downlink SHARED CHANNEL, PDSCH) resource, and a spectrum efficiency parameter of a Physical Uplink shared channel (Physical Uplink SHARED CHANNEL, PUSCH) resource.

In one embodiment, the spectral efficiency parameter may be spectral efficiency, i.e. the amount of data that can be transmitted per unit of spectrum.

In one embodiment, the minimum value and the maximum value of the spectrum efficiency supported by the cell may be divided into a plurality of intervals, and each interval corresponds to a characterization value. The spectrum efficiency of the sample terminal belongs to which section, and the spectrum efficiency parameter is the characteristic value of the section. The characterization value may be a value, for example, a fraction corresponding to a section where the spectral efficiency of the sample terminal belongs, assuming that the maximum value is 100 minutes and the minimum value is 0 minutes. The characterization value may be the number of the interval, may be the maximum value, the minimum value, the median or the average value of the spectrum efficiency in the interval, or may be an indication information, for example, indicating that the spectrum efficiency is high, medium or low.

In an embodiment, terminals (also referred to as User Equipment (UE)) with close uplink and/or downlink signal transceiving states in a cell may be divided into different subgroups, for example, UE1 and UE2 have multiple identical neighboring cells, and if the mean square error of uplink and/or downlink signal measurement values of the two UEs in all the identical neighboring cells is smaller than a preset threshold value, UE1 and UE2 are divided into the same subgroup. The spectral efficiency parameter may be a maximum, minimum, median or average value of the spectral efficiency of all UEs in the group to which the sample terminal belongs.

The concepts of the spectral efficiency parameters described above remain consistent throughout and are not described in detail below.

(5) And the uplink spectrum efficiency parameters of the terminal on the adjacent cell.

(6) User experience parameters of the terminal on the neighbor cell. The user experience parameters may include at least one of the following information:

A. uplink quality of service (Quality of Service, qoS) parameters.

B. Downstream QoS parameters.

C. Quality of experience (Quality of Experience, qoE) parameters.

Wherein the QoS parameters may include at least one of the following information:

a. data granularity identification. The data granularity identification may indicate that the QoS parameter is based on a data measurement corresponding to the data granularity identification. The data granularity identification may be at least one of a slice identification, a 5G QoS identifier (5G QoS Identifier,5QI) identification, a quality of service (Quality of Service, qoS) flow identification, a protocol data unit (Protocol Data Unit, PDU) session identification, and a UE identification.

B. rate. The rate may be a rate of a different protocol layer, such as at least one of a medium access control (Medium Access Control, MAC) layer rate, a radio link control (Radio Link Control, RLC) layer rate, and a packet data convergence protocol (PACKET DATA Convergence Protocol, PDCP) layer rate.

C. Packet loss rate. The packet loss rate may be a number of transmission losses or transmission failures per unit time, for example, at least one of RLC layer packet loss rate, PDCP layer packet loss rate, and hybrid automatic repeat request (Hybrid Automatic Repeat reQuest, HARQ) transmission failure rate.

D. Retransmission rate. The retransmission rate may be the number of retransmissions per unit time, for example, at least one of RLC layer retransmission rate, PDCP layer retransmission rate, and HARQ retransmission rate.

E. Time delay. The delay may be one delay, multiple delays, or a sum of multiple delays in the component part of the radio access network (Radio Access Network, RAN) side delay (RAN part of delay) in the 3GPP technical specification 38.314.

F. transmission queue length. The transmission queue length may be a transmission queue length of a different protocol layer, such as an RLC layer transmission queue length and/or a PDCP layer transmission queue length.

G. the packets are dithered. The packet jitter may be packet jitter of different protocol layers, such as RLC layer packet jitter and/or PDCP layer packet jitter.

The QoE parameters may include at least one of the following information:

a. Service type. The traffic type may be at least one of voice, video, and traffic type (using serviceType delivery in AppLayerMeasConfig field) defined in 3GPP technical specification 38.331 for application layer measurements.

B. At least one information in the application layer measurement report. The application layer measurement report is consistent with the application layer measurement report (delivered using measReportAppLayerContainer) used in 3GPP technical specification 38.331.

C. The RAN can see at least one information in the measurement report. The RAN visible measurement report is consistent with the RAN visible measurement report (delivered using RAN-VisibleMeasurements) used in 3GPP technical specification 38.331.

The concepts of the user experience parameters are consistent throughout, and will not be described in detail.

The parameter prediction result can also directly contain the optimal neighbor cell identifier corresponding to the terminal predicted by the parameter prediction model, and the optimal neighbor cell can be used as the selected target cell. The optimal neighbor cell identity corresponding to the terminal may be at least one of a global cell identity (Cell Global Identifier, CGI), a physical cell identity (PHYSICAL CELL IDENTIFIER, PCI), an absolute radio frequency channel number (Absolute Radio Frequency Channel Number, ARFCN), a tracking area code (TRACKING AREA code, TAC), a radio access network based notification area code (RAN-based Notification Area Code, RANAC) and a public land mobile network (Public Land Mobile Network, PLMN).

The parameter prediction model may be trained (e.g., reinforcement learning, supervised learning, etc.) using machine learning methods based on the sample information. The sample information used for training at least comprises parameters used for representing the uplink capacity and/or the downlink capacity of the sample terminal on the sample adjacent area. The uplink and/or downlink capacity of the sample terminal on the sample neighbor may reflect the capacity of the sample terminal to perform uplink and/or downlink data transmission on the sample neighbor.

In some embodiments, parameters in the sample parameter information used to characterize the uplink and/or downlink capabilities of the sample terminal on the sample neighbor may include one or more of the following:

(1) And the uplink spectrum efficiency parameter and/or the downlink spectrum efficiency parameter of the sample terminal on the sample adjacent cell.

(2) The uplink bandwidth and/or the downlink bandwidth of the sample terminal on the sample neighbor cell, namely the uplink bandwidth and/or the downlink bandwidth used by the sample terminal on the sample neighbor cell.

(3) User experience parameters of sample terminals on sample neighbor cells.

The method for selecting the target cell provided by the embodiment of the application comprises the steps of obtaining a parameter prediction result, and selecting the target cell to which the terminal is switched according to the parameter prediction result, wherein the parameter prediction result is obtained by reasoning through a parameter prediction model, sample parameter information for training the parameter prediction model comprises parameters for representing the uplink capacity and/or the downlink capacity of the sample terminal on a sample adjacent cell, and the parameter prediction result comprises performance parameters after the terminal is switched to the adjacent cell and/or optimal adjacent cell identifiers corresponding to the terminal. Therefore, the cell with the largest uplink and downlink capacity can be selected as the target cell, and the user performance is improved.

In some embodiments, obtaining a parameter predictor includes:

acquiring parameter prediction results from the first network device, or

And obtaining a parameter prediction result based on the parameter prediction model.

Specifically, the source network device may obtain the parameter prediction result from the first network device. The first network device may be any one of gNB, eNB, ng-eNB, en-gNB, CU of gNB, CUCP of gNB, CUUP of gNB, DU of gNB, RIC or newly defined network node. The first network device stores the parameter prediction model, and the first network device may be the same as the base station where the source network device is located or a component part (for example CU, CUCP, CUUP or DU) of the base station where the source network device is located, may be the same as the base station where the neighboring cell is located or a component part (for example CU, CUCP, CUUP or DU) of the base station where the neighboring cell is located, or may be different from the base station or the device.

Or the source network device can also directly use the parameter prediction model to predict to obtain the parameter prediction result. The parameter prediction model may be stored on the source network device before the parameter prediction result is obtained, or may be obtained by requesting the other network devices for obtaining the parameter prediction result in the process of obtaining the parameter prediction result.

In some embodiments, the method further comprises:

transmitting handover optimization request information to the second network device, the handover optimization request information being used to obtain one or more of:

Sample parameter information;

A parameter prediction model;

Feedback information after the terminal is switched to the target cell;

And predicting a result of the parameter.

In particular, the second network device may be any of gNB, eNB, ng-eNB, en-gNB, CU of gNB, CUCP of gNB, CUUP of gNB, DU of gNB, RIC or newly defined network node. The second network device may be the same as the first network device or may be different from the first network device, and is not specifically limited herein.

In one embodiment, when the parameter prediction model needs to be trained, the source network device may send handover optimization request information to the second network device to obtain sample parameter information. The second network device may be the network device where the neighbor cell of the source cell is located.

In one embodiment, when the parameter prediction model is stored in the second network device, the source network device may send handover optimization request information to the second network device to obtain the parameter prediction model.

Stored in the second network device may be a parameter prediction model that has been trained.

In an embodiment, when the target cell is within the range of the second network device, the source network device may send handover optimization request information to the second network device to obtain feedback information after the terminal is handed over to the target cell.

In one embodiment, when the parameter prediction model is stored on the second network device, the source network device may not obtain the parameter prediction model, but may use the parameter prediction model to perform prediction on the second network device, so as to obtain a parameter prediction result. The source network device may send handover optimization request information to the second network device to obtain the parameter prediction result. The second network device may obtain the input parameters of the parameter prediction model from the source network device, or may directly obtain the input parameters of the parameter prediction model from the neighboring cell of the source cell, then obtain the parameter prediction result according to the input parameters of the parameter prediction model, and then send the parameter prediction result to the source network device.

In some embodiments, the sample parameter information may further include one or more of the following:

(1) Cell identity of the sample source cell. Wherein the cell identity may be at least one of CGI, PCI, ARFCN, TAC, RANAC and a PLMN.

(2) Cell identification of the sample neighbor. Wherein the cell identity may be at least one of CGI, PCI, ARFCN, TAC, RANAC and a PLMN.

(3) Identification of the serving beam on the sample neighbor.

(4) Identification of the serving beam on the sample source cell.

(5) Identification of sample terminals. The identity of the terminal may be at least one of Source NG-RAN node UE XnAP ID、Target NG-RAN node UE XnAP ID、gNB-CU UE F1AP ID、gNB-DU UE F1AP ID、RAN UE ID、 international mobile equipment identity (International Mobile Equipment Identity, IMEI), international mobile subscriber identity (International Mobile Subscriber Identity, IMSI), globally unique temporary UE identity (Globally Unique Temporary UE Identity, GUTI), user permanent identifier (SUbscription PERMANENT IDENTIFIER, SUPI), user hidden identifier (Subscriptionconcealed identifier, SUCI) and radio network temporary identity (Radio Network Temporary Identity, RNTI).

(6) And the downlink transmitting power of the sample adjacent cell. The transmit power may be an actual transmit power and/or a maximum transmit power.

(7) The downlink transmit power of the serving beam on the sample neighbor. The transmit power may be an actual transmit power and/or a maximum transmit power.

(8) The downlink transmit power of the sample source cell. The transmit power may be an actual transmit power and/or a maximum transmit power.

(9) The downlink transmit power of the serving beam on the sample source cell. The transmit power may be an actual transmit power and/or a maximum transmit power.

(10) Uplink transmit power of the sample terminal. The transmit power may be an actual transmit power and/or a maximum transmit power.

(11) The number of downlink transmitting antennas in the neighboring cell of the sample.

(12) The number of uplink receiving antennas in the neighboring cell of the sample.

(13) The number of downlink transmission antennas of the sample source cell.

(14) The number of uplink receive antennas of the sample source cell.

(15) The number of uplink transmit antennas of the sample terminal.

(16) The number of downlink receive antennas of the sample terminal.

(17) And the sample terminal reports the measurement result of at least one cell which is different from the frequency point of the sample source cell.

(18) And the measurement result of at least one cell which is reported by the sample terminal and is the same as the frequency point of the sample source cell.

(19) And measuring results of the sample neighbor cell for measuring the sample terminal.

The measurement result of the sample neighbor cell for measuring the sample terminal may include at least one of a measurement result of the sample neighbor cell for measuring an SRS of the sample terminal, a measurement result of the sample neighbor cell for measuring other uplink reference signals of the sample terminal, and a measurement result of the sample neighbor cell for measuring an NR-U channel used by the sample terminal.

The measurement results include at least one of RSRP, RSRQ, SINR, RSSI and CO measured by the cell.

In case the above measurement result comprises CO of a cell measurement, EDT may also be included in the measurement result.

(20) And measuring results of the sample source cell for measuring the sample terminal.

(21) CQI and/or downlink MCS Index of the sample terminal.

(22) Uplink MCS Index of the sample terminal.

(23) Load status of the sample neighbor. The load status may include, among other things, some or all of the information reported by the Resource Status Reporting procedure defined in the XnAP protocol in the existing mechanism.

(24) The load state of the sample source cell.

In some embodiments, feedback information after the terminal switches to the target cell may include one or more of the following:

(1) Identification of the target cell.

(2) Identification of the serving beam on the target cell.

(3) And measuring results of the target cell for measuring the terminal.

(4) CQI and/or downlink MCS Index for the terminal.

(5) Uplink MCS Index of the terminal.

(6) And the downlink spectrum efficiency parameters of the terminal on the target cell.

(7) And the uplink spectrum efficiency parameter of the terminal on the target cell.

(8) User experience parameters of the terminal on the target cell.

In some embodiments, the input parameters of the parametric prediction model may include one or more of the following:

(1) Cell identity of the neighbor cell. Wherein the cell identity may be at least one of CGI, PCI, ARFCN, TAC, RANAC and a PLMN.

(2) Identification of the serving beam on the neighbor.

(3) Cell identity of the source cell.

(4) Identification of the serving beam on the source cell.

(5) And (5) identification of the terminal.

(6) Downlink transmission power of the neighbor cell. The transmit power may be an actual transmit power and/or a maximum transmit power.

(7) Downlink transmit power of the serving beam on the neighbor. The transmit power may be an actual transmit power and/or a maximum transmit power.

(8) Downlink transmit power of the source cell. The transmit power may be an actual transmit power and/or a maximum transmit power.

(9) Downlink transmit power of the serving beam on the source cell. The transmit power may be an actual transmit power and/or a maximum transmit power.

(10) Uplink transmit power of the terminal. The transmit power may be an actual transmit power and/or a maximum transmit power.

(11) The number of downlink transmission antennas in the neighboring cell.

(12) The number of uplink receiving antennas in the neighboring cell.

(13) The number of downlink transmit antennas of the source cell.

(14) The number of uplink receive antennas of the source cell.

(15) The number of uplink transmit antennas of the terminal.

(16) The number of downlink receiving antennas of the terminal.

(17) And the uplink effective bandwidth of the terminal on the adjacent cell.

(18) And the downlink effective bandwidth of the terminal on the adjacent cell.

(19) The uplink idle bandwidth of the neighbor cell.

(20) Downlink idle bandwidth of the neighbor cell.

(21) And the terminal reports the measurement result of at least one cell which is different from the frequency point of the source cell.

(22) And the terminal reports the measurement result of at least one cell which is the same as the frequency point of the source cell.

(23) And the source cell measures the measurement result of the terminal.

(24) Load status of neighbor cells. The load status may be obtained according to existing mechanisms.

(25) Load status of the source cell.

In one embodiment, the uplink and downlink effective bandwidths of the neighbor cells may be estimated.

Fig. 2 is a flow chart of an uplink and downlink effective bandwidth estimation method of a neighboring cell according to an embodiment of the present application, as shown in fig. 2, the method includes the following steps:

1. and acquiring uplink and downlink resource conditions of the neighbor cell, wherein the resource conditions comprise the utilization rate of physical resource blocks (Physical Resource Block, PRB) and idle bandwidth.

2. Calculating the uplink and downlink rates of the UE, judging that the UE is an uplink large-traffic user if the uplink rate is larger than a preset threshold, judging that the UE is a downlink large-traffic user if the downlink rate is larger than the preset threshold, and judging that the UE is a non-large-traffic user if the downlink rate is larger than the preset threshold. When the uplink rate and the downlink rate of the UE are both greater than a preset threshold, it may be determined that the UE belongs to an uplink large traffic user or a downlink large traffic user according to a preset rule. For example, when the uplink rate and the downlink rate of the UE are both greater than a preset threshold, the UE is determined to be an uplink large-traffic user, or when the uplink rate and the downlink rate of the UE are both greater than a preset threshold, the UE is determined to be a downlink large-traffic user.

3. If the UE is an uplink large-traffic user, comparing the uplink idle bandwidth of the adjacent cell with the maximum uplink bandwidth supported by the UE, and taking a small value from the uplink idle bandwidth and the maximum uplink bandwidth as an uplink effective bandwidth. When the uplink free bandwidth of the adjacent cell is larger, in order to avoid estimation distortion of the uplink effective bandwidth, if the uplink PRB utilization rate of the adjacent cell is higher than a preset threshold or the number of active users is higher than a preset threshold, the uplink effective bandwidth is unchanged, otherwise, the uplink effective bandwidth=the uplink effective bandwidth/(the number of active users of the candidate target cell+1). The active user number refers to a user who has uplink data or downlink data transmission. And taking the finally obtained uplink effective bandwidth as the uplink effective bandwidth of the neighbor cell available to the UE, and exiting the estimation process.

4. If the UE is a downlink user with large traffic, comparing the downlink idle bandwidth of the adjacent cell with the maximum downlink bandwidth supported by the UE, and taking a small value from the two as the downlink effective bandwidth. When the downlink idle bandwidth of the adjacent cell is larger, in order to avoid estimation distortion of the downlink effective bandwidth, if the downlink PRB utilization rate of the adjacent cell is higher than a preset threshold or the number of active users is higher than a preset threshold, the downlink effective bandwidth is unchanged, otherwise, the downlink effective bandwidth=the downlink effective bandwidth/(the number of active users of the candidate target cell+1). The active user number refers to a user who has uplink data or downlink data transmission. And taking the finally obtained downlink effective bandwidth as the downlink effective bandwidth of the available neighbor cell of the UE, and exiting the estimation process.

In some embodiments, the parameter prediction result may further include one or more of the following:

cell identity of the neighbor cell. The method is used for marking the cell corresponding to the parameter prediction result.

The reliability of the parameter prediction result. The method for selecting the target cell provided by the embodiment of the application can be used for representing the reliability of the parameter prediction result, and when the reliability of one or more parameters in the parameter prediction result is smaller than a preset threshold, the target cell can be selected according to the existing mechanism instead of the method for selecting the target cell provided by the embodiment of the application.

In some embodiments, the handover optimization request information may include one or more of the following:

(3) The first indication information is used for indicating to start, update or stop collecting sample parameter information.

(4) And the first period information is used for indicating the period of sending the sample parameter information to the source network equipment.

(5) The first direction information is used for indicating uplink information and/or downlink information in the collected sample parameter information.

(6) And the second indication information is used for indicating the type of the sample parameter information required to be acquired. For example, whether to collect spectral efficiency parameters and/or whether to collect user experience parameters.

(7) Data granularity identification. The second network device may collect user experience parameters obtained by measuring data corresponding to the data granularity identifier. The data granularity identification may be at least one of a slice identification, a 5QI identification, a QoS flow identification, a PDU session identification, and a UE identification.

(8) QoS parameter type. The QoS parameter type may be at least one of rate, packet loss rate, retransmission rate, delay, transmission queue length, and packet jitter.

(9) Service type. The second network device may collect user experience parameters corresponding to the service type. The traffic type may be at least one of voice, video, and traffic type (using serviceType delivery in AppLayerMeasConfig field) defined in 3GPP technical specification 38.331 for application layer measurements.

(10) Identification of sample terminals. The second network device may determine, according to the identity of the sample terminal, a terminal that needs to collect information. The identity of the sample terminal may be an identity of the sample terminal on the neighbor cell and/or the source cell, e.g. the identity of the sample terminal may be at least one of Source NG-RAN node UE XnAP ID、Target NG-RAN node UE XnAP ID、gNB-CU UE F1AP ID、gNB-DU UE F1AP ID、RAN UE ID、IMEI、IMSI、GUTI、SUPI、SUCI and RNTI.

(11) The first time length information is used for indicating a time period for collecting sample parameter information.

(12) And the third indication information is used for indicating to start, update or stop sending the parameter prediction model to the source network equipment.

(13) And second period information for indicating a period of transmitting the parameter prediction model to the source network device.

(14) Cell identity of the source cell. Wherein the cell identity may be at least one of CGI, PCI, ARFCN, TAC, RANAC and a PLMN.

(15) Cell identity of the target cell. Wherein the cell identity may be at least one of CGI, PCI, ARFCN, TAC, RANAC and a PLMN.

(16) And the fourth indication information is used for indicating feedback information after the acquisition terminal starts, updates or stops switching to the target cell.

(17) And third period information for indicating a period of transmitting feedback information to the source network device.

(18) And the second direction information is used for indicating the uplink information and/or the downlink information in the acquisition feedback information.

(19) Fifth indicating information for indicating the type of feedback information that needs to be collected. For example, whether to collect spectral efficiency parameters and/or whether to collect user experience parameters.

(20) And (5) identification of the terminal. The second network device may determine, according to the identity of the terminal, the terminal that needs to collect the information. The identity of the terminal may be at least one of Source NG-RAN node UE XnAP ID、Target NG-RAN node UE XnAP ID、gNB-CU UE F1AP ID、gNB-DU UE F1AP ID、RAN UE ID、IMEI、IMSI、GUTI、SUPI、SUCI and RNTI.

(21) And the second time length information is used for indicating a time period for collecting the feedback information.

(22) And the sixth indication information is used for indicating that the target cell is obtained by prediction and/or the credibility of the parameter prediction result. When the sixth indication information includes the reliability of the parameter prediction result, whether to switch the terminal to the target cell may also be determined according to the reliability of the parameter prediction result. For example, when the reliability of one or more parameters in the parameter prediction result is less than the preset threshold, the method for selecting the target cell provided by the embodiment of the present application may not be used, but the target cell may be selected according to an existing mechanism.

In some embodiments, the method further comprises:

receiving feedback information sent by second network equipment;

and optimizing the parameter prediction model based on the feedback information.

Specifically, the prediction accuracy of the trained parameter prediction model may not be high, and at this time, feedback information after the terminal is handed over to the target cell may be used as a sample to be input into the parameter prediction model (for example, as a feedback (report) parameter of reinforcement learning), so as to optimize the parameter prediction model and improve the prediction accuracy of the parameter prediction model.

In some embodiments, selecting a target cell to which the terminal is handed over based on the parameter prediction result includes:

based on the parameter prediction result, estimating the uplink capacity and/or the downlink capacity of the terminal on the adjacent cell;

and selecting a target cell to which the terminal is switched based on the uplink capacity and/or the downlink capacity of the terminal on the adjacent cell.

Specifically, after the parameter prediction result is obtained, the source network device may estimate uplink capability and/or downlink capability of the terminal on the neighboring cell according to the parameter prediction result.

In an embodiment, when the parameter prediction result includes uplink and/or downlink spectrum efficiency parameters of the terminal on the neighboring cell, uplink and/or downlink capacity of the terminal on the neighboring cell may be estimated based on the uplink and/or downlink spectrum efficiency parameters of the terminal on the neighboring cell.

For example, the uplink capability and/or the downlink capability of the terminal on the neighboring cell may be estimated by:

Uplink capability of terminal on neighbor = uplink of terminal on neighbor line spectral efficiency parameter the uplink effective bandwidth of the terminal on the neighbor cell.

Downlink capability of terminal on neighbor = downlink of terminal on neighbor line spectral efficiency parameter the effective downlink bandwidth of the terminal in the neighboring cell.

In an embodiment, when the parameter prediction result includes a user experience parameter of the terminal on the neighboring cell, uplink capability and/or downlink capability of the terminal on the neighboring cell may be estimated based on the user experience parameter of the terminal on the neighboring cell.

Uplink capability of terminal on neighbor = uplink rate of terminal in user experience parameters on neighbor.

Downlink capability of terminal on neighbor = downlink rate of terminal in user experience parameters on neighbor.

After the uplink capacity and/or the downlink capacity of the terminal on the neighboring cell are estimated, the target cell to which the terminal is switched can be selected based on the uplink capacity and/or the downlink capacity of the terminal on the neighboring cell.

In some embodiments, selecting a target cell to which the terminal is handed over based on uplink capability and/or downlink capability of the terminal on the neighboring cell includes:

selecting adjacent cell with maximum corresponding uplink capacity and/or downlink capacity, determining as target cell to which the terminal is switched, or

And selecting a target cell to which the terminal is switched based on the uplink capacity and/or the downlink capacity of the terminal on the adjacent cell and the traffic type of the terminal.

Specifically, after the uplink capability and/or the downlink capability of the terminal on the neighboring cells are estimated, the neighboring cell with the largest corresponding uplink capability and/or downlink capability can be selected, and the neighboring cell is determined to be the target cell to which the terminal is switched.

Or the target cell to which the terminal is switched can also be selected based on the uplink capability and/or the downlink capability of the terminal on the neighboring cell and the traffic type of the terminal (the terminal is an uplink large traffic user or a downlink large traffic user).

In some embodiments, selecting a target cell to which the terminal is handed over based on the uplink capability and/or the downlink capability of the terminal on the neighboring cell, and the traffic type of the terminal, includes:

If the terminal is the uplink user with large service volume, selecting the target cell to which the terminal is switched from the adjacent cell with the largest corresponding uplink capacity and the corresponding uplink capacity larger than the uplink capacity of the terminal on the source cell, or

And selecting a target cell to which the terminal is switched from the adjacent cells which have the largest corresponding downlink capacity and have the corresponding downlink capacity larger than the downlink capacity of the terminal on the source cell under the condition that the terminal is a downlink user with large service volume.

Specifically, when a target cell to which a terminal is handed over is selected based on the uplink capability and/or downlink capability of the terminal on a neighboring cell and the traffic type of the terminal (whether the terminal is an uplink high traffic user or a downlink high traffic user), the uplink and/or downlink capability on the source cell may be determined first.

In one embodiment, when the uplink and/or downlink capability of the terminal on the neighboring cell is determined based on the spectrum efficiency parameter of the terminal on the neighboring cell, the uplink and/or downlink capability of the source cell may also be determined according to the spectrum efficiency parameter of the terminal on the source cell.

For example, the uplink and/or capability on the source cell may be determined by:

Uplink capability on source cell = uplink spectrum efficiency parameter on source cell for terminal uplink bandwidth used on source cell for terminal.

Downlink capability on source cell = downlink spectrum efficiency parameter on source cell for terminal downlink bandwidth used on source cell for terminal.

In one embodiment, when the uplink and/or downlink capabilities of the terminal on the neighboring cell are determined based on the user experience parameters of the terminal on the neighboring cell, the uplink and/or downlink capabilities of the source cell may also be determined according to the user experience parameters of the terminal on the source cell.

Uplink capability on source cell = uplink rate of terminal in user experience parameters on source cell. The uplink rate of the terminal in the user experience parameter on the source cell may be an average value or a sampling value in the last unit time.

Downlink capability on source cell = downlink rate of terminal in user experience parameters on source cell. The downlink rate of the terminal in the user experience parameter on the source cell may be an average value or a sampling value in the last unit time.

And under the condition that the terminal is an uplink large-traffic user, selecting a target cell to which the terminal is switched from the adjacent cells which have the largest corresponding uplink capacity and have the corresponding uplink capacity larger than the uplink capacity of the terminal on the source cell.

In one embodiment, when there are a plurality of neighbor cells having the largest corresponding uplink capability and having a larger corresponding uplink capability than the uplink capability of the terminal on the source cell, the cell having the largest downlink capability may be selected as the target cell from the neighbor cells. When there are also a plurality of cells having the largest downlink capability, at least one neighbor cell having the best one of the CQI, the uplink MCS Index, the downlink MCS Index, and the measurement result of the UE may be selected as the target cell.

In one embodiment, when there are a plurality of neighbor cells having the largest corresponding downlink capability and having a larger corresponding downlink capability than the downlink capability of the terminal on the source cell, the cell having the largest uplink capability may be selected as the target cell from the neighbor cells. When there are also a plurality of cells having the largest uplink capacity, at least one neighbor cell having the best one of the CQI, the uplink MCS Index, the downlink MCS Index, and the measurement result of the UE may be selected as the target cell.

In some embodiments, when the parameter prediction result includes the optimal neighbor cell identifier corresponding to the terminal, the optimal neighbor cell may be directly selected as the target cell to which the terminal is switched.

Fig. 3 is a second flowchart of a method for selecting a target cell according to an embodiment of the present application, as shown in fig. 3, where the method is applied to a second network device, and includes the following steps:

and 300, receiving switching optimization request information sent by source network equipment.

Step 301, according to the handover optimization request information, one or more of the following are sent to the source network device:

sample parameter information for training a parameter prediction model;

A parameter prediction model;

Feedback information after the terminal is switched to the target cell;

The parameter prediction result comprises performance parameters and/or optimal neighbor cell identifiers corresponding to the terminal after the terminal is switched to the neighbor cell, wherein the performance parameters and/or the optimal neighbor cell identifiers are predicted based on the parameter prediction model.

Specifically, when the target cell to which the terminal needs to be switched needs to be selected, the second network device may receive the switching optimization request information sent by the source network device.

The second network device may be any of gNB, eNB, ng-eNB, en-gNB, CU of gNB, CUCP of gNB, CUUP of gNB, DU of gNB, RIC or newly defined network node. The source network device may be any of gNB, eNB, ng-eNB, en-gNB, CU of gNB, CUCP of gNB, CUUP of gNB, DU of gNB, RIC or newly defined network node.

In one embodiment, when the parameter prediction model needs to be trained, the second network device may receive the handover optimization request information sent by the source network device, and send sample parameter information to the source network device according to the handover optimization request information. The second network device may be the network device where the neighbor cell of the source cell is located.

In one embodiment, when the parameter prediction model is stored in the second network device, the second network device may receive the handover optimization request information sent by the source network device, and send the parameter prediction model to the source network device according to the handover optimization request information.

In an embodiment, when the target cell is within the range of the second network device, the second network device may receive the handover optimization request information sent by the source network device, and send feedback information after the terminal is handed over to the target cell to the source network device according to the handover optimization request information.

In one embodiment, when the parameter prediction model is stored on the second network device, the second network device may not send the parameter prediction model to the source network device, but use the parameter prediction model to perform prediction to obtain a parameter prediction result. The second network device may receive the handover optimization request information sent by the source network device, and send a parameter prediction result to the source network device according to the handover optimization request information. The second network device may obtain the input parameters of the parameter prediction model from the source network device, or may directly obtain the input parameters of the parameter prediction model from the neighboring cell of the source cell, and then obtain the parameter prediction result according to the input parameters of the parameter prediction model, and send the parameter prediction result to the source network device.

According to the method for selecting the target cell, the second network equipment receives the switching optimization request information sent by the source network equipment, and sends at least one of sample parameter information, the parameter prediction model, feedback information after the terminal is switched to the target cell and the parameter prediction result to the source network equipment according to the switching optimization request information, so that the source network equipment can determine the parameter prediction result, and therefore the cell with the largest uplink and downlink capacity is selected as the target cell to which the terminal is switched according to the parameter prediction result, and user performance is improved.

In some embodiments, the sample parameter information may include one or more of the following:

(3) Identification of the serving beam on the sample neighbor.

(4) Identification of the serving beam on the sample source cell.

(5) Identification of sample terminals. The identity of the terminal may be at least one of Source NG-RAN node UE XnAP ID、Target NG-RAN node UE XnAP ID、gNB-CU UE F1AP ID、gNB-DU UE F1AP ID、RAN UE ID、IMEI、IMSI、GUTI、SUPI、SUCI and RNTI.

(13) The number of downlink transmission antennas of the sample source cell.

(14) The number of uplink receive antennas of the sample source cell.

(15) The number of uplink transmit antennas of the sample terminal.

(16) The number of downlink receive antennas of the sample terminal.

(21) CQI and/or downlink MCS Index of the sample terminal.

(22) Uplink MCS Index of the sample terminal.

(24) The load state of the sample source cell.

(25) And the uplink spectrum efficiency parameter and/or the downlink spectrum efficiency parameter of the sample terminal on the sample adjacent cell.

(26) The uplink bandwidth and/or the downlink bandwidth of the sample terminal on the sample neighbor cell.

(27) User experience parameters of sample terminals on sample neighbor cells.

The methods provided by the embodiments of the present application are based on the same application conception, so that the implementation of each method can be referred to each other, and the repetition is not repeated.

The method provided by each of the above embodiments of the present application is illustrated below by way of example of a specific application scenario.

Example one, a target cell to which a terminal is handed over is selected.

And the third network equipment predicts the performance parameters of the UE after being switched to the adjacent cell according to the data acquired by the source cell and/or the data acquired by the adjacent cell of the source cell, and selects the proper adjacent cell as the switched target cell according to the predicted performance parameters of the UE after being switched to the adjacent cell. The third network device may be the same as the base station where the source cell is located, may be the same as the base station where the neighbor cell is located, or may be different from both the base station where the source cell is located and the base station where the neighbor cell is located.

Fig. 4 is a third flowchart of a method for selecting a target cell according to an embodiment of the present application, as shown in fig. 4, the method includes the following steps:

1. A machine learning method is used for training a parameter prediction model for predicting performance parameters of the UE after the UE is connected to a neighboring cell.

In training, the sample information includes at least one of the following information:

A cell identity of the source cell, which may be at least one of CGI, PCI, ARFCN, TAC, RANAC, PLMN;

cell identification of a sample neighbor cell;

Identification of the service beam on the sample neighbor;

identification of the serving beam on the sample source cell;

the identity of the sample UE may be an identity of the sample UE on a neighbor cell and/or an identity on a source cell, e.g. at least one of Source NG-RAN node UE XnAP ID、Target NG-RAN node UE XnAP ID、gNB-CU UE F1AP ID、gNB-DU UE F1AP ID、RAN UE ID、IMEI、IMSI、GUTI、SUPI、SUCI and RNTI;

The downlink transmitting power of the sample adjacent cell can be actual power and/or maximum power;

the downlink transmitting power of the service beam on the sample adjacent cell can be actual power and/or maximum power;

the downlink transmitting power of the sample source cell can be actual power and/or maximum power;

the downlink transmitting power of the service beam on the sample source cell can be actual power and/or maximum power;

The uplink transmission power of the sample UE may be actual power and/or maximum power;

the number of downlink transmitting antennas of the sample neighbor cell;

the number of uplink receiving antennas of the sample neighbor cell;

the number of downlink transmitting antennas of the sample source cell;

the number of uplink receiving antennas of the sample source cell;

the uplink transmission antenna number of the sample UE;

the number of downlink receiving antennas of the sample UE;

The downlink bandwidth used by the sample UE;

The uplink bandwidth used by the sample UE;

at least one cell with different frequency points from the cell of the sample source, which is reported by the sample UE;

The measurement result of at least one cell which is reported by the sample UE and is the same as the frequency point of the sample source cell;

A measurement result of the sample source cell for measuring the sample UE;

CQI and/or downlink MCS Index of the sample UE;

Uplink MCS Index of the sample UE;

Load state of the sample neighbor cell;

The load state of the sample source cell;

A downlink spectrum efficiency parameter of the sample UE;

Uplink spectrum efficiency parameters of the sample UE;

Sample UE user experience parameters.

The measurement result of the sample neighbor cell for measuring the sample UE may include at least one of a measurement result of the sample neighbor cell for measuring SRS of the sample UE, a measurement result of the sample neighbor cell for measuring other uplink reference signals of the sample UE, and a measurement result of the sample neighbor cell for measuring NR-U channel used by the sample UE.

The load status of the sample neighbor may include some or all of the information reported by the Resource Status Reporting procedure defined in the XnAP protocol in the existing mechanism.

The user experience parameter may include at least one of the following information:

Uplink QoS parameters;

downlink QoS parameters;

QoE parameters.

the data granularity identifier indicates that the rest of QoS parameters are measured based on data corresponding to the data granularity identifier, and the data granularity identifier can be at least one of a slice identifier, a 5QI identifier, a QoS flow identifier, a PDU session identifier and a UE identifier;

A rate, which may be a rate of a different protocol layer, such as at least one of a MAC layer rate, an RLC layer rate, and a PDCP layer rate;

a packet loss rate, which may be a number of transmission losses or transmission failures per unit time, such as at least one of RLC layer packet loss rate, PDCP packet loss rate, and HARQ transmission failure rate;

A retransmission rate, which may be the number of retransmissions per unit time, such as at least one of RLC layer retransmission rate, PDCP retransmission rate, and HARQ retransmission rate;

The delay may include at least one of, one, more, and a sum of the components of the RAN-side delay (RAN part of delay) in the 3GPP technical specification 38.314;

a transmission queue length, which may be a transmission queue length of a different protocol layer, such as an RLC layer transmission queue length and/or a PDCP layer transmission queue length;

Packet jitter, which may be packet jitter of different protocol layers, such as RLC layer packet jitter and/or PDCP layer packet jitter.

Wherein the QoE parameters may comprise at least one of the following information:

A traffic type, which may be at least one of voice, video, and traffic type for application layer measurement (using serviceType delivery in AppLayerMeasConfig field) defined in 3GPP technical specification 38.331;

At least one information in an application layer measurement report that is consistent with an application layer measurement report (delivered using measReportAppLayerContainer) used in 3GPP technical specification 38.331;

At least one of the RAN visible measurement reports is information consistent with the RAN visible measurement report (communicated using RAN-VisibleMeasurements) used in the 3GPP technical specification 38.331.

The spectrum efficiency parameter may be a spectrum efficiency parameter corresponding to all or part of resources of the cell, for example, a spectrum efficiency parameter of all bandwidths of the cell, a spectrum efficiency parameter of PDSCH resources, or a spectrum efficiency parameter of PUSCH resources. The method for calculating the spectrum efficiency parameter can be any one of the following methods:

the spectrum efficiency parameter is spectrum efficiency, namely the data quantity which can be transmitted in unit spectrum.

Dividing the minimum value and the maximum value of the spectrum efficiency supported by the cell into a plurality of intervals, wherein each interval corresponds to a characterization value. The spectrum efficiency of the UE belongs to which interval, and the spectrum efficiency parameter is a representation value of the interval. The characterization value may be a numerical value, for example, a fraction corresponding to the interval when the maximum value is 100 minutes and the minimum value is 0 minutes, may be the number of the interval, may be the maximum value, the minimum value, the median or the average value of the spectrum efficiency in the interval, or may be an indication information, for example, indicate that the spectrum efficiency is high, medium or low.

Dividing the UE with the uplink signal and/or downlink signal receiving and transmitting state close to each other in the cell into different groups, for example, dividing the UE1 and the UE2 into the same groups if the UE1 and the UE2 have a plurality of same adjacent cells and the mean square error of the uplink and/or downlink signal measurement values of the two UE in all the same adjacent cells is smaller than a preset threshold value. The spectral efficiency parameter is the maximum, minimum, median or average of the spectral efficiency of all UEs in the group to which the UE belongs.

Methods of machine learning may include, but are not limited to, reinforcement learning.

Training of the parametric prediction model may be performed at a third network device.

The source cell and/or the neighbor cell transmits the acquired sample information to the third network device according to the request of the third network device.

The third network device sends switching optimization request information to the source cell and/or the adjacent cell, wherein the switching optimization request information comprises at least one of the following information:

Cell identification of the sample source cell;

cell identification of a sample neighbor cell;

the first indication information is used for indicating to start, update or stop collecting sample parameter information;

the system comprises first period information, wherein the first period information is used for indicating a period for sending sample parameter information to source network equipment;

the first direction information is used for indicating uplink information and/or downlink information in the collected sample parameter information;

the second indication information is used for indicating the type of the sample parameter information to be acquired;

Data granularity identification;

Quality of service QoS parameter types;

A service type;

Identification of the sample terminal;

the first time length information is used for indicating a time period for collecting sample parameter information;

the third indication information is used for indicating to start, update or stop sending the parameter prediction model to the source network equipment;

The second period information is used for indicating the period of sending the parameter prediction model to the source network equipment;

cell identification of the source cell;

Cell identification of the target cell;

The fourth indication information is used for indicating feedback information after starting, updating or stopping the acquisition terminal to switch to the target cell;

Third period information for indicating a period of transmitting feedback information to the source network device;

The second direction information is used for indicating to collect uplink information and/or downlink information in the feedback information;

fifth indicating information for indicating the type of feedback information to be acquired;

Identification of the terminal;

the second time length information is used for indicating a time period for collecting feedback information;

And the sixth indication information is used for indicating that the target cell is obtained by prediction and/or the credibility of the parameter prediction result.

And the source cell and/or the adjacent cell sends the acquired sample information to the third network equipment according to the switching optimization request information.

The input parameters of the parametric prediction model include one or more of the following:

cell identification of the neighbor cell;

Identification of the service beam on the neighbor cell;

cell identification of the source cell;

An identification of the serving beam on the source cell;

Identification of the terminal;

downlink transmitting power of the adjacent cell;

Downlink transmission power of the service beam on the neighbor cell;

Downlink transmitting power of source cell;

Downlink transmit power of the serving beam on the source cell;

uplink transmitting power of the terminal;

The number of downlink transmitting antennas of the neighboring cell;

the number of uplink receiving antennas of the neighboring cell;

The number of downlink transmitting antennas of the source cell;

The number of uplink receiving antennas of the source cell;

the number of uplink transmitting antennas of the terminal;

The number of downlink receiving antennas of the terminal;

uplink effective bandwidth of the terminal on the adjacent cell;

the downlink effective bandwidth of the terminal on the adjacent cell;

uplink idle bandwidth of neighbor cells;

Downlink idle bandwidth of neighbor cell;

the terminal reports the measurement result of at least one cell different from the frequency point of the source cell;

The terminal reports the measurement result of at least one cell which is the same as the frequency point of the source cell;

the source cell measures the measurement result of the terminal;

The load state of the neighbor cell;

Load status of the source cell. Wherein the uplink or downlink effective bandwidth of the neighboring cell can be estimated, the following is an estimated algorithm:

(1) And acquiring the uplink and downlink resource conditions of the neighbor cell, wherein the resource conditions comprise PRB utilization rate and idle bandwidth.

(2) Calculating the uplink and downlink rates of the UE, judging that the UE is an uplink large-traffic user if the uplink rate is larger than a preset threshold, judging that the UE is a downlink large-traffic user if the downlink rate is larger than the preset threshold, and judging that the UE is a non-large-traffic user if the downlink rate is larger than the preset threshold. When the uplink rate and the downlink rate of the UE are both greater than a preset threshold, it may be determined that the UE belongs to an uplink large traffic user or a downlink large traffic user according to a preset rule. For example, when the uplink rate and the downlink rate of the UE are both greater than a preset threshold, the UE is determined to be an uplink large-traffic user, or when the uplink rate and the downlink rate of the UE are both greater than a preset threshold, the UE is determined to be a downlink large-traffic user.

(3) If the UE is an uplink large-traffic user, comparing the uplink idle bandwidth of the adjacent cell with the maximum uplink bandwidth supported by the UE, and taking a small value from the uplink idle bandwidth and the maximum uplink bandwidth as an uplink effective bandwidth. When the uplink free bandwidth of the adjacent cell is larger, in order to avoid estimation distortion of the uplink effective bandwidth, if the uplink PRB utilization rate of the adjacent cell is higher than a preset threshold or the number of active users is higher than a preset threshold, the uplink effective bandwidth is unchanged, otherwise, the uplink effective bandwidth=the uplink effective bandwidth/(the number of active users of the candidate target cell+1). The active user number refers to a user who has uplink data or downlink data transmission. And taking the finally obtained uplink effective bandwidth as the uplink effective bandwidth of the neighbor cell available to the UE, and exiting the estimation process.

(4) If the UE is a downlink user with large traffic, comparing the downlink idle bandwidth of the adjacent cell with the maximum downlink bandwidth supported by the UE, and taking a small value from the two as the downlink effective bandwidth. When the downlink idle bandwidth of the adjacent cell is larger, in order to avoid estimation distortion of the downlink effective bandwidth, if the downlink PRB utilization rate of the adjacent cell is higher than a preset threshold or the number of active users is higher than a preset threshold, the downlink effective bandwidth is unchanged, otherwise, the downlink effective bandwidth=the downlink effective bandwidth/(the number of active users of the candidate target cell+1). The active user number refers to a user who has uplink data or downlink data transmission. And taking the finally obtained downlink effective bandwidth as the downlink effective bandwidth of the available neighbor cell of the UE, and exiting the estimation process.

The parameter prediction result comprises one or more of the following:

The neighbor cell measures the measurement result of the terminal;

CQI and/or downlink MCS Index of the terminal;

uplink MCS Index of the terminal;

A downlink spectrum efficiency parameter of the terminal on the adjacent cell;

uplink spectrum efficiency parameters of the terminal on the adjacent cell;

user experience parameters of the terminal on the neighbor cell;

cell identification of the neighbor cell;

reliability of the parameter prediction result;

cell identity of the optimal neighbor cell.

The parameter prediction results are predictions of some performance parameters assuming the UE is connected to the neighbor cell.

In the training process, a part of sample information can be selected as feedback information of a model prediction result to be input into the model, for example, as feedback (reward) parameters of reinforcement learning, so as to help to improve the prediction accuracy of the parameter prediction model.

The source cell may obtain the parameter prediction result in any one of the following two ways.

Mode one:

the source cell sends switching optimization request information to the adjacent cell, and the adjacent cell sends collected sample information to the source cell according to the switching optimization request information. The source cell generates input parameters of the parameter prediction model according to one or more of the received sample information and information acquired by the source cell (for example, measurement results of at least one cell which is the same as the frequency point of the source cell and reported by the UE).

The source cell sends a first message to the third network device, wherein the first message comprises input parameters of the parameter prediction model.

And the third network equipment uses the parameter prediction model to infer a parameter prediction result according to the input parameters of the parameter prediction model.

The third network device sends a second message to the source cell, wherein the second message comprises a parameter prediction result.

Mode two:

the source cell sends a third message to the third network device, wherein the third message comprises at least one of the following information:

And second period information for indicating a period of transmitting the parameter prediction model to the source network device.

And the third network equipment sends a fourth message to the source cell according to the third message, wherein the fourth message comprises the parameter prediction model.

The source cell generates input parameters of the parameter prediction model according to the method in mode one.

And the source cell uses the parameter prediction model to infer a parameter prediction result according to the input parameters of the parameter prediction model.

2. The source cell selects the UE that needs to be handed over. The selection condition includes that the signal strength of the source cell measured by the UE is smaller than a preset threshold, and the UE is judged to be the UE needing to be switched in the uplink large traffic or the downlink large traffic or other existing mechanisms.

The source cell may select one or more sufficiently good signal neighbors according to existing mechanisms. If there is only one selected adjacent cell, the cell is used as the target cell to execute the switch, otherwise, the following process is executed.

3. If the source cell selects a plurality of adjacent cells with good enough signals, the source cell also needs to determine a target cell according to uplink and downlink capabilities. And after the target cell is selected, executing the switching.

The source cell can estimate the uplink and downlink capacities of the neighbor cells according to the parameter prediction results.

Fig. 5 is a schematic flow chart of estimating uplink and downlink capacities of neighboring cells and selecting a target cell according to a parameter prediction result provided in an embodiment of the present application, and as shown in fig. 5, the method includes the following steps:

A. And estimating the uplink capacity and/or the downlink capacity of each adjacent cell according to the parameter prediction result.

If the parameter prediction result includes the downlink spectrum efficiency parameter of the UE and/or the uplink spectrum efficiency parameter of the UE, estimating the uplink capability and/or the downlink capability of each neighboring cell according to the following method:

and selecting each adjacent cell in turn, and estimating the uplink capacity and/or the downlink capacity of the UE on the adjacent cell.

If the parameter prediction result includes the user experience parameter of the UE, estimating the uplink capacity and/or the downlink capacity of each neighboring cell according to the following method:

B. And selecting the cell with the largest uplink capacity and/or downlink capacity in all the adjacent cells.

C. the uplink and/or downlink capabilities of the UE on the source cell are estimated.

When the uplink and/or downlink capacity of the terminal on the neighboring cell is determined based on the spectrum efficiency parameter of the terminal on the neighboring cell, the uplink and/or downlink capacity of the source cell may also be determined according to the spectrum efficiency parameter of the terminal on the source cell.

When the uplink and/or downlink capacity of the terminal on the neighboring cell is determined based on the user experience parameter of the terminal on the neighboring cell, the uplink and/or downlink capacity of the source cell may also be determined according to the user experience parameter of the terminal on the source cell.

The method for calculating the spectrum efficiency parameter of the source cell is the same as the method for calculating the spectrum efficiency parameter in the sample information.

D. if the UE is an uplink large-traffic user, selecting a cell with the largest uplink capacity in a neighbor cell and larger than the uplink capacity of a source cell, if the UE is the uplink large-traffic user, selecting a cell with the largest downlink capacity in the remaining neighbor cells, if the UE is the downlink large-traffic user, selecting a cell with the largest downlink capacity in the neighbor cells, and if the UE is the downlink large-traffic user, selecting a cell with the largest downlink capacity in the remaining neighbor cells, selecting a cell with the largest uplink capacity in the remaining neighbor cells, and if the UE is the downlink large-traffic user, selecting a cell with the largest downlink capacity in the remaining neighbor cells, wherein the UE is the CQI, the uplink MCS Index, the downlink MCS Index of the UE and at least one optimal cell in the measurement results of the UE.

Otherwise, the cell selected in step B is selected.

And executing the switching by taking the selected cell as a target cell.

E. If the parameter prediction model is trained in the source cell, the source cell may require the target cell to send feedback information. The feedback information may include one or more of the following:

Identification of the target cell;

The target cell measures the measurement result of the terminal;

identification of the serving beam on the target cell;

CQI and/or downlink MCS Index of the terminal;

uplink MCS Index of the terminal;

a downlink spectrum efficiency parameter of a terminal on a target cell;

Uplink spectrum efficiency parameters of the terminal on the target cell;

user experience parameters of the terminal on the target cell.

F. The source cell optimizes the parameter prediction model according to the feedback information, for example, the feedback information is used as a reward parameter input of the parameter prediction model, and the prediction accuracy of the parameter prediction model is improved.

Steps E-F are not necessary.

The reliability of parameter prediction may be considered in selecting the target cell. For example, if the reliability of one or more output parameters in the parameter prediction result is less than a preset threshold, the method is exited, and the target cell is determined according to the existing mechanism.

And if the parameter prediction result comprises the optimal neighbor cell identifier corresponding to the terminal, the step A-D is omitted, the optimal neighbor cell is used as a target cell, and switching is executed. And then executing the rest steps according to the actual situation.

In the second example, the node sends the switching optimization request information to the node II, and the node II sends the information to the node I according to the switching optimization request information.

Node one may be any of gNB, eNB, ng-eNB, en-gNB, CU of gNB, CUCP of gNB, CUUP of gNB, DU of gNB, RIC or newly defined network node. Node two may be any of gNB, eNB, ng-eNB, en-gNB, CU of gNB, CUCP of gNB, CUUP of gNB, DU of gNB, RIC or newly defined network node.

Fig. 6 is a schematic flow chart of a process for sending a handover optimization request message to a second node by a node according to an embodiment of the present application, where the process includes the following steps as shown in fig. 6:

1. The node sends a message one to the node two. The first message includes handover optimization request information.

The first message may be an Xn interface message, an X2 interface message, an F1 interface message, an E1 interface message, or a RIC-supported message.

If message one is an Xn interface message, the Xn interface message may be at least one of RESOURCE STATUS REQUEST, a HANDOVER REQUEST, NG-RAN NODE CONFIGURATION UPDATE, and a newly defined Xn interface message (e.g., AI/ML INFORMATION REQUEST).

If message one is an X2 interface message, the X2 interface message may be at least one of RESOURCE STATUS REQUEST, a HANDOVER REQUEST, ENB CONFIGURATION UPDATE, and a newly defined X2 interface message.

If message one is an F1 interface message, the F1 interface message may be at least one of RESOURCE STATUS REQUEST、UE CONTEXT SETUP REQUEST、UE CONTEXT SETUP REQUEST、UE CONTEXT MODIFICATION REQUEST、GNB-CU CONFIGURATION UPDATE and a newly defined F1 interface message.

If message one is an E1 interface message, the E1 interface message may be at least one of RESOURCE STATUS REQUEST、GNB-CU-CP CONFIGURATION UPDATE、BEARER CONTEXT SETUP REQUEST、BEARER CONTEXT MODIFICATION REQUEST and a newly defined E1 interface message.

And the second node generates information required by the first node according to the switching optimization request information.

For example, the node one includes, in the handover optimization request information, indication information that a sample neighbor starts or updates acquisition sample information, and:

if the direction information of the downlink related information in the collected sample information and the indication information of the collected spectrum efficiency parameter are included, the node two starts to collect the sample information related to the downlink, for example, the information may include at least one of the following information:

the number of downlink transmitting antennas of the sample neighbor cell;

the number of downlink transmitting antennas of the sample source cell;

the number of downlink receiving antennas of the sample UE;

The downlink bandwidth used by the sample UE;

CQI and/or downlink MCS Index of the sample UE;

Load state of the sample neighbor cell;

The load state of the sample source cell;

and (5) a downlink spectrum efficiency parameter of the sample UE.

If the direction information of the uplink related information in the collected sample information and the indication information of the collected spectrum efficiency parameter are included, the node two starts to collect the sample information related to the uplink, for example, the information may include at least one of the following information:

the number of uplink receiving antennas of the sample neighbor cell;

the uplink transmitting power of the sample source cell can be actual power and/or maximum power;

the number of uplink receiving antennas of the sample source cell;

the uplink transmission antenna number of the sample UE;

The uplink bandwidth used by the sample UE;

the sample neighbor cell measures the measurement result of the sample UE;

A measurement result of the sample source cell for measuring the sample UE;

Uplink MCS Index of the sample UE;

Load state of the sample neighbor cell;

The load state of the sample source cell;

Uplink spectral efficiency parameters of the sample UE.

If the information indicating the acquisition of the user experience parameters is included, and the information includes a data granularity identifier and/or a QoS parameter type, for example, the data granularity identifier with the 5QI identifier being 1 and the QoS parameter type with the value being the rate are included, the node starts to acquire the user experience parameters, for example, the information may include at least one of the following information:

Uplink QoS parameters;

downstream QoS parameters.

Wherein the QoS parameters include at least one of the following information:

A data granularity identification, e.g., 5QI identification of 1;

A rate, e.g., a rate of 5QI for data identified as 1.

If the indication information for collecting the user experience parameters is included, and the information includes a service type, for example, the service type with a value of streaming, the second node selects UE, for example, UE configured with an application layer measurement report corresponding to the service type, and starts collecting the user experience parameters, for example, the information may include at least one of the following information:

QoE parameters.

Wherein the QoE parameters include at least one of the following information:

the service type, for example, value is streaming;

At least one of information in the application layer measurement report of the corresponding service, for example Initial Playout Delay, and/or Buffer Level.

The RAN for the corresponding service sees at least one information, e.g., initialPlayoutDelay, in the measurement report.

2. The node sends a message two to the node one.

Wherein message two may be an Xn interface message, an X2 message, an F1 interface message, an E1 interface message, or a RIC-supported message.

If message two is an Xn interface message, the Xn interface message may be at least one of RESOURCE STATUS UPDATE、RESOURCE STATUS RESPONSE、HANDOVER REPORT、ACCESS AND MOBILITY INDICATION、NG-RAN NODE CONFIGURATION UPDATE ACKNOWLEDGE、ENB CONFIGURATION UPDATE ACKNOWLEDGE、XN SETUP REQUEST、XN SETUP RESPONSE and a newly defined Xn interface message (e.g., AI/ML INFORMATION UPDATE).

If message two is an X2 interface message, the X2 interface message may be at least one of RESOURCE STATUS RESPONSE, RESOURCE STATUS UPDATE, HANDOVER REPORT, and a newly defined X2 interface message.

If message two is an F1 interface message, the F1 interface message may be at least one of RESOURCE STATUS RESPONSE、RESOURCE STATUS UPDATE、ACCESS AND MOBILITY INDICATION、GNB-DU CONFIGURATION UPDATE、GNB-CU CONFIGURATION UPDATE ACKNOWLEDGE、F1 SETUP REQUEST、UE CONTEXT SETUP RESPONSE、UE CONTEXT MODIFICATION RESPONSE and a newly defined F1 interface message.

If message two is an E1 interface message, the E1 interface message may be at least one of RESOURCE STATUS RESPONSE、RESOURCE STATUS UPDATE、GNB-CU-UP CONFIGURATION UPDATE ACKNOWLEDGE、BEARER CONTEXT SETUP RESPONSE、BEARER CONTEXT MODIFICATION RESPONSE、GNB-CU-CP MEASUREMENT RESULTS INFORMATION、BEARER CONTEXT MODIFICATION REQUIRED and a newly defined F1 interface message.

In one example, the first node includes indication information of starting or updating acquisition sample information of a cell in the handover optimization request information, and includes first period information, and the second node includes acquisition sample information of the second node, and periodically sends the second message to the second node according to the indication of the first period information.

Example three, gNB1 requires gNB2 to provide sample information.

Wherein gNB2 is composed of gNB-CUCP2, gNB-CUUP2 and gNB-DU 2.

Fig. 7 is a schematic flow chart of the gNB1 requesting the gNB2 to provide sample information according to an embodiment of the present application, and as shown in fig. 7, the process includes the following steps:

1. gNB-DU2 sends an F1 message SETUP REQUEST (F1 SETUP REQUEST) to gNB-CUCP2, including at least one of the following information:

cell identification of the managed cell;

an identification of the serving beam on the managed cell;

Maximum downlink transmit power of the managed cell;

maximum downlink transmit power of the serving beam on the managed cell;

the number of downlink transmitting antennas of the managed cell;

The number of uplink receive antennas of the managed cell.

2. GNB-CUCP2 sends an F1 message SETUP request RESPONSE (F1 SETUP RESPONSE) to gNB-DU 2.

Through the steps 1-2, gNB-CUCP2 acquires the downlink transmission power information of the wave beam of the cell managed by gNB-DU2, and/or antenna information.

The information received by gNB-CUCP2 may be sent to gNB1 using an Xn message, such as NG-RAN NODE CONFIGURATION UPDATE, or may be sent to gNB1 in step 11 as part of the sample information.

3. GNB1 finds that there is a neighbor cell of the cell on gNB1 on gNB2, and if the cell on gNB1 is used as a source cell for handover, the neighbor cell may become a target cell. gNB1 determines the training parameter prediction model. gNB1 requires gNB2 to report sample information.

The gNB1 sends an Xn message resource status request (RESOURCE STATUS REQUEST) to the gNB-CUCP2, including handover optimization request information including a cell identity of the source cell and a cell identity of the neighbor cell. The handover optimization request information may also include at least one of other information in the handover optimization request information.

The sample UE may be selected by gNB-CUCP2, by gNB-DU2, or by gNB-CUUP 2.

If the gNB-CUCP2 selects a sample UE, when selecting, the UE which can receive a source cell signal on a neighbor cell is preferentially selected, and in addition, if the switching optimization request information comprises a data granularity identifier and/or a service type, the UE which is transmitting the data corresponding to the data granularity identifier and/or the service type and/or the UE which is configured with the measurement of an application layer corresponding to the same service type are preferentially selected.

4. The gNB-CUCP2 sends an F1 message resource status request (RESOURCE STATUS REQUEST) to the gNB-DU2, including at least one of the handover optimization request information described in step 3, and if gNB-CUCP2 selects a sample UE, also includes the UE identity of the sample UE.

5. GNB-DU2 sends an F1 message resource status request response (RESOURCE STATUS RESPONSE) to gNB-CUCP2, including the UE identity of the sample UE if gNB-DU2 selects the sample UE.

6. The gNB-CUCP2 sends an E1 message resource status request (RESOURCE STATUS REQUEST) to the gNB-CUUP, including at least one of the handover optimization request information described in step 3, and if gNB-CUCP2 selects a sample UE, also includes the UE identity of the sample UE.

7. GNB-CUUP2 sends an F1 message resource status request response (RESOURCE STATUS RESPONSE) to gNB-CUCP2, including the UE identity of the sample UE if gNB-CUUP selects the sample UE.

8. GNB-CUCP2 sends an Xn message resource status request response to gNB1 (RESOURCE STATUS RESPONSE).

The gNB-CUCP2 may use the F1 message RESOURCE STATUS REQUEST to notify the gNB-DU2 of the updated handover optimization request information and/or use the E1 message RESOURCE STATUS REQUEST to notify the gNB-CUUP of the updated handover optimization request information, e.g., if the sample UE selected by gNB-CUUP2 and/or gNB-DU2 is different from the sample UE selected by gNB-CUCP2, the gNB-CUCP2 notifies the gNB-CUUP2 and/or gNB-DU2 of the updated sample UE.

Through the above steps, gNB-CUCP2 determines the selected sample UE. And configuring measurement of the frequency point of the source cell and/or measurement of the frequency point of the adjacent cell for the selected sample UE according to the existing mechanism by the gNB-CUCP to acquire a corresponding measurement report.

And if the handover optimization request information received by the gNB-DU2 comprises indication information for starting or updating acquisition sample information, the gNB-DU2 acquires the sample information of the sample UE according to the handover optimization request information. For example, the handover optimization request information includes indication information of a collected spectrum efficiency parameter, and the gNB-DU2 collects the spectrum efficiency parameter of the sample UE.

9. The gNB-DU2 sends F1 message resource status update (RESOURCE STATUS UPDATE) to the gNB-CUCP2 according to the requirement of the handover optimization request information, for example, according to the first period information, including sample information collected by the gNB-DU2, wherein the identification of the sample UE is used for the gNB-CUCP2 to find the corresponding UE context.

If the handover optimization request information received by the gNB-CUUP2 comprises indication information for starting or updating acquisition sample information, the gNB-CUUP2 acquires the sample information of the sample UE according to the handover optimization request information. For example, the handover optimization request information includes indication information for acquiring user experience parameters, and the gNB-CUUP2 acquires the user experience parameters of the sample UE on the gNB-CUUP.

10. The gNB-CUUP2 sends E1 message resource status update (RESOURCE STATUS UPDATE) to the gNB-CUCP2 according to the requirement of the handover optimization request information, for example, according to the first period information, including sample information collected by the gNB-CUUP2, wherein the identification of the sample UE is used by the gNB-CUCP2 to find the corresponding UE context.

11. If the handover optimization request information received by the gNB-CUCP2 includes indication information for starting or updating acquisition sample information, the gNB-CUCP sends an Xn message resource status update (RESOURCE STATUS UPDATE) to the gNB1 according to the requirement of the handover optimization request information, for example, according to first period information, including the sample information acquired by the gNB 2.

Through the steps, the gNB1 can acquire sample information acquired by the gNB2, and a parameter prediction model is trained.

12. The gNB1 sends an Xn message resource status request (RESOURCE STATUS REQUEST) to the gNB-CUCP2 including handover optimization request information including an indication to stop collecting sample information.

13. GNB-CUCP2 sends an F1 message resource status request (RESOURCE STATUS REQUEST) to gNB-DU2, including handover optimization request information including indication information to stop collecting sample information.

14. GNB-DU2 sends an F1 message resource status request response to gNB-CUCP2 (RESOURCE STATUS RESPONSE). The gNB-DU2 stops collecting sample information.

15. The gNB-CUCP2 sends an E1 message resource status request (RESOURCE STATUS REQUEST) to the gNB-CUUP, including handover optimization request information including an indication to stop collecting sample information.

16. GNB-CUUP2 sends an E1 message resource status request response to gNB-CUCP2 (RESOURCE STATUS RESPONSE). gNB-CUUP2 stopped collecting sample information.

17. GNB-CUCP2 sends an Xn message resource status request response to gNB1 (RESOURCE STATUS RESPONSE).

The gNB1 can select a proper target cell for the UE by using a parameter prediction model, so that the performance of the UE after switching is optimized to the greatest extent, and the user experience is improved.

The order of the messages in this example may be different from that shown in fig. 7.

Example four, gNB3 selects a target cell for the UE using a parametric prediction model.

Wherein the source cell of the UE is on gNB3 and the target cell is on gNB 4. gNB3 is composed of gNB-CUCP3, gNB-CUUP3 and gNB-DU3, and gNB4 is composed of gNB-CUCP4, gNB-CUUP4 and gNB-DU 4.

Fig. 8 is a schematic flow chart of selecting a target cell for a UE by using a parameter prediction model by the gNB3 according to an embodiment of the present application, and as shown in fig. 8, the process includes the following steps:

the source cell determines that the UE needs to be handed over to other cells.

1. GNB-CUCP3 sends an F1 message resource status request (RESOURCE STATUS REQUEST) to gNB-DU3, including handover optimization request information. The information comprises UE identification and indication information for acquiring user experience parameters.

2. GNB-DU3 sends an F1 message resource status request response to gNB-CUCP (RESOURCE STATUS RESPONSE).

3. And the gNB-DU3 acquires sample information according to the switching optimization request information. The gNB-DU3 sends an F1 message resource status update (RESOURCE STATUS UPDATE) to the gNB-CUCP including the collected sample information. The sample information comprises user experience parameters acquired by gNB-DU 3.

4. GNB-CUCP3 sends an E1 message resource status request (RESOURCE STATUS REQUEST) to gNB-CUUP3, including handover optimization request information. The information comprises UE identification and indication information for acquiring user experience parameters.

5. GNB-CUUP3 sends an E1 message resource status request response to gNB-CUCP3 (RESOURCE STATUS RESPONSE).

6. And the gNB-CUUP3 acquires sample information according to the switching optimization request information. gNB-CUUP3 sends an E1 message resource status update (RESOURCE STATUS UPDATE) to gNB-CUCP, including the collected sample information. The sample information comprises user experience parameters collected by gNB-CUUP.

And (3) acquiring user experience parameters of the UE in the source cell by the gNB-CUCP through the steps 1-6. Steps 1-6 are not necessary.

7. And the gNB-CUCP obtains the measurement result of the UE and determines the candidate target cell according to the measurement result.

8. And gNB-CUCP3 acquires the sample information of the neighbor cell. And the gNB-CUCP3 takes information in the sample information and/or information acquired by the gNB-CUCP3, such as at least one of a same-frequency measurement result, a different-frequency measurement result of the UE and a user experience parameter of the UE in a source cell, as input parameters of a parameter prediction model, and inferences are carried out to obtain a parameter prediction result.

9. And determining the target cell by the gNB-CUCP according to the parameter prediction result.

10. The gNB-CUCP sends an Xn message HANDOVER REQUEST (HANDOVER REQUEST) to the gNB-CUCP, including HANDOVER optimization REQUEST information. The handover optimization request information includes at least one of the following information:

cell identification of the source cell;

cell identification of candidate target cells;

an identification of the UE;

the indication information is used for indicating to collect spectrum efficiency parameters and/or collecting user experience parameters;

The time length is used for collecting sample information within a time period limited by the time length after the switching optimization request information is received;

indication information indicating that the target cell is predicted and/or including the reliability of the prediction, wherein the prediction may be a prediction of a user experience parameter on the target cell and/or a prediction of the target cell;

Any one or more of the other information in the handover optimization request information.

If the target cell in the Xn message HANDOVER REQUEST received by the gNB-CUCP4 is selected according to the user experience parameter on the predicted target cell and/or the target cell is predicted and includes the predicted reliability, the gNB-CUCP4 may decide whether to accept the HANDOVER according to the reliability, for example, the gNB-CUCP4 refuses the HANDOVER when the reliability is lower than a preset threshold.

11. The gNB-CUCP4 sends an E1 message bearer context request (BEARER CONTEXT SETUP REQUEST) to the gNB-CUUP, including at least one of the received handover optimization request information.

12. GNB-CUUP4 sends an E1 message bearer context request response to gNB-CUCP (BEARER CONTEXT SETUP RESPONSE).

13. GNB-CUCP4 sends an F1 message terminal context request (UE CONTEXT SETUP REQUEST) to gNB-DU4, including at least one of the received handover optimization request information.

14. GNB-DU4 sends an F1 message terminal context request response to gNB-CUCP4 (UE CONTEXT SETUP RESPONSE).

15. GNB-CUCP4 sends an Xn message switch request accept (HANDOVER REQUEST ACKNOWLEDGE) to gNB-CUCP 3.

And the gNB-CUUP4 collects sample information of the UE according to the received handover optimization request information, for example, if the handover optimization request information comprises indication information for collecting user experience parameters and a time length, the gNB-CUUP4 collects the user experience parameters of the UE within the time length.

16. GNB-CUUP4 sends E1 message base station hub unit control plane measurement result information (GNB-CU-CP MEASUREMENT RESULTS INFORMATION) to gNB-CUCP, including sample information of the UE collected by gNB-CUUP.

The gNB-DU4 collects sample information of the UE according to the received handover optimization request information, for example, if the handover optimization request information includes indication information for collecting spectrum efficiency parameters and a time length, the gNB-CUUP4 collects the spectrum efficiency parameters of the UE within the time length.

17. The gNB-DU4 sends F1 message access and mobility indication (ACCESS AND MOBILITY INDICATION) to the gNB-CUCP4 including sample information of the UE acquired by the gNB-DU 4.

18. The gNB-CUCP4 sends an Xn message access and mobility indication (ACCESS AND MOBILITY INDICATION) to the gNB-CUCP, including the sample information of the UE collected by the gNB 4.

According to the above steps, the gNB3 obtains sample information after the UE is switched to the target cell selected according to the parameter prediction model, for example, spectrum efficiency parameters and/or user experience parameters of the UE switched to the target cell. The sample information represents a change of some performance parameters, such as a spectrum efficiency improvement or degradation, or a user experience improvement or degradation, of the UE upon handover to the target cell.

The gNB3 can take the information in the sample information as a feedback parameter of the parameter prediction model, so that the accuracy of the parameter prediction model prediction is improved. In the subsequent switching process, the source cell can select the optimal target cell, so that the optimal user experience of the user is ensured, and the whole network performance is improved.

The order of messages in this example may be different from that of fig. 8.

An example five is an algorithm in which the source cell selects the target cell using the parameter prediction results.

The conditions for selecting the target cell in the algorithm comprise QoE parameters, qoS parameters and spectrum efficiency parameters after the UE is connected to the adjacent cell, which are predicted by the parameter prediction model. One or more of the conditions are also selected at the time of implementation, and the order of judgment may be different from that in the present algorithm.

In the algorithm, the QoE parameter is exemplified by the QoE parameter with the service type being streaming, and the QoS parameter is exemplified by the uplink and downlink rates of the UE.

Fig. 9 is a flowchart of an algorithm for selecting a target cell by using a parameter prediction result according to an embodiment of the present application, as shown in fig. 9, the algorithm includes the following steps:

1. The source cell determines whether the UE has established a specified service. The service may be performed by a service type configured by an operation and maintenance management (Operation Administration AND MAINTENANCE, OAM). For example, the service is designated as streaming in this example.

2. If the UE establishes the specified service, judging whether the source cell can acquire QoE parameters of the specified service of the UE and deducing the QoE parameters of the specified service on at least one adjacent cell through a parameter prediction model.

If the source cell can acquire the QoE parameters of the specified service of the UE and can infer the QoE parameters of the specified service on at least one neighbor cell through a parameter prediction model, step 3 is performed.

And if the source cell cannot acquire the QoE parameters of the specified service of the UE or cannot infer the QoE parameters of the specified service on at least one neighbor cell through a parameter prediction model, or the UE does not establish the specified service, executing the step 4.

3. And estimating service experience parameters of the UE on the source cell and the neighbor cell according to the QoE parameters. In this example, the estimation method may be, for example, an estimation method of an audio/video mean subjective opinion score (Mean Opinion Score, MOS) score specified in the 3GPP technical specification 26.247, where the audio/video MOS score is the service experience parameter in this example.

And 3a, judging whether the service experience parameters are better than those of the neighbor cells of the source cell. If so, step 3b is performed. If not, step 4 is performed.

And 3b, selecting the adjacent cell with the optimal service experience parameter as a target cell, and executing the step 8.

4. And judging whether the source cell can acquire the QoS parameters of the UE and deducing the QoS parameters of at least one adjacent cell through a parameter prediction model. In this example, the QoS parameter is the uplink and downlink rate of the UE.

If the source cell can acquire the QoS parameters of the UE and can infer the QoS parameters of at least one neighbor cell through the parameter prediction model, step 4a is performed.

If the source cell cannot acquire the QoS parameters of the UE or cannot infer the QoS parameters of at least one neighbor cell through the parameter prediction model, step 5 is performed.

And 4a, estimating the uplink capacity and the downlink capacity of the UE on the source cell and the adjacent cell according to the QoS parameters, and executing the step 6.

5. And (6) estimating the uplink capacity and the downlink capacity of the UE on the source cell and the neighbor cells according to the spectrum efficiency parameters of the UE acquired by the source cell and the spectrum efficiency parameters of at least one neighbor cell inferred by the parameter prediction model, and executing the step (6).

If the source cell cannot acquire the spectrum efficiency parameters of the UE or deduces the spectrum efficiency parameters of at least one adjacent cell through a parameter prediction model, selecting a target cell by using the existing mechanism, and exiting the algorithm.

6. And judging the large traffic state of the UE according to the traffic of the UE.

And 6a, if the UE is an uplink large-traffic user, selecting a cell with the largest uplink capacity in the adjacent cells and larger than the uplink capacity of the source cell, if more than one cell is selected from the cells, and if more than one cell is selected, selecting at least one optimal cell from CQI (channel quality indicator), uplink MCS Index, downlink MCS Index of the UE in the cells and measurement results of the adjacent cells on the UE.

And 6b, if the UE is a downlink high traffic user or a non-high traffic user, selecting a cell with the largest downlink capacity in the neighbor cell and larger than the downlink capacity of the source cell, if more than one cell is selected from the cells, and if more than one cell is selected, selecting at least one optimal cell from CQI (channel quality indicator), uplink MCS Index, downlink MCS Index of the UE in the cells and measurement results of the neighbor cell on the UE.

7. If a suitable neighbor cell is selected, taking the neighbor cell as a target cell, and executing step 8. If the appropriate target cell is not selected, step 7a is performed.

7A, determining whether handover is necessary, for example, if the co-channel measurement result of the UE in the source cell is smaller than a preset threshold value, and considering that handover is necessary. If a handover is not necessary, the algorithm is exited. If a handover is necessary, step 7b is performed.

7B, if the UE is the user with large uplink traffic, selecting the cell with the largest uplink capacity in the adjacent cells, if more than one cell is selected, selecting one cell randomly in the cells, if the UE is other users, selecting the cell with the largest downlink capacity in the adjacent cells, if more than one cell is selected, selecting the cell with the largest uplink capacity in the cells, and if more than one cell is selected, selecting one cell randomly in the cells. The selected cell is taken as a target cell. Step 8 is performed.

8. And executing switching to the target cell. The algorithm is exited.

According to the algorithm, the source cell can select the optimal target cell to execute the switching, so that the UE is ensured to obtain the optimal user experience after the switching.

And six, transmitting the input parameters of the parameter prediction model by the three-way node four, and transmitting the parameter prediction result by the four-way node three.

Wherein node three may be any of gNB, eNB, ng-eNB, en-gNB, CU of gNB, CUCP of gNB, CUUP of gNB, DU of gNB, RIC or a newly defined network node. Node four may be any one of gNB, eNB, ng-eNB, en-gNB, CU of gNB, CUCP of gNB, CUUP of gNB, DU of gNB, RIC, or newly defined network node, and node four is a network device with the capability to perform model reasoning.

Fig. 10 is a schematic flow chart of a parameter prediction result sent by a node three-way node four, and as shown in fig. 10, the process includes the following steps:

1. and the third node generates input parameters of the parameter prediction model according to one or more of the received sample information and the information acquired by the third node. And the node three-way node four sends a message three. Message three includes the input parameters of the parameter prediction model.

2. And the fourth node acquires a parameter prediction model. And the fourth node uses the parameter prediction model to infer a parameter prediction result according to the input parameters of the parameter prediction model. And the node IV sends a message IV to the node III, wherein the message comprises a parameter prediction result.

And selecting an optimal target cell according to the parameter prediction result by the node III.

And seventhly, acquiring a parameter prediction model from the node six by the node five.

Wherein node five may be any of gNB, eNB, ng-eNB, en-gNB, CU of gNB, CUCP of gNB, CUUP of gNB, DU of gNB, RIC or a newly defined network node. Node six may be any of gNB, eNB, ng-eNB, en-gNB, CU of gNB, CUCP of gNB, CUUP of gNB, DU of gNB, RIC or newly defined network node, and node six is a network device with the capability to perform model reasoning.

Fig. 11 is a schematic flow chart of acquiring a parameter prediction model from a node six by a node five according to an embodiment of the present application, as shown in fig. 11, the process includes the following steps:

1. node five sends message five to node six. Message five includes at least one of the following information:

an indication message for indicating to start or update or stop sending the trained parameter prediction model to the node five;

and second period information indicating that the trained parameter prediction model is transmitted every time indicated by the second period information.

2. The node six sends the message six to the node five according to the requirement of the message five, for example, according to the second period information, including the parameter prediction model trained by the node six.

And fifthly, deducing a parameter prediction result according to the received parameter prediction model, and selecting an optimal target cell according to the parameter prediction result.

The prior art does not consider the performance of the UE after handover when selecting a target cell for the UE. The embodiment of the application supports the source cell to predict the performance of the UE after switching, so as to select the optimal target cell and ensure that the UE obtains the optimal user experience after switching.

The method and the device provided by the embodiments of the present application are based on the same application conception, and because the principles of solving the problems by the method and the device are similar, the implementation of the device and the method can be referred to each other, and the repetition is not repeated.

Fig. 12 is a schematic structural diagram of a source network device according to an embodiment of the present application, and as shown in fig. 12, the source network device includes a memory 1220, a transceiver 1210 and a processor 1200, where the processor 1200 and the memory 1220 may also be physically separated.

A memory 1220 for storing a computer program, and a transceiver 1210 for transceiving data under the control of the processor 1200.

In particular, the transceiver 1210 is configured to receive and transmit data under the control of the processor 1200.

Wherein in fig. 12, a bus architecture may comprise any number of interconnected buses and bridges, and in particular, one or more processors represented by processor 1200 and various circuits of memory represented by memory 1220, linked together. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, power management circuits, etc., all as are well known in the art and, therefore, will not be described further herein. The bus interface provides an interface. The transceiver 1210 may be a number of elements, including a transmitter and a receiver, providing a means for communicating with various other apparatus over transmission media, including wireless channels, wired channels, optical cables, and the like.

The processor 1200 is responsible for managing the bus architecture and general processing, and the memory 1220 may store data used by the processor 1200 in performing operations.

The processor 1200 may be a central processing unit (Central Processing Unit, CPU), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA), or complex Programmable logic device (Complex Programmable Logic Device, CPLD), and may also employ a multi-core architecture.

The processor 1200 is configured to execute any of the methods provided in the embodiments of the present application according to the obtained executable instructions by calling a computer program stored in the memory 1220, for example, obtaining a parameter prediction result, where the parameter prediction result includes a performance parameter and/or an optimal neighbor identifier corresponding to a terminal after the terminal is switched to a neighbor, which is predicted based on a parameter prediction model;

In some embodiments, obtaining a parameter predictor includes:

acquiring parameter prediction results from the first network device, or

In some embodiments, the operations further comprise:

Sample parameter information;

A parameter prediction model;

Feedback information after the terminal is switched to the target cell;

And predicting a result of the parameter.

In some embodiments, the parameters for characterizing the uplink and/or downlink capabilities of the sample terminal on the sample neighbor include one or more of the following:

the uplink spectrum efficiency parameter and/or the downlink spectrum efficiency parameter of the sample terminal on the sample neighbor cell;

The uplink bandwidth and/or the downlink bandwidth of the sample terminal on the sample neighbor cell;

User experience parameters of sample terminals on sample neighbor cells.

In some embodiments, the sample parameter information further comprises one or more of the following:

Cell identification of the sample source cell;

cell identification of a sample neighbor cell;

Identification of the service beam on the sample neighbor;

identification of the serving beam on the sample source cell;

Identification of the sample terminal;

Downlink transmitting power of the sample adjacent cell;

downlink transmitting power of service wave beam on sample adjacent area;

downlink transmitting power of the sample source cell;

Downlink transmission power of a service beam on a sample source cell;

Uplink transmitting power of the sample terminal;

the number of downlink transmitting antennas of the sample neighbor cell;

the number of uplink receiving antennas of the sample neighbor cell;

the number of downlink transmitting antennas of the sample source cell;

the number of uplink receiving antennas of the sample source cell;

The number of uplink transmitting antennas of the sample terminal;

the number of downlink receiving antennas of the sample terminal;

At least one cell with different frequency points from the cell of the sample source, which is reported by the sample terminal;

the measurement result of at least one cell which is reported by the sample terminal and is the same as the frequency point of the sample source cell;

the sample neighbor cell measures the measurement result of the sample terminal;

the sample source cell measures the measurement result of the sample terminal;

channel quality indicator CQI and/or downlink modulation coding mode Index MCS Index of the sample terminal;

uplink MCS Index of the sample terminal;

Load state of the sample neighbor cell;

the load state of the sample source cell.

In some embodiments, the input parameters of the parametric prediction model include one or more of:

cell identification of the neighbor cell;

Identification of the service beam on the neighbor cell;

cell identification of the source cell;

An identification of the serving beam on the source cell;

Identification of the terminal;

downlink transmitting power of the adjacent cell;

Downlink transmission power of the service beam on the neighbor cell;

Downlink transmitting power of source cell;

Downlink transmit power of the serving beam on the source cell;

uplink transmitting power of the terminal;

The number of downlink transmitting antennas of the neighboring cell;

the number of uplink receiving antennas of the neighboring cell;

The number of downlink transmitting antennas of the source cell;

The number of uplink receiving antennas of the source cell;

the number of uplink transmitting antennas of the terminal;

The number of downlink receiving antennas of the terminal;

uplink effective bandwidth of the terminal on the adjacent cell;

the downlink effective bandwidth of the terminal on the adjacent cell;

uplink idle bandwidth of neighbor cells;

Downlink idle bandwidth of neighbor cell;

the source cell measures the measurement result of the terminal;

The load state of the neighbor cell;

Load status of the source cell.

In some embodiments, the performance parameters after the terminal is handed over to the neighboring cell include one or more of:

The neighbor cell measures the measurement result of the terminal;

CQI and/or downlink MCS Index of the terminal;

uplink MCS Index of the terminal;

A downlink spectrum efficiency parameter of the terminal on the adjacent cell;

uplink spectrum efficiency parameters of the terminal on the adjacent cell;

User experience parameters of the terminal on the neighbor cell.

In some embodiments, the parameter prediction result further comprises one or more of the following:

cell identification of the neighbor cell;

the reliability of the parameter prediction result.

In some embodiments, the handover optimization request information includes one or more of the following:

Cell identification of the sample source cell;

cell identification of a sample neighbor cell;

Data granularity identification;

Quality of service QoS parameter types;

A service type;

Identification of the sample terminal;

cell identification of the source cell;

Cell identification of the target cell;

Identification of the terminal;

In some embodiments, the operations further comprise:

receiving feedback information sent by second network equipment;

Fig. 13 is a schematic structural diagram of a second network device according to an embodiment of the present application, as shown in fig. 13, where the second network device includes a memory 1320, a transceiver 1310, and a processor 1300, where the processor 1300 and the memory 1320 may also be physically separated.

Memory 1320 for storing a computer program, and a transceiver 1310 for transceiving data under the control of the processor 1300.

In particular, the transceiver 1310 is configured to receive and transmit data under the control of the processor 1300.

Where in FIG. 13, a bus architecture may comprise any number of interconnected buses and bridges, with various circuits of the one or more processors, specifically represented by processor 1300, and the memory, represented by memory 1320, being linked together. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, power management circuits, etc., all as are well known in the art and, therefore, will not be described further herein. The bus interface provides an interface. The transceiver 1310 may be a number of elements, including a transmitter and a receiver, providing a means for communicating with various other apparatus over a transmission medium, including wireless channels, wired channels, optical cables, etc.

The processor 1300 is responsible for managing the bus architecture and general processing, and the memory 1320 may store data used by the processor 1300 in performing operations.

Processor 1300 may be CPU, ASIC, FPGA or a CPLD, and the processor may also employ a multi-core architecture.

Processor 1300 is configured to execute any of the methods provided in the embodiments of the present application according to the obtained executable instructions by calling a computer program stored in memory 1320, for example, receiving handover optimization request information sent by a source network device;

According to the handover optimization request information, one or more of the following are sent to the source network device:

sample parameter information for training a parameter prediction model;

A parameter prediction model;

Feedback information after the terminal is switched to the target cell;

Cell identification of the sample source cell;

cell identification of a sample neighbor cell;

Data granularity identification;

Quality of service QoS parameter types;

A service type;

Identification of the sample terminal;

cell identification of the source cell;

Cell identification of the target cell;

Identification of the terminal;

In some embodiments, the sample parameter information includes one or more of the following:

Cell identification of the sample source cell;

cell identification of a sample neighbor cell;

Identification of the service beam on the sample neighbor;

identification of the serving beam on the sample source cell;

Identification of the sample terminal;

Downlink transmitting power of the sample adjacent cell;

downlink transmitting power of service wave beam on sample adjacent area;

downlink transmitting power of the sample source cell;

Downlink transmission power of a service beam on a sample source cell;

Uplink transmitting power of the sample terminal;

the number of downlink transmitting antennas of the sample neighbor cell;

the number of uplink receiving antennas of the sample neighbor cell;

the number of downlink transmitting antennas of the sample source cell;

the number of uplink receiving antennas of the sample source cell;

The number of uplink transmitting antennas of the sample terminal;

the number of downlink receiving antennas of the sample terminal;

the sample source cell measures the measurement result of the sample terminal;

uplink MCS Index of the sample terminal;

Load state of the sample neighbor cell;

The load state of the sample source cell;

User experience parameters of sample terminals on sample neighbor cells.

It should be noted that, the source network device and the second network device provided in the embodiments of the present application can implement all the method steps implemented in the embodiments of the present application, and can achieve the same technical effects, and detailed descriptions of the same parts and beneficial effects as those of the embodiments of the present application are omitted herein.

Fig. 14 is a schematic structural diagram of an apparatus for selecting a target cell according to an embodiment of the present application, as shown in fig. 14, where the apparatus includes:

The obtaining unit 1400 is configured to obtain a parameter prediction result, where the parameter prediction result includes a performance parameter obtained by predicting that the terminal is switched to the neighboring cell based on the parameter prediction model and/or an optimal neighboring cell identifier corresponding to the terminal;

a selecting unit 1410, configured to select a target cell to which the terminal is handed over, based on the parameter prediction result;

In some embodiments, obtaining a parameter predictor includes:

acquiring parameter prediction results from the first network device, or

In some embodiments, the apparatus further comprises:

The first sending unit is used for sending switching optimization request information to the second network equipment, wherein the switching optimization request information is used for acquiring one or more of the following:

Sample parameter information;

A parameter prediction model;

Feedback information after the terminal is switched to the target cell;

And predicting a result of the parameter.

User experience parameters of sample terminals on sample neighbor cells.

Cell identification of the sample source cell;

cell identification of a sample neighbor cell;

Identification of the service beam on the sample neighbor;

identification of the serving beam on the sample source cell;

Identification of the sample terminal;

Downlink transmitting power of the sample adjacent cell;

downlink transmitting power of service wave beam on sample adjacent area;

downlink transmitting power of the sample source cell;

Downlink transmission power of a service beam on a sample source cell;

Uplink transmitting power of the sample terminal;

the number of downlink transmitting antennas of the sample neighbor cell;

the number of uplink receiving antennas of the sample neighbor cell;

the number of downlink transmitting antennas of the sample source cell;

the number of uplink receiving antennas of the sample source cell;

The number of uplink transmitting antennas of the sample terminal;

the number of downlink receiving antennas of the sample terminal;

the sample source cell measures the measurement result of the sample terminal;

uplink MCS Index of the sample terminal;

Load state of the sample neighbor cell;

the load state of the sample source cell.

cell identification of the neighbor cell;

Identification of the service beam on the neighbor cell;

cell identification of the source cell;

An identification of the serving beam on the source cell;

Identification of the terminal;

downlink transmitting power of the adjacent cell;

Downlink transmission power of the service beam on the neighbor cell;

Downlink transmitting power of source cell;

Downlink transmit power of the serving beam on the source cell;

uplink transmitting power of the terminal;

The number of downlink transmitting antennas of the neighboring cell;

the number of uplink receiving antennas of the neighboring cell;

The number of downlink transmitting antennas of the source cell;

The number of uplink receiving antennas of the source cell;

the number of uplink transmitting antennas of the terminal;

The number of downlink receiving antennas of the terminal;

uplink effective bandwidth of the terminal on the adjacent cell;

the downlink effective bandwidth of the terminal on the adjacent cell;

uplink idle bandwidth of neighbor cells;

Downlink idle bandwidth of neighbor cell;

the source cell measures the measurement result of the terminal;

The load state of the neighbor cell;

Load status of the source cell.

The neighbor cell measures the measurement result of the terminal;

CQI and/or downlink MCS Index of the terminal;

uplink MCS Index of the terminal;

A downlink spectrum efficiency parameter of the terminal on the adjacent cell;

uplink spectrum efficiency parameters of the terminal on the adjacent cell;

User experience parameters of the terminal on the neighbor cell.

cell identification of the neighbor cell;

the reliability of the parameter prediction result.

Cell identification of the sample source cell;

cell identification of a sample neighbor cell;

Data granularity identification;

Quality of service QoS parameter types;

A service type;

Identification of the sample terminal;

cell identification of the source cell;

Cell identification of the target cell;

Identification of the terminal;

In some embodiments, the apparatus further comprises:

the first receiving unit is used for receiving feedback information sent by the second network equipment;

and the optimizing unit is used for optimizing the parameter prediction model based on the feedback information.

Fig. 15 is a second schematic structural diagram of an apparatus for selecting a target cell according to an embodiment of the present application, as shown in fig. 15, the apparatus includes:

A second receiving unit 1500, configured to receive handover optimization request information sent by a source network device;

A second sending unit 1510, configured to send, to the source network device, one or more of the following according to the handover optimization request information:

sample parameter information for training a parameter prediction model;

A parameter prediction model;

Feedback information after the terminal is switched to the target cell;

Cell identification of the sample source cell;

cell identification of a sample neighbor cell;

Data granularity identification;

Quality of service QoS parameter types;

A service type;

Identification of the sample terminal;

cell identification of the source cell;

Cell identification of the target cell;

Identification of the terminal;

Cell identification of the sample source cell;

cell identification of a sample neighbor cell;

Identification of the service beam on the sample neighbor;

identification of the serving beam on the sample source cell;

Identification of the sample terminal;

Downlink transmitting power of the sample adjacent cell;

downlink transmitting power of service wave beam on sample adjacent area;

downlink transmitting power of the sample source cell;

Downlink transmission power of a service beam on a sample source cell;

Uplink transmitting power of the sample terminal;

the number of downlink transmitting antennas of the sample neighbor cell;

the number of uplink receiving antennas of the sample neighbor cell;

the number of downlink transmitting antennas of the sample source cell;

the number of uplink receiving antennas of the sample source cell;

The number of uplink transmitting antennas of the sample terminal;

the number of downlink receiving antennas of the sample terminal;

the sample source cell measures the measurement result of the sample terminal;

uplink MCS Index of the sample terminal;

Load state of the sample neighbor cell;

The load state of the sample source cell;

User experience parameters of sample terminals on sample neighbor cells.

It should be noted that, in the embodiment of the present application, the division of the units is schematic, which is merely a logic function division, and other division manners may be implemented in actual practice. In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a processor-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present application. The storage medium includes a U disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, an optical disk, or other various media capable of storing program codes.

It should be noted that, the above device provided in the embodiment of the present application can implement all the method steps implemented in the method embodiment and achieve the same technical effects, and detailed descriptions of the same parts and beneficial effects as those in the method embodiment in this embodiment are omitted.

In another aspect, embodiments of the present application further provide a computer-readable storage medium storing a computer program for causing a computer to execute the method for selecting a target cell provided in the above embodiments.

It should be noted that, the computer readable storage medium provided in the embodiment of the present application can implement all the method steps implemented in the above method embodiment and achieve the same technical effects, and detailed descriptions of the same parts and beneficial effects as those in the method embodiment in this embodiment are omitted.

The computer-readable storage medium can be any available medium or data storage device that can be accessed by a computer, including, but not limited to, magnetic storage (e.g., floppy disks, hard disks, magnetic tape, magneto-optical disks (MOs), etc.), optical storage (e.g., CD, DVD, BD, HVD, etc.), and semiconductor storage (e.g., ROM, EPROM, EEPROM, nonvolatile storage (NAND FLASH), solid State Disk (SSD)), etc.

The technical scheme provided by the embodiment of the application can be suitable for various systems, in particular to a 5G system. For example, applicable systems may be global system for mobile communications (global system of mobile communication, GSM), code division multiple access (code division multiple access, CDMA), wideband code division multiple access (Wideband Code Division Multiple Access, WCDMA) universal packet Radio service (GENERAL PACKET Radio service, GPRS), long term evolution (long term evolution, LTE), LTE frequency division duplex (frequency division duplex, FDD), LTE time division duplex (time division duplex, TDD), long term evolution-advanced (long term evolution advanced, LTE-a), universal mobile system (universal mobile telecommunication system, UMTS), worldwide interoperability for microwave access (worldwide interoperability for microwave access, wiMAX), 5G New air interface (New Radio, NR) systems, and the like. Terminal devices and network devices are included in these various systems. Core network parts such as evolved packet system (Evloved PACKET SYSTEM, EPS), 5G system (5 GS), etc. may also be included in the system.

The terminal according to the embodiment of the application can be a device for providing voice and/or data connectivity for a user, a handheld device with a wireless connection function, or other processing devices connected to a wireless modem, etc. The names of terminals may also be different in different systems, for example in a 5G system, a terminal may be referred to as User Equipment (UE). The wireless terminal device may communicate with one or more Core Networks (CNs) via a radio access Network (Radio Access Network, RAN), which may be mobile terminal devices such as mobile phones (or "cellular" phones) and computers with mobile terminal devices, e.g., portable, pocket, hand-held, computer-built-in or vehicle-mounted mobile devices that exchange voice and/or data with the radio access Network. Such as Personal communication services (Personal Communication Service, PCS) phones, cordless phones, session initiation protocol (Session Initiated Protocol, SIP) phones, wireless local loop (Wireless Local Loop, WLL) stations, personal digital assistants (Personal DIGITAL ASSISTANT, PDA) and the like. The wireless terminal device may also be referred to as a system, subscriber unit (subscriber unit), subscriber station (subscriber station), mobile station (mobile station), remote station (remote station), access point (access point), remote terminal device (remote terminal), access terminal device (ACCESS TERMINAL), user terminal device (user terminal), user agent (user agent), user equipment (user device), and embodiments of the present application are not limited.

The network device according to the embodiment of the present application may be a base station, where the base station may include a plurality of cells for providing services for the terminal. A base station may also be called an access point or may be a device in an access network that communicates over the air-interface, through one or more sectors, with wireless terminal devices, or other names, depending on the particular application. The network device may be configured to exchange received air frames with internet protocol (Internet Protocol, IP) packets as a router between the wireless terminal device and the rest of the access network, which may include an Internet Protocol (IP) communication network. The network device may also coordinate attribute management for the air interface. For example, the network device according to the embodiment of the present application may be a network device (Base Transceiver Station, BTS) in a global system for mobile communications (Global System for Mobile communications, GSM) or code division multiple access (Code Division Multiple Access, CDMA), a network device (NodeB) in a wideband code division multiple access (Wide-band Code Division Multiple Access, WCDMA), an evolved network device (evolutional Node B, eNB or e-NodeB) in a long term evolution (long term evolution, LTE) system, a 5G base station (gNB) in a 5G network architecture (next generation system), a home evolved base station (Home evolved Node B, heNB), a relay node (relay node), a home base station (femto), a pico base station (pico), etc., which are not limited in the embodiment of the present application. In some network structures, the network devices may include centralized unit (centralized unit, CU) nodes and Distributed Unit (DU) nodes, which may also be geographically separated.

Multiple-input Multiple-output (Multi Input Multi Output, MIMO) transmissions may each be made between the network device and the terminal using one or more antennas, and the MIMO transmissions may be Single User MIMO (SU-MIMO) or Multiple User MIMO (MU-MIMO). The MIMO transmission may be 2D-MIMO, 3D-MIMO, FD-MIMO, or massive-MIMO, or may be diversity transmission, precoding transmission, beamforming transmission, or the like, depending on the form and number of the root antenna combinations.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-executable instructions. These computer-executable instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These processor-executable instructions may also be stored in a processor-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the processor-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These processor-executable instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims

1. A method for selecting a target cell, characterized in that it is applied to a source network device, comprising:

Obtaining parameter prediction results; the parameter prediction results include performance parameters of the terminal after switching to a neighboring cell and/or an optimal neighboring cell identifier corresponding to the terminal, which are predicted based on a parameter prediction model;

Based on the parameter prediction result, selecting a target cell to which the terminal switches;

The parameter prediction model is obtained through training based on sample parameter information, and the sample parameter information at least includes parameters for characterizing the uplink capability and/or downlink capability of the sample terminal in the sample neighboring area.

2. The method for selecting a target cell according to claim 1, wherein obtaining the parameter prediction result comprises:

Acquire the parameter prediction result from the first network device; or,

The parameter prediction result is obtained based on the parameter prediction model.

3. The method for selecting a target cell according to claim 2, characterized in that the method further comprises:

Sending handover optimization request information to the second network device, where the handover optimization request information is used to obtain one or more of the following:

The sample parameter information;

The parameter prediction model;

Feedback information after the terminal switches to the target cell;

The parameters predict the outcome.

4. The method for selecting a target cell according to claim 1, wherein the parameter used to characterize the uplink capability and/or downlink capability of the sample terminal in the sample neighboring cell comprises one or more of the following:

Uplink spectrum efficiency parameters and/or downlink spectrum efficiency parameters of the sample terminal in the sample neighboring area;

The uplink bandwidth and/or downlink bandwidth of the sample terminal in the sample neighboring area;

User experience parameters of sample terminals in sample neighborhoods.

5. The method for selecting a target cell according to any one of claims 1 to 4, characterized in that the sample parameter information further comprises one or more of the following:

The cell identifier of the sample source cell;

The cell identifier of the sample neighborhood;

The identifier of the serving beam on the sample neighborhood;

The identifier of the serving beam on the sample source cell;

The identification of the sample terminal;

Downlink transmission power of sample neighboring cells;

Downlink transmit power of the serving beam in the sample neighboring cell;

Downlink transmission power of the sample source cell;

Downlink transmit power of the serving beam on the sample source cell;

Uplink transmit power of the sample terminal;

Number of downlink transmit antennas in the sample neighboring cell;

The number of uplink receiving antennas in the sample neighborhood;

The number of downlink transmit antennas of the sample source cell;

The number of uplink receiving antennas of the sample source cell;

The number of uplink transmit antennas of the sample terminal;

The number of downlink receiving antennas of the sample terminal;

The measurement result of at least one cell with a different frequency from the sample source cell reported by the sample terminal;

The measurement result of at least one cell with the same frequency as the sample source cell reported by the sample terminal;

The measurement results of the sample terminal measured by the sample neighboring area;

The measurement result of the sample source cell on the sample terminal;

Channel quality indicator CQI and/or downlink modulation and coding scheme index MCS Index of the sample terminal;

Uplink MCS Index of the sample terminal;

Load status of the sample neighborhood;

The load status of the sample source cell.

6. The method for selecting a target cell according to claim 1, wherein the input parameters of the parameter prediction model include one or more of the following:

The cell identifier of the neighboring cell;

An identifier of a serving beam on the neighboring cell;

The cell identifier of the source cell;

The identifier of the serving beam on the source cell;

an identification of the terminal;

Downlink transmission power of the neighboring cell;

The downlink transmission power of the serving beam in the neighboring cell;

Downlink transmit power of the source cell;

Downlink transmit power of the serving beam on the source cell;

The uplink transmission power of the terminal;

The number of downlink transmitting antennas of the neighboring cell;

The number of uplink receiving antennas of the neighboring cell;

Number of downlink transmit antennas of the source cell;

The number of uplink receiving antennas of the source cell;

The number of uplink transmit antennas of the terminal;

The number of downlink receiving antennas of the terminal;

The effective uplink bandwidth of the terminal in the neighboring cell;

The downlink effective bandwidth of the terminal in the neighboring cell;

The uplink idle bandwidth of the neighboring cell;

downlink idle bandwidth of the neighboring cell;

The measurement result of at least one cell having a frequency different from that of the source cell reported by the terminal;

The measurement result of at least one cell having the same frequency as the source cell reported by the terminal;

a measurement result of the source cell measuring the terminal;

The load status of the neighboring cell;

Load status of the source cell.

7. The method for selecting a target cell according to claim 1, wherein the performance parameters after the terminal switches to the neighboring cell include one or more of the following:

A measurement result of the neighboring cell measuring the terminal;

CQI and/or downlink MCSIndex of the terminal;

An uplink MCS Index of the terminal;

A downlink spectrum efficiency parameter of the terminal in the neighboring cell;

An uplink spectrum efficiency parameter of the terminal in the neighboring cell;

User experience parameters of the terminal in the neighboring cell.

8. The method for selecting a target cell according to claim 1 or 7, wherein the parameter prediction result further comprises one or more of the following:

The cell identifier of the neighboring cell;

The reliability of the parameter prediction results.

9. The method for selecting a target cell according to claim 3, wherein the handover optimization request information includes one or more of the following:

The cell identifier of the sample source cell;

The cell identifier of the sample neighborhood;

first indication information, where the first indication information is used to indicate starting, updating or stopping collecting the sample parameter information;

first cycle information, where the first cycle information is used to indicate a cycle for sending the sample parameter information to the source network device;

first direction information, where the first direction information is used to indicate the collection of uplink information and/or downlink information in the sample parameter information;

second indication information, where the second indication information is used to indicate the type of the sample parameter information that needs to be collected;

Data granularity identification;

Quality of service QoS parameter type;

Type of business;

The identification of the sample terminal;

first time length information, where the first time length information is used to indicate a time period for collecting the sample parameter information;

third indication information, where the third indication information is used to indicate starting, updating or stopping sending the parameter prediction model to the source network device;

second cycle information, where the second cycle information is used to indicate a cycle for sending the parameter prediction model to the source network device;

The cell identifier of the source cell;

The cell identifier of the target cell;

Fourth indication information, where the fourth indication information is used to indicate starting, updating or stopping collecting feedback information after the terminal switches to the target cell;

third cycle information, where the third cycle information is used to indicate a cycle for sending the feedback information to the source network device;

second direction information, where the second direction information is used to indicate the collection of uplink information and/or downlink information in the feedback information;

fifth indication information, where the fifth indication information is used to indicate the type of the feedback information to be collected;

an identification of the terminal;

second time length information, where the second time length information is used to indicate a time period for collecting the feedback information;

Sixth indication information, the sixth indication information is used to indicate that the target cell is predicted and/or the credibility of the parameter prediction result.

10. The method for selecting a target cell according to claim 1, wherein the step of selecting a target cell to which the terminal switches based on the parameter prediction result comprises:

Based on the parameter prediction result, estimating the uplink capability and/or downlink capability of the terminal in the neighboring cell;

A target cell to which the terminal switches is selected based on the uplink capability and/or downlink capability of the terminal in the neighboring cell.

11. The method for selecting a target cell according to claim 10, wherein the step of selecting a target cell to which the terminal switches based on the uplink capability and/or downlink capability of the terminal in the neighboring cell comprises:

Select a neighboring cell with the largest uplink capacity and/or downlink capacity, and determine it as the target cell to which the terminal switches; or

A target cell to which the terminal switches is selected based on the uplink capability and/or downlink capability of the terminal in the neighboring cell and the traffic type of the terminal.

12. The method for selecting a target cell according to claim 11, wherein the selecting the target cell to which the terminal switches based on the uplink capability and/or downlink capability of the terminal in the neighboring cell and the traffic type of the terminal comprises:

In the case where the terminal is a user with a large uplink traffic volume, selecting a target cell to which the terminal is switched from a neighboring cell having the largest corresponding uplink capacity and a corresponding uplink capacity greater than the uplink capacity of the terminal in the source cell; or

In the case that the terminal is a user with a large downlink traffic volume, a target cell to which the terminal switches is selected from a neighboring cell whose corresponding downlink capacity is the largest and whose corresponding downlink capacity is greater than the downlink capacity of the terminal in the source cell.

13. The method for selecting a target cell according to claim 3 or 9, characterized in that the method further comprises:

receiving the feedback information sent by the second network device;

Based on the feedback information, the parameter prediction model is optimized.

14. A method for selecting a target cell, characterized in that it is applied to a second network device, comprising:

Receiving switching optimization request information sent by the source network device;

According to the handover optimization request information, one or more of the following is sent to the source network device:

Sample parameter information used to train parameter prediction models;

The parameter prediction model;

Feedback information after the terminal switches to the target cell;

Parameter prediction results; the parameter prediction results include performance parameters of the terminal after switching to a neighboring cell predicted based on a parameter prediction model and/or an optimal neighboring cell identifier corresponding to the terminal.

15. The method for selecting a target cell according to claim 14, wherein the handover optimization request information includes one or more of the following:

The cell identifier of the sample source cell;

The cell identifier of the sample neighborhood;

Data granularity identification;

Quality of service QoS parameter type;

Type of business;

The identification of the sample terminal;

The cell identifier of the source cell;

The cell identifier of the target cell;

an identification of the terminal;

16. The method for selecting a target cell according to claim 14, wherein the sample parameter information comprises one or more of the following:

The cell identifier of the sample source cell;

The cell identifier of the sample neighborhood;

The identifier of the serving beam on the sample neighborhood;

The identifier of the serving beam on the sample source cell;

The identification of the sample terminal;

Downlink transmission power of sample neighboring cells;

Downlink transmit power of the serving beam in the sample neighboring cell;

Downlink transmission power of the sample source cell;

Downlink transmit power of the serving beam on the sample source cell;

Uplink transmit power of the sample terminal;

Number of downlink transmit antennas in the sample neighboring cell;

The number of uplink receiving antennas in the sample neighborhood;

The number of downlink transmit antennas of the sample source cell;

The number of uplink receiving antennas of the sample source cell;

The number of uplink transmit antennas of the sample terminal;

The number of downlink receiving antennas of the sample terminal;

The measurement result of the sample source cell on the sample terminal;

Uplink MCS Index of the sample terminal;

Load status of the sample neighborhood;

The load status of the sample source cell;

An uplink spectrum efficiency parameter and/or a downlink spectrum efficiency parameter of the sample terminal in the sample neighboring cell;

User experience parameters of sample terminals in sample neighborhoods.

17. A source network device, characterized by comprising a memory, a transceiver, and a processor;

A memory for storing a computer program; a transceiver for transmitting and receiving data under the control of the processor; and a processor for reading the computer program in the memory and performing the following operations:

18. The source network device according to claim 17, wherein the obtaining the parameter prediction result comprises:

Acquire the parameter prediction result from the first network device; or,

19. The source network device according to claim 18, wherein the operation further comprises:

The sample parameter information;

The parameter prediction model;

Feedback information after the terminal switches to the target cell;

The parameters predict the outcome.

20. The source network device according to claim 17, wherein the parameter used to characterize the uplink capability and/or downlink capability of the sample terminal in the sample neighboring area comprises one or more of the following:

User experience parameters of sample terminals in sample neighborhoods.

21. The source network device according to any one of claims 17 to 20, wherein the sample parameter information further comprises one or more of the following:

The cell identifier of the sample source cell;

The cell identifier of the sample neighborhood;

The identifier of the serving beam on the sample neighborhood;

The identifier of the serving beam on the sample source cell;

The identification of the sample terminal;

Downlink transmission power of sample neighboring cells;

Downlink transmit power of the serving beam in the sample neighboring cell;

Downlink transmission power of the sample source cell;

Downlink transmit power of the serving beam on the sample source cell;

Uplink transmit power of the sample terminal;

Number of downlink transmit antennas in the sample neighboring cell;

The number of uplink receiving antennas in the sample neighborhood;

The number of downlink transmit antennas of the sample source cell;

The number of uplink receiving antennas of the sample source cell;

The number of uplink transmit antennas of the sample terminal;

The number of downlink receiving antennas of the sample terminal;

The measurement result of the sample source cell on the sample terminal;

Uplink MCS Index of the sample terminal;

Load status of the sample neighborhood;

The load status of the sample source cell.

22. The source network device according to claim 17, wherein the input parameters of the parameter prediction model include one or more of the following:

The cell identifier of the neighboring cell;

An identifier of a serving beam on the neighboring cell;

The cell identifier of the source cell;

The identifier of the serving beam on the source cell;

an identification of the terminal;

Downlink transmission power of the neighboring cell;

The downlink transmission power of the serving beam in the neighboring cell;

Downlink transmit power of the source cell;

Downlink transmit power of the serving beam on the source cell;

The uplink transmission power of the terminal;

The number of downlink transmitting antennas of the neighboring cell;

The number of uplink receiving antennas of the neighboring cell;

Number of downlink transmit antennas of the source cell;

The number of uplink receiving antennas of the source cell;

The number of uplink transmit antennas of the terminal;

The number of downlink receiving antennas of the terminal;

The effective uplink bandwidth of the terminal in the neighboring cell;

The downlink effective bandwidth of the terminal in the neighboring cell;

The uplink idle bandwidth of the neighboring cell;

downlink idle bandwidth of the neighboring cell;

a measurement result of the source cell measuring the terminal;

The load status of the neighboring cell;

Load status of the source cell.

23. The source network device according to claim 17, wherein the performance parameters after the terminal switches to the neighboring cell include one or more of the following:

A measurement result of the neighboring cell measuring the terminal;

CQI and/or downlink MCSIndex of the terminal;

An uplink MCS Index of the terminal;

User experience parameters of the terminal in the neighboring cell.

24. The source network device according to claim 17 or 23, wherein the parameter prediction result further comprises one or more of the following:

The cell identifier of the neighboring cell;

The reliability of the parameter prediction results.

25. The source network device according to claim 19, wherein the switching optimization request information includes one or more of the following:

The cell identifier of the sample source cell;

The cell identifier of the sample neighborhood;

Data granularity identification;

Quality of service QoS parameter type;

Type of business;

The identification of the sample terminal;

The cell identifier of the source cell;

The cell identifier of the target cell;

an identification of the terminal;

26. The source network device according to claim 17, wherein the selecting the target cell to which the terminal switches based on the parameter prediction result comprises:

27. The source network device according to claim 26, wherein the selecting the target cell to which the terminal switches based on the uplink capability and/or downlink capability of the terminal in the neighboring cell comprises:

28. The source network device according to claim 27, wherein the selecting the target cell to which the terminal switches based on the uplink capability and/or downlink capability of the terminal in the neighboring cell and the traffic type of the terminal comprises:

29. The source network device according to claim 19 or 25, wherein the operation further comprises:

receiving the feedback information sent by the second network device;

Based on the feedback information, the parameter prediction model is optimized.

30. A second network device, characterized by comprising a memory, a transceiver, and a processor;

Sample parameter information used to train parameter prediction models;

The parameter prediction model;

Feedback information after the terminal switches to the target cell;

31. The second network device according to claim 30, wherein the handover optimization request information includes one or more of the following:

The cell identifier of the sample source cell;

The cell identifier of the sample neighborhood;

Data granularity identification;

Quality of service QoS parameter type;

Type of business;

The identification of the sample terminal;

The cell identifier of the source cell;

The cell identifier of the target cell;

an identification of the terminal;

32. The second network device according to claim 30, wherein the sample parameter information includes one or more of the following:

The cell identifier of the sample source cell;

The cell identifier of the sample neighborhood;

The identifier of the serving beam on the sample neighborhood;

The identifier of the serving beam on the sample source cell;

The identification of the sample terminal;

Downlink transmission power of sample neighboring cells;

Downlink transmit power of the serving beam in the sample neighboring cell;

Downlink transmission power of the sample source cell;

Downlink transmit power of the serving beam on the sample source cell;

Uplink transmit power of the sample terminal;

Number of downlink transmit antennas in the sample neighboring cell;

The number of uplink receiving antennas in the sample neighborhood;

The number of downlink transmit antennas of the sample source cell;

The number of uplink receiving antennas of the sample source cell;

The number of uplink transmit antennas of the sample terminal;

The number of downlink receiving antennas of the sample terminal;

The measurement result of the sample source cell on the sample terminal;

Uplink MCS Index of the sample terminal;

Load status of the sample neighborhood;

The load status of the sample source cell;

User experience parameters of sample terminals in sample neighborhoods.

33. A device for selecting a target cell, comprising:

An acquisition unit, configured to acquire a parameter prediction result; the parameter prediction result includes a performance parameter of the terminal after switching to a neighboring cell predicted based on a parameter prediction model and/or an optimal neighboring cell identifier corresponding to the terminal;

A selection unit, configured to select a target cell to which the terminal switches based on the parameter prediction result;

34. A device for selecting a target cell, comprising:

A second receiving unit, configured to receive the switching optimization request information sent by the source network device;

A second sending unit is configured to send one or more of the following to the source network device according to the handover optimization request information:

Sample parameter information used to train parameter prediction models;

The parameter prediction model;

Feedback information after the terminal switches to the target cell;

35. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, wherein the computer program is used to enable a computer to execute the method according to any one of claims 1 to 13.

36. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, wherein the computer program is used to enable a computer to execute the method according to any one of claims 14 to 16.