[go: up one dir, main page]

CN117880835A - Beam management method, device, computing equipment and storage medium - Google Patents

Beam management method, device, computing equipment and storage medium Download PDF

Info

Publication number
CN117880835A
CN117880835A CN202211211021.9A CN202211211021A CN117880835A CN 117880835 A CN117880835 A CN 117880835A CN 202211211021 A CN202211211021 A CN 202211211021A CN 117880835 A CN117880835 A CN 117880835A
Authority
CN
China
Prior art keywords
terminal
prediction model
information
tested
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202211211021.9A
Other languages
Chinese (zh)
Inventor
刘玮
乔晶
张宏坤
马学军
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Mobile Communications Group Co Ltd
China Mobile Group Design Institute Co Ltd
Original Assignee
China Mobile Communications Group Co Ltd
China Mobile Group Design Institute Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Mobile Communications Group Co Ltd, China Mobile Group Design Institute Co Ltd filed Critical China Mobile Communications Group Co Ltd
Priority to CN202211211021.9A priority Critical patent/CN117880835A/en
Publication of CN117880835A publication Critical patent/CN117880835A/en
Pending legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
    • H04W16/24—Cell structures
    • H04W16/28—Cell structures using beam steering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/06—Testing, supervising or monitoring using simulated traffic
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本发明公开了一种波束管理方法、装置、计算设备及存储介质，涉及无线通信技术领域，该方法包括：根据待测终端的当前覆盖信息确定传输场景；获取待测终端对应在传输场景下的待处理特征信息；将待处理特征信息输入至传输场景对应的预先训练的预测模型进行处理，得到模型预测结果；根据模型预测结果确定待测终端的待切换波束信息，根据待切换波束信息为待测终端切换波束。通过上述方式，将深度神经网络结合波束管理来预测未来波束信息，能够减少因时延带来的误差，能够提高波束估计的精准度。

The present invention discloses a beam management method, device, computing equipment and storage medium, which relates to the field of wireless communication technology. The method includes: determining a transmission scenario according to the current coverage information of a terminal to be tested; obtaining feature information to be processed corresponding to the terminal to be tested in the transmission scenario; inputting the feature information to be processed into a pre-trained prediction model corresponding to the transmission scenario for processing to obtain a model prediction result; determining the beam information to be switched of the terminal to be tested according to the model prediction result, and switching the beam for the terminal to be tested according to the beam information to be switched. In the above manner, combining a deep neural network with beam management to predict future beam information can reduce errors caused by time delays and improve the accuracy of beam estimation.

Description

Beam management method, device, computing equipment and storage medium
Technical Field
The present invention relates to the field of wireless communications technologies, and in particular, to a beam management method, a device, a computing device, and a storage medium.
Background
In recent years, the fifth generation communication system (5G) has become a research hotspot in the communication field. The 5G expands the spectrum resources to the millimeter wave band, and compared with the frequency band below Sub-6GHz, the millimeter wave band is higher in bandwidth, so that the problem of user internet congestion can be better solved, but due to the high-frequency characteristic, the signal has higher path loss in the transmission process. To solve this problem, large-scale antenna arrays and beamforming techniques have been introduced. In the downlink channel, both communication parties perform beam scanning and switch to the best beam by periodically measuring a channel state information Reference Signal (Channel State Information-Reference Signal, CSI-RS), which generates a certain delay, resulting in a decrease in the accuracy of beam management. In a high-speed mobile scenario, the channel condition of the user changes rapidly, and the beam needs to be switched frequently, which results in an increase in signaling overhead of beam switching.
Disclosure of Invention
The present invention has been made in view of the above problems, and it is an object of the present invention to provide a beam management method, apparatus, computing device and storage medium that overcomes or at least partially solves the above problems.
According to an aspect of the present invention, there is provided a beam management method, including:
determining a transmission scene according to the current coverage information of the terminal to be tested;
acquiring feature information to be processed corresponding to a terminal to be tested in a transmission scene;
inputting the feature information to be processed into a pre-trained prediction model corresponding to the transmission scene for processing to obtain a model prediction result;
and determining the information of the beam to be switched of the terminal to be tested according to the model prediction result, and switching the beam for the terminal to be tested according to the information of the beam to be switched.
Optionally, the transmission scenario includes: the prediction model corresponding to the video transmission scene is a track prediction model;
the obtaining the feature information to be processed of the terminal to be tested corresponding to the transmission scene specifically comprises the following steps: acquiring track data of a terminal to be tested in a first preset period;
inputting the feature information to be processed into a pre-trained prediction model corresponding to the transmission scene for processing, wherein the obtaining of the model prediction result specifically comprises the following steps:
inputting the track data in the first preset period into a pre-trained track prediction model for processing to obtain predicted track data of the terminal to be tested;
the determining the information of the beam to be switched of the terminal to be tested according to the model prediction result specifically comprises the following steps:
and determining a coverage area to which the predicted track data belongs, and determining the information of the beam to be switched of the terminal to be tested according to the mapping relation between the coverage area and the beam.
Optionally, the method further comprises: the mapping relation between each wave beam in the base station and the corresponding coverage area is recorded in advance.
Optionally, the method further comprises:
acquiring sample track data of a plurality of user terminals;
inputting sample track data of each user terminal into an initial track prediction model for processing to obtain initial predicted track data;
and calculating loss according to the initial predicted track data and the real track data of the corresponding period of the user terminal, carrying out back propagation based on the loss, adjusting parameters of the initial track prediction model, and repeatedly executing the steps until the preset iteration ending condition is met, so as to obtain the track prediction model.
Optionally, the transmission scenario includes: a non-line-of-sight transmission scene, wherein a prediction model corresponding to the non-line-of-sight transmission scene is a channel prediction model;
the obtaining the feature information to be processed of the terminal to be tested corresponding to the transmission scene specifically comprises the following steps: acquiring channel information data in a second preset period of a terminal to be tested;
inputting the feature information to be processed into a pre-trained prediction model corresponding to the transmission scene for processing, wherein the obtaining of the model prediction result specifically comprises the following steps:
and inputting the channel information data in the second preset period into a pre-trained channel prediction model for processing to obtain predicted channel information data.
Optionally, the method further comprises:
acquiring sample channel information data of a plurality of user terminals;
inputting the sample channel information data of each user terminal into an initial channel prediction model for processing to obtain initial prediction channel data;
and calculating loss according to the initial predicted channel data and the real channel information data of the corresponding time period of the user terminal, carrying out back propagation based on the loss, adjusting parameters of the initial channel prediction model, and repeatedly executing the steps until the preset iteration ending condition is met, so as to obtain the channel prediction model.
Alternatively, the mean square error is used as a loss function for calculating the loss.
According to another aspect of the present invention, there is provided a beam management apparatus comprising:
the scene detection module is suitable for determining a transmission scene according to the current coverage information of the terminal to be detected;
the characteristic acquisition module is suitable for acquiring characteristic information to be processed of the terminal to be detected under a transmission scene;
the prediction processing module is suitable for inputting the characteristic information to be processed into a pre-trained prediction model corresponding to the transmission scene for processing, so as to obtain a model prediction result;
and the beam management module is suitable for determining the information of the beam to be switched of the terminal to be tested according to the model prediction result, and switching the beam for the terminal to be tested according to the information of the beam to be switched.
Optionally, the transmission scenario includes: the prediction model corresponding to the video transmission scene is a track prediction model;
the feature acquisition module is further adapted to: acquiring track data of a terminal to be tested in a first preset period; the prediction processing module is further adapted to: inputting the track data in the first preset period into a pre-trained track prediction model for processing to obtain predicted track data of the terminal to be tested; the beam management module is further adapted to: and determining a coverage area to which the predicted track data belongs, and determining the information of the beam to be switched of the terminal to be tested according to the mapping relation between the coverage area and the beam.
Optionally, the apparatus further comprises: and the recording module is suitable for pre-recording the mapping relation between each wave beam in the base station and the corresponding coverage area.
Optionally, the apparatus further comprises: the first model training module is suitable for acquiring sample track data of a plurality of user terminals; inputting sample track data of each user terminal into an initial track prediction model for processing to obtain initial predicted track data; and calculating loss according to the initial predicted track data and the real track data of the corresponding period of the user terminal, carrying out back propagation based on the loss, adjusting parameters of the initial track prediction model, and repeatedly executing the steps until the preset iteration ending condition is met, so as to obtain the track prediction model.
Optionally, the transmission scenario includes: a non-line-of-sight transmission scene, wherein a prediction model corresponding to the non-line-of-sight transmission scene is a channel prediction model;
the feature acquisition module is further adapted to: acquiring channel information data in a second preset period of a terminal to be tested;
the prediction processing module is further adapted to: and inputting the channel information data in the second preset period into a pre-trained channel prediction model for processing to obtain predicted channel information data.
Optionally, the apparatus further comprises: the second model training module is suitable for acquiring sample channel information data of a plurality of user terminals; inputting the sample channel information data of each user terminal into an initial channel prediction model for processing to obtain initial prediction channel data; and calculating loss according to the initial predicted channel data and the real channel information data of the corresponding time period of the user terminal, carrying out back propagation based on the loss, adjusting parameters of the initial channel prediction model, and repeatedly executing the steps until the preset iteration ending condition is met, so as to obtain the channel prediction model.
Alternatively, a mean square error loss function is employed for calculating the loss.
According to yet another aspect of the present invention, there is provided a computing device comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the beam management method.
According to still another aspect of the present invention, there is provided a computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the beam management method described above.
The invention relates to a beam management method, a device, a computing device and a storage medium, which relate to the technical field of wireless technology and determine a transmission scene according to the current coverage information of a terminal to be tested; acquiring feature information to be processed corresponding to a terminal to be tested in a transmission scene; inputting the feature information to be processed into a pre-trained prediction model corresponding to the transmission scene for processing to obtain a model prediction result; and determining the information of the beam to be switched of the terminal to be tested according to the model prediction result, and switching the beam for the terminal to be tested according to the information of the beam to be switched. By means of the method, the future wave beam information can be predicted by combining the deep neural network with wave beam management, errors caused by time delay can be reduced, and the accuracy of wave beam estimation is improved.
The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present invention more readily apparent.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
fig. 1 shows a flowchart of a beam management method provided by an embodiment of the present invention;
fig. 2 is a flowchart of a beam management method according to another embodiment of the present invention;
fig. 3 is a schematic structural diagram of a beam management apparatus according to an embodiment of the present invention;
FIG. 4 illustrates a schematic diagram of a computing device provided by an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Fig. 1 shows a flowchart of a beam management method according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:
step S110, determining a transmission scene according to the current coverage information of the terminal to be tested.
According to the current coverage condition of the terminal to be tested, determining a wireless transmission scene, wherein the transmission scene is divided into a line-of-sight transmission scene and a non-line-of-sight transmission scene, the line-of-sight transmission scene refers to no obvious shielding in the coverage area of the base station, and is relatively open, and the non-line-of-sight transmission scene refers to shielding in the coverage area of the base station. Specifically, a transmission scene corresponding to the base station is determined in advance according to surrounding environment information of the base station, and then the corresponding transmission scene is determined according to the base station to which the coverage area of the terminal to be tested belongs.
Step S120, obtaining feature information to be processed corresponding to the terminal to be tested in the transmission scene.
In order to perform beam management, the information required to be predicted is different in different transmission scenes, the characteristic information required to be predicted is different, and the characteristic information to be processed of the terminal to be tested corresponding to the transmission scenes is obtained.
And step S130, inputting the feature information to be processed into a pre-trained prediction model corresponding to the transmission scene for processing, and obtaining a model prediction result.
And for each transmission scene, training by using sample data through a deep learning algorithm in advance to obtain a prediction model under the transmission scene, inputting the characteristic information to be processed of the terminal to be tested into the prediction model for processing, and outputting a prediction result after the processing of the prediction model.
And step S140, determining the information of the beam to be switched of the terminal to be tested according to the model prediction result, and switching the beam for the terminal to be tested according to the information of the beam to be switched.
According to the beam management method provided by the embodiment, a transmission scene is determined according to the current coverage information of the terminal to be tested; acquiring feature information to be processed corresponding to a terminal to be tested in a transmission scene; inputting the feature information to be processed into a pre-trained prediction model corresponding to the transmission scene for processing to obtain a model prediction result; and determining the information of the beam to be switched of the terminal to be tested according to the model prediction result, and switching the beam for the terminal to be tested according to the information of the beam to be switched. By means of the method, the future wave beam information can be predicted by combining the deep neural network with wave beam management, errors caused by time delay can be reduced, and the accuracy of wave beam estimation is improved.
Fig. 2 shows a flowchart of a beam management method according to another embodiment of the present invention, as shown in fig. 2, the method includes the following steps:
step S210, determining a transmission scene according to the current coverage information of the terminal to be tested.
The transmission scenes are divided into a line-of-sight transmission scene and a non-line-of-sight transmission scene, wherein the line-of-sight transmission scene refers to no obvious shielding in the coverage area of the base station and is relatively open, and the non-line-of-sight transmission scene refers to shielding in the coverage area of the base station. Specifically, a transmission scene corresponding to the base station is determined in advance according to surrounding environment information of the base station, and then the corresponding transmission scene is determined according to the base station to which the coverage area of the terminal to be tested belongs.
In the method of the embodiment, different beam management algorithms are adopted for different transmission scenes, and if the transmission scene is a line-of-sight transmission scene, step S220 is executed; if the transmission scene is a non-line-of-sight transmission scene, step S240 is performed.
S220, acquiring track data in a first preset period of the terminal to be tested, and inputting the track data in the first preset period into a pre-trained track prediction model for processing to obtain predicted track data of the terminal to be tested.
And if the transmission scene is a line-of-sight transmission scene, acquiring track data in a first preset period of the terminal to be tested, inputting the track data into a pre-trained track prediction model for processing, and outputting predicted track data of the terminal to be tested by the track prediction model.
The track prediction model is obtained through training in the following mode: acquiring sample track data of a plurality of user terminals; inputting sample track data of each user terminal into an initial track prediction model for processing to obtain initial predicted track data; and calculating loss according to the initial predicted track data and the real track data of the corresponding period of the user terminal, carrying out back propagation based on the loss, adjusting parameters of the initial track prediction model, and repeatedly executing the steps until the preset iteration ending condition is met, so as to obtain the track prediction model. The initial track prediction model is constructed according to the deep neural network, for example, parameters of the deep neural network are initialized, and the initial track prediction model is obtained.
For example, track data of a plurality of user terminals in an observation period is acquired as sample track data, that is, the sample track data is time sequence data, for example, more than 6 ten thousand groups of sample track data are acquired, and the observation period is expressed as: t= (1, 2,3, …, t) last )，t last Representing the last point in time within the observation period, acquiring trajectory data for a plurality of user terminals within the observation period, expressed as: p= (P) 1 ,P 2 ,…,P i ,…,P N ) Wherein N represents the number of user terminals in the observation period, and the coordinates of the user terminal i at the time point t are as followst＝(1,2,3,…,t last )，/>And->The abscissa and the ordinate of the user terminal i at time t are indicated, respectively.
Inputting track data of each user terminal in an observation period of 1 to T into an initial track prediction model, and obtaining predicted track data of each user terminal in a future period of (t+1) to (t+T) through forward propagation, wherein the predicted track data of the user terminal in the future period of (t+1) to (t+T) is expressed as:the true trajectory data of the user terminal at (t+1) to (t+t) are expressed as: />Calculating the mean square error of the predicted coordinate value and the real coordinate value, and completing the forward propagation process; and then, calculating the gradient value of the loss function relative to the parameter of the initial track prediction model according to a back propagation algorithm, updating the parameter of the initial track prediction model by adopting a gradient descent algorithm, and continuously iterating until the model converges.
Wherein, the mean square error is adopted as the loss function, and the formula is as follows:
after training to obtain a track prediction model, track data of the terminal to be tested in a first preset period is obtained, the first preset period is consistent with the duration of the observation period, the track data in the first preset period is input into the track prediction model for processing, and the track prediction model outputs a predicted track of the terminal to be tested in a future period.
Step S230, determining a coverage area to which the predicted track data belongs, determining information of a beam to be switched of the terminal to be tested according to a mapping relation between the coverage area and the beam, and switching the beam for the terminal to be tested according to the information of the beam to be switched.
And judging the coverage area to which the predicted track data belongs, selecting a corresponding beam according to the mapping relation between the beam and the coverage area, and scanning in a small range according to the predicted track to determine the beam to be switched of the terminal to be tested, and subsequently switching the terminal to be tested to the beam to be switched, so that the pilot frequency overhead can be reduced, and the accuracy of beam management is improved.
The mapping relation between each beam and the corresponding coverage area in the base station is recorded in advance, and in the base station site planning construction stage, the number of the beams and the coverage area range of each beam are known, and each beam and the corresponding coverage area are recorded in a one-to-one correspondence.
In specific implementation, the beam management algorithm of the line-of-sight transmission scenario is executed at the base station side, that is, the main execution body of the step S220 and the step S230 is the base station.
Step S240, obtaining channel information data in a second preset period of the terminal to be tested; and inputting the channel information data in the second preset period into a pre-trained channel prediction model for processing to obtain predicted channel information data.
If the transmission scene is a non-line-of-sight transmission scene, acquiring a plurality of channel information data estimated on the CSI-RS in a preset period of the terminal to be tested, inputting the channel information data into a pre-trained channel prediction model for processing, and outputting predicted channel information data of the terminal to be tested by the channel prediction model.
The channel prediction model is obtained through training in the following mode: acquiring sample channel information data of a plurality of user terminals; inputting the sample channel information data of each user terminal into an initial channel prediction model for processing to obtain initial prediction channel data; and calculating loss according to the initial predicted channel data and the real channel information data of the corresponding time period of the user terminal, carrying out back propagation based on the loss, adjusting parameters of the initial channel prediction model, and repeatedly executing the steps until the preset iteration ending condition is met, so as to obtain the channel prediction model. The initial channel prediction model is constructed according to the deep neural network, for example, parameters of the deep neural network are initialized, and the initial channel prediction model is obtained.
For example, channel information data of a plurality of user terminals in an observation period is acquired as sample channel information data, for example, more than 6 ten thousand sets of sample channel information data are acquired, a sequence of 1 to t' periods is obtainedAs sample channel information data, wherein +_> Representing the frequency response of the v-th transmitting antenna to the u-th receiving antenna on the k-th subcarrier at the nth time point, taking the real part and the imaginary part of the complex number H, namely [ Re (H), im (H), respectively]The method comprises the following steps of:
information H of multiple channels to be 1 to t' period new Input into the initial channel prediction type, initial predicted channel data at future time periods of (T ' +1) to (T ' +t ') are obtained through forward propagation, specifically:wherein T' represents the length of the output channel data sequence; the real channel information data in the (T ' +1) to (T ' +t ') periods are: />Adopting the mean square error as a loss function of the network to finish the forward propagation process; a kind of electronic deviceAnd then, calculating the gradient value of the loss function relative to the parameter of the initial channel prediction model through a back propagation algorithm, updating the parameter by adopting a gradient descent algorithm, and continuously iterating until convergence.
Wherein, the loss function formula is as follows:
after training to obtain a channel prediction model, obtaining channel information data of a terminal to be tested in a second preset period, wherein the second preset period is consistent with the duration of an observation period of a model training stage, inputting the channel information data in the second preset period into the channel prediction model for processing, and outputting the channel information data in a future period by the channel prediction model, wherein the channel information data is specifically expressed as:
wherein (1)> Indicating the frequency response of the nth transmit antenna through the nth receive antenna on the kth subcarrier at the nth point in time.
Step S250, the information of the beam to be switched of the terminal to be tested is determined according to the predicted channel information data, and the beam is switched according to the information of the beam to be switched.
The base station selects the beam information at the corresponding moment according to the predicted channel information data and the conventional technical means of selecting the beam according to the channel information, and then switches the terminal to be tested to the beam to be switched, so that errors caused by time delay can be reduced, and the accuracy of beam estimation and the throughput of the system can be improved.
In particular, step S240 is performed at the user side, and step S250 is performed at the base station side, that is, after the predicted channel information data is obtained at the user side, the predicted channel information data is provided to the base station, so that the base station determines the beam information to be switched according to the predicted channel state information.
According to the beam management method, the method is divided into a line-of-sight transmission scene algorithm and a non-line-of-sight transmission scene algorithm, under the line-of-sight transmission scene, a deep neural network is applied to a base station side for predicting the movement track of a user, and the base station side can accurately acquire the movement track of the user so as to perform beam management, so that pilot frequency overhead can be reduced, and the accuracy of the beam management is improved; in a non-line-of-sight transmission scene, the deep neural network at the terminal side is applied to predict future channel information, and the base station selects beam information according to the predicted channel information, so that errors caused by time delay can be reduced, and the accuracy of beam estimation and the throughput of a system can be improved.
Fig. 3 is a schematic structural diagram of a beam management apparatus according to an embodiment of the present invention, where, as shown in fig. 3, the apparatus includes:
the scene detection module 31 is suitable for determining a transmission scene according to the current coverage information of the terminal to be detected;
the feature acquisition module 32 is adapted to acquire feature information to be processed of the terminal to be detected corresponding to the transmission scene;
the prediction processing module 33 is adapted to input the feature information to be processed into a pre-trained prediction model corresponding to the transmission scene for processing, so as to obtain a model prediction result;
the beam management module 34 is adapted to determine information of a beam to be switched of the terminal to be tested according to the model prediction result, and switch the beam for the terminal to be tested according to the information of the beam to be switched.
In an alternative way, the transmission scenario includes: the prediction model corresponding to the video transmission scene is a track prediction model;
the feature acquisition module 32 is further adapted to: acquiring track data of a terminal to be tested in a first preset period; the prediction processing module 33 is further adapted to: inputting the track data in the first preset period into a pre-trained track prediction model for processing to obtain predicted track data of the terminal to be tested; the beam management module 34 is further adapted to: and determining a coverage area to which the predicted track data belongs, and determining the information of the beam to be switched of the terminal to be tested according to the mapping relation between the coverage area and the beam.
In an alternative, the apparatus further comprises: and the recording module is suitable for pre-recording the mapping relation between each wave beam in the base station and the corresponding coverage area.
In an alternative, the apparatus further comprises: the first model training module is suitable for acquiring sample track data of a plurality of user terminals; inputting sample track data of each user terminal into an initial track prediction model for processing to obtain initial predicted track data; and calculating loss according to the initial predicted track data and the real track data of the corresponding period of the user terminal, carrying out back propagation based on the loss, adjusting parameters of the initial track prediction model, and repeatedly executing the steps until the preset iteration ending condition is met, so as to obtain the track prediction model.
In an alternative way, the transmission scenario includes: a non-line-of-sight transmission scene, wherein a prediction model corresponding to the non-line-of-sight transmission scene is a channel prediction model;
the feature acquisition module 32 is further adapted to: acquiring channel information data in a second preset period of a terminal to be tested;
the prediction processing module 33 is further adapted to: and inputting the channel information data in the second preset period into a pre-trained channel prediction model for processing to obtain predicted channel information data.
In an alternative, the apparatus further comprises: the second model training module is suitable for acquiring sample channel information data of a plurality of user terminals; inputting the sample channel information data of each user terminal into an initial channel prediction model for processing to obtain initial prediction channel data; and calculating loss according to the initial predicted channel data and the real channel information data of the corresponding time period of the user terminal, carrying out back propagation based on the loss, adjusting parameters of an initial channel prediction model, and repeatedly executing the steps until a preset iteration ending condition is met, so as to obtain the channel prediction model.
In an alternative approach, a mean square error loss function is employed for calculating the loss.
Embodiments of the present invention provide a non-volatile computer storage medium storing at least one executable instruction that may perform the beam management method of any of the method embodiments described above.
FIG. 4 illustrates a schematic diagram of an embodiment of a computing device of the present invention, and the embodiments of the present invention are not limited to a particular implementation of the computing device.
As shown in fig. 4, the computing device may include: a processor 402, a communication interface (Communications Interface) 404, a memory 406, and a communication bus 408.
Wherein: processor 402, communication interface 404, and memory 406 communicate with each other via communication bus 408. A communication interface 404 for communicating with network elements of other devices, such as clients or other servers. Processor 402 is configured to execute program 410 and may specifically perform the relevant steps of the beam management method embodiments for a computing device described above.
In particular, program 410 may include program code including computer-operating instructions.
The processor 402 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included by the computing device may be the same type of processor, such as one or more CPUs; but may also be different types of processors such as one or more CPUs and one or more ASICs.
Memory 406 for storing programs 410. Memory 406 may comprise high-speed RAM memory or may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It will be appreciated that the teachings of the present invention described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the present invention.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the above description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.
Various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functionality of some or all of the components according to embodiments of the present invention may be implemented in practice using a microprocessor or Digital Signal Processor (DSP). The present invention can also be implemented as an apparatus or device program (e.g., a computer program and a computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present invention may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specifically stated.

Claims (10)

1.一种波束管理方法，其特征在于，包括：1. A beam management method, comprising: 根据待测终端的当前覆盖信息确定传输场景；Determine the transmission scenario according to the current coverage information of the terminal to be tested; 获取所述待测终端对应在所述传输场景下的待处理特征信息；Obtaining feature information to be processed corresponding to the terminal under test in the transmission scenario; 将所述待处理特征信息输入至所述传输场景对应的预先训练的预测模型进行处理，得到模型预测结果；Inputting the feature information to be processed into a pre-trained prediction model corresponding to the transmission scenario for processing to obtain a model prediction result; 根据所述模型预测结果确定所述待测终端的待切换波束信息，根据待切换波束信息为所述待测终端切换波束。The beam information to be switched of the terminal to be tested is determined according to the model prediction result, and the beam is switched for the terminal to be tested according to the beam information to be switched. 2.根据权利要求1所述的方法，其特征在于，所述传输场景包括：视距传输场景，视距传输场景对应的预测模型为轨迹预测模型；2. The method according to claim 1 is characterized in that the transmission scenario includes: a line-of-sight transmission scenario, and the prediction model corresponding to the line-of-sight transmission scenario is a trajectory prediction model; 所述获取所述待测终端对应在所述传输场景下的待处理特征信息具体包括：获取待测终端的第一预设时段内的轨迹数据；The obtaining of the feature information to be processed corresponding to the terminal under test in the transmission scenario specifically includes: obtaining trajectory data of the terminal under test within a first preset time period; 所述将所述待处理特征信息输入至所述传输场景对应的预先训练的预测模型进行处理，得到模型预测结果具体包括：The step of inputting the feature information to be processed into a pre-trained prediction model corresponding to the transmission scenario for processing to obtain a model prediction result specifically includes: 将所述第一预设时段内的轨迹数据输入至预先训练的轨迹预测模型进行处理，得到所述待测终端的预测轨迹数据；Inputting the trajectory data within the first preset time period into a pre-trained trajectory prediction model for processing to obtain predicted trajectory data of the terminal to be tested; 所述根据所述模型预测结果确定所述待测终端的待切换波束信息具体包括：The determining the to-be-switched beam information of the terminal to be tested according to the model prediction result specifically includes: 确定所述预测轨迹数据归属的覆盖区域，根据覆盖区域与波束之间的映射关系，确定所述待测终端的待切换波束信息。Determine the coverage area to which the predicted trajectory data belongs, and determine the beam information to be switched of the terminal to be tested according to a mapping relationship between the coverage area and the beam. 3.根据权利要求2所述的方法，其特征在于，所述方法还包括：预先记录基站中每一个波束与其对应的覆盖范围的映射关系。3. The method according to claim 2 is characterized in that the method also includes: pre-recording the mapping relationship between each beam in the base station and its corresponding coverage range. 4.根据权利要求2或3所述的方法，其特征在于，所述方法还包括：4. The method according to claim 2 or 3, characterized in that the method further comprises: 获取多个用户终端的样本轨迹数据；Obtaining sample trajectory data of multiple user terminals; 将每一个用户终端的样本轨迹数据输入至初始轨迹预测模型进行处理，得到初始预测轨迹数据；Inputting the sample trajectory data of each user terminal into the initial trajectory prediction model for processing to obtain initial predicted trajectory data; 根据所述初始预测轨迹数据与该用户终端的相应时段的真实轨迹数据计算损失，基于所述损失进行反向传播，调节所述初始轨迹预测模型的参数，重复执行本步骤直至满足预设迭代结束条件，得到所述轨迹预测模型。The loss is calculated according to the initial predicted trajectory data and the real trajectory data of the user terminal in the corresponding period, and back propagation is performed based on the loss to adjust the parameters of the initial trajectory prediction model. This step is repeated until a preset iteration end condition is met to obtain the trajectory prediction model. 5.根据权利要求1所述的方法，其特征在于，所述传输场景包括：非视距传输场景，非视距传输场景对应的预测模型为信道预测模型；5. The method according to claim 1, characterized in that the transmission scenario includes: a non-line-of-sight transmission scenario, and the prediction model corresponding to the non-line-of-sight transmission scenario is a channel prediction model; 所述获取所述待测终端对应在所述传输场景下的待处理特征信息具体包括：获取所述待测终端的第二预设时段内的信道信息数据；The obtaining of the to-be-processed characteristic information of the terminal under test corresponding to the transmission scenario specifically includes: obtaining channel information data of the terminal under test within a second preset time period; 所述将所述待处理特征信息输入至所述传输场景对应的预先训练的预测模型进行处理，得到模型预测结果具体包括：The step of inputting the feature information to be processed into a pre-trained prediction model corresponding to the transmission scenario for processing to obtain a model prediction result specifically includes: 将所述第二预设时段内的信道信息数据输入至预先训练的信道预测模型中进行处理，得到预测信道信息数据。The channel information data within the second preset time period is input into a pre-trained channel prediction model for processing to obtain predicted channel information data. 6.根据权利要求5所述的方法，其特征在于，所述方法还包括：6. The method according to claim 5, characterized in that the method further comprises: 获取多个用户终端的样本信道信息数据；Acquiring sample channel information data of multiple user terminals; 将每一个用户终端的样本信道信息数据输入至初始信道预测模型中进行处理，得到初始预测信道数据；Inputting the sample channel information data of each user terminal into the initial channel prediction model for processing to obtain initial predicted channel data; 根据所述初始预测信道数据与该用户终端的相应时段的真实信道信息数据计算损失，基于所述损失进行反向传播，调节所述初始信道预测模型的参数，重复执行本步骤直至满足预设迭代结束条件，得到所述信道预测模型。The loss is calculated based on the initial predicted channel data and the real channel information data of the corresponding time period of the user terminal, and back propagation is performed based on the loss to adjust the parameters of the initial channel prediction model. This step is repeated until the preset iteration end condition is met to obtain the channel prediction model. 7.根据权利要求4或6所述的方法，其特征在于，采用均方误差作为损失函数用于计算损失。7. The method according to claim 4 or 6 is characterized in that the mean square error is used as the loss function to calculate the loss. 8.一种波束管理装置，其特征在于，包括：8. A beam management device, comprising: 场景检测模块，适于根据待测终端的当前覆盖信息确定传输场景；A scene detection module, adapted to determine a transmission scene according to current coverage information of the terminal to be tested; 特征获取模块，适于获取所述待测终端对应在所述传输场景下的待处理特征信息；A feature acquisition module, adapted to acquire feature information to be processed corresponding to the terminal to be tested in the transmission scenario; 预测处理模块，适于将所述待处理特征信息输入至所述传输场景对应的预先训练的预测模型进行处理，得到模型预测结果；A prediction processing module, adapted to input the feature information to be processed into a pre-trained prediction model corresponding to the transmission scenario for processing to obtain a model prediction result; 波束管理模块，适于根据所述模型预测结果确定所述待测终端的待切换波束信息，根据待切换波束信息为待测终端切换波束。The beam management module is adapted to determine the beam information to be switched of the terminal to be tested according to the model prediction result, and switch the beam for the terminal to be tested according to the beam information to be switched. 9.一种计算设备，包括：处理器、存储器、通信接口和通信总线，所述处理器、所述存储器和所述通信接口通过所述通信总线完成相互间的通信；9. A computing device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other through the communication bus; 所述存储器用于存放至少一可执行指令，所述可执行指令使所述处理器执行如权利要求1-7中任一项所述的波束管理方法对应的操作。The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the beam management method according to any one of claims 1-7. 10.一种计算机存储介质，所述存储介质中存储有至少一可执行指令，所述可执行指令使处理器执行如权利要求1-7中任一项所述的波束管理方法对应的操作。10. A computer storage medium, wherein at least one executable instruction is stored in the storage medium, and the executable instruction enables a processor to perform operations corresponding to the beam management method according to any one of claims 1 to 7.
CN202211211021.9A 2022-09-30 2022-09-30 Beam management method, device, computing equipment and storage medium Pending CN117880835A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211211021.9A CN117880835A (en) 2022-09-30 2022-09-30 Beam management method, device, computing equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211211021.9A CN117880835A (en) 2022-09-30 2022-09-30 Beam management method, device, computing equipment and storage medium

Publications (1)

Publication Number Publication Date
CN117880835A true CN117880835A (en) 2024-04-12

Family

ID=90575948

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211211021.9A Pending CN117880835A (en) 2022-09-30 2022-09-30 Beam management method, device, computing equipment and storage medium

Country Status (1)

Country Link
CN (1) CN117880835A (en)

Similar Documents

Publication Publication Date Title
WO2023143572A1 (en) Positioning method based on artificial intelligence (ai) model, and communication device
CN116234001A (en) Positioning method and communication equipment
JP7518296B2 (en) Enhanced Fingerprint Positioning
CN116234000A (en) Positioning method and communication equipment
US20240373257A1 (en) Information interaction method and apparatus, and communication device
EP4266603A1 (en) Space division-based data processing method and communication device
CN108370303A (en) Method and apparatus related with the Selective long-range DEPT of radio signal
CN108646213A (en) Direct wave AOA determination methods under a kind of indoor multipath environment
CN113169777A (en) beam alignment
US20210281311A1 (en) Timing measurement method and related device
JP2018514994A (en) Beam information acquisition method, apparatus and communication system
WO2023088387A1 (en) Channel prediction method and apparatus, ue, and system
CN115314130A (en) A baseline calibration method, device, network side device and storage medium
CN113543017A (en) Wave beam switching method of millimeter wave internet of vehicles and related equipment
CN117880835A (en) Beam management method, device, computing equipment and storage medium
CN110890932A (en) Method and device for determining 5G millimeter wave channel information based on ESN model
CN115334523B (en) Network coverage measurement method, device, equipment and computer-readable storage medium
WO2024120444A1 (en) Model supervision method and apparatus, terminal, network side device and readable storage medium
CN116095700B (en) 5GtoB coverage optimization method, system and storage medium based on DOA
WO2024120445A1 (en) Model input information determination method, apparatus, device and system, and storage medium
WO2025140432A1 (en) Information reporting method and apparatus
CN120034820A (en) Positioning method, device, equipment and readable storage medium based on AI model
WO2024067281A1 (en) Ai model processing method and apparatus, and communication device
WO2024083004A1 (en) Ai model configuration method, terminal, and network side device
CN119547519A (en) Data efficient updating for channel classification

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination