WO2024255991A1

WO2024255991A1 - Ping-pong handover cost reduction

Info

Publication number: WO2024255991A1
Application number: PCT/EP2023/065816
Authority: WO
Inventors: Janne ALI-TOLPPA; Ahmad Masri; Hans Thomas HÖHNE; Teemu Mikael VEIJALAINEN; Amaanat ALI
Original assignee: Nokia Technologies Oy
Priority date: 2023-06-13
Filing date: 2023-06-13
Publication date: 2024-12-19

Abstract

Embodiments of the present disclosure relate to devices, methods, apparatuses and computer readable storage media of. The method comprises obtaining, by a source network node and from a terminal device, a report of a mobility trigger event with a measurement report associated with a serving network node and one or more neighboring network nodes; determining, based on the measurement report, whether a handover to at least one of the one or more neighboring network nodes, triggered by the mobility trigger event, is likely to lead to a ping-pong; configuring, based on the determination, at least a timer for delaying resource release by the source network node and at least one return condition for the terminal device to return to be served by the source network node; and transmitting to the terminal device, a handover command along with the configured timer and the at least one return condition.

Description

PING-PONG HANDOVER COST REDUCTION

FIELD

[0001] Embodiments of the present disclosure generally relate to the field of telecommunication and in particular to devices, methods, apparatuses and computer readable storage media of ping-pong handover cost reduction.

BACKGROUND

[0002] In a handover procedure, a connection to a current-serving network node from a terminal device may be switched to a new network node. The current-serving network node may act as a source network node of the handover procedure and the new network node may act as a target network node of the handover procedure.

[0003] The execution of handover may be delayed due to Time-to-Trigger (TTT) (e.g., -200-300ms), offset (e.g., l-3dB), and signalling delays. On the other hand, shorter TTT and smaller offset may lead to too early triggering and/or triggering handover to suboptimal target.

SUMMARY

[0004] In a first aspect, there is provided an apparatus. The apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: obtain, from a terminal device, a report of a mobility trigger event with a measurement report associated with a serving network node and one or more neighboring network nodes; determine, based on the measurement report, whether a handover to at least one of the one or more neighboring network nodes, triggered by the mobility trigger event, is likely to lead to a ping-pong; configure, based on the determination, at least a timer for delaying resource release by the apparatus and at least one return condition for the terminal device to return to be served by the apparatus; and transmit to the terminal device, a handover command along with the configured timer and the at least one return condition.

[0005] In a second aspect, there is provided an apparatus. The apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: transmit, to a source network node, a report of a mobility trigger event with a measurement report associated with a serving network node and one or more neighboring network nodes; receive, from the source network node, a handover command, for a handover triggered by the mobility trigger event, along with at least a timer for delaying resource release by the source network node and at least one return condition for the terminal device to return to be served by the source network node, wherein the handover to at least one of the one or more neighboring network nodes is likely to lead to a ping-pong.

[0006] In a third aspect, there is provided a method. The method comprises obtaining, by a source network node and from a terminal device, a report of a mobility trigger event with a measurement report associated with a serving network node and one or more neighboring network nodes; determining, based on the measurement report, whether a handover to at least one of the one or more neighboring network nodes, triggered by the mobility trigger event, is likely to lead to a ping-pong; configuring, based on the determination, at least a timer for delaying resource release by the source network node and at least one return condition for the terminal device to return to be served by the source network node; and transmitting to the terminal device, a handover command along with the configured timer and the at least one return condition.

[0007] In a fourth aspect, there is provided a method. The method comprises transmitting, from a terminal device and to a source network node, a report of a mobility trigger event with a measurement report associated with a serving network node and one or more neighboring network nodes; receiving, from the source network node, a handover command for a handover triggered by the mobility trigger event along with at least a timer for delaying resource release by the source network node and at least one return condition for the terminal device to return to be served by the source network node, wherein the handover to at least one of the one or more neighboring network nodes is likely to lead to a ping-pong; and performing the handover based on the handover command, the timer and the at least one return condition.

[0008] In a fifth aspect, there is provided an apparatus comprising means for obtaining, from a terminal device, a report of a mobility trigger event with a measurement report associated with a serving network node and one or more neighboring network nodes; means for determining, based on the measurement report, whether a handover to at least one of the one or more neighboring network nodes, triggered by the mobility trigger event, is likely to lead to a ping-pong; means for configuring, based on the determination, at least a timer for delaying resource release by the apparatus and at least one return condition for the terminal device to return to be served by the apparatus; and means for transmitting to the terminal device, a handover command along with the configured timer and the at least one return condition.

[0009] In a sixth aspect, there is provided an apparatus comprising means for transmitting, to a source network node, a report of a mobility trigger event with a measurement report associated with a serving network node and one or more neighboring network nodes; means for receiving, from the source network node, a handover command , for a handover triggered by the mobility trigger event, along with at least a timer for delaying resource release by the source network node and at least one return condition for the terminal device to return to be served by the source network node, wherein the handover to at least one of the one or more neighboring network nodes is likely to lead to a ping-pong; and means for performing the handover based on the handover command, the timer and the at least one return condition.

[0010] In a seventh aspect, there is provided a computer readable medium having a computer program stored thereon which, when executed by at least one processor of an apparatus, causes the apparatus to carry out the method according to the third aspect or the fourth aspect.

[0011] Other features and advantages of the embodiments of the present disclosure will also be apparent from the following description of specific embodiments when read in conjunction with the accompanying drawings, which illustrate, by way of example, the principles of embodiments of the disclosure.

BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Embodiments of the disclosure are presented in the sense of examples and their advantages are explained in greater detail below, with reference to the accompanying drawings.

[0013] FIG. 1 illustrates an example environment in which example embodiments of the present disclosure may be implemented;

[0014] FIG. 2 shows a signaling chart illustrating an example of process according to some example embodiments of the present disclosure;

[0015] FIG. 3 shows an example of process of ping-pong prediction according to some example embodiments of the present disclosure; [0016] FIG. 4 shows an example of process of ping-pong prediction according to some example embodiments of the present disclosure;

[0017] FIG. 5 shows a flowchart of an example method of ping-pong handover cost reduction according to some example embodiments of the present disclosure;

[0018] FIG. 6 shows a flowchart of an example method of ping-pong handover cost reduction according to some example embodiments of the present disclosure;

[0019] FIG. 7 shows a simplified block diagram of a device that is suitable for implementing example embodiments of the present disclosure; and

[0020] FIG. 8 shows a block diagram of an example computer readable medium in accordance with some embodiments of the present disclosure.

[0021] Throughout the drawings, the same or similar reference numerals may represent the same or similar element.

DETAILED DESCRIPTION

[0022] Principle of the present disclosure will now be described with reference to some example embodiments. It is to be understood that these embodiments are described only for the purpose of illustration and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitation as to the scope of the disclosure. Embodiments described herein may be implemented in various manners other than the ones described below.

[0023] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein may have the same meaning as commonly understood by one of ordinary skills in the art to which this disclosure belongs.

[0024] References in the present disclosure to “one embodiment,” “an embodiment,” “an example embodiment,” and the like indicate that the embodiment described may include a particular feature, structure, or characteristic, but it is not necessary that every embodiment includes the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described. [0025] It shall be understood that although the terms “first,” “second” and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and similarly, a second element could be termed a first element, without departing from the scope of example embodiments. As used herein, the term “and/or” includes any and all combinations of one or more of the listed terms.

[0026] As used herein, “at least one of the following: <a list of two or more elements>” and “at least one of <a list of two or more elements>” and similar wording, where the list of two or more elements are joined by “and” or “or”, mean at least any one of the elements, or at least any two or more of the elements, or at least all the elements.

[0027] As used herein, unless stated explicitly, performing a step “in response to A” does not indicate that the step is performed immediately after “A” occurs and one or more intervening steps may be included.

[0028] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises”, “comprising”, “has”, “having”, “includes” and/or “including”, when used herein, specify the presence of stated features, elements, and/or components etc., but do not preclude the presence or addition of one or more other features, elements, components and/ or combinations thereof.

[0029] As used in this application, the term “circuitry” may refer to one or more or all of the following:

(a) hardware-only circuit implementations (such as implementations in only analog and/or digital circuitry) and

(b) combinations of hardware circuits and software, such as (as applicable):

(i) a combination of analog and/or digital hardware circuit(s) with software/firmware and

(ii) any portions of hardware processor(s) with software (including digital signal processor(s)), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions) and (c) hardware circuit(s) and or processor(s), such as a microprocessor(s) or a portion of a microprocessor(s), that requires software (e.g., firmware) for operation, but the software may not be present when it is not needed for operation.

[0030] This definition of circuitry applies to all uses of this term in this application, including in any claims. As a further example, as used in this application, the term circuitry also covers an implementation of merely a hardware circuit or processor (or multiple processors) or portion of a hardware circuit or processor and its (or their) accompanying software and/or firmware. The term circuitry also covers, for example and if applicable to the particular claim element, a baseband integrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in server, a cellular network node, or other computing or network node.

[0031] As used herein, the term “communication network” refers to a network following any suitable communication standards, such as New Radio (NR), Long Term Evolution (LTE), LTE- Advanced (LTE- A), Wideband Code Division Multiple Access (WCDMA), High-Speed Packet Access (HSPA), Narrow Band Internet of Things (NB-IoT), an Enhanced Machine type communication (eMTC) and so on. Furthermore, the communications between a terminal device and a network node in the communication network may be performed according to any suitable generation communication protocols, including, but not limited to, the first generation (1G), the second generation (2G), 2.5G, 2.75G, the third generation (3G), the fourth generation (4G), 4.5G, the fifth generation (5G), the sixth generation (6G) communication protocols, and/or any other protocols either currently known or to be developed in the future. Embodiments of the present disclosure may be applied in various communication systems. Given the rapid development in communications, there will of course also be future type communication technologies and systems with which the present disclosure may be embodied. It should not be seen as limiting the scope of the present disclosure to only the aforementioned system.

[0032] As used herein, the terms “network node”, “radio network node” and/or “radio access network node” refers to a node in a communication network via which a terminal device accesses the network and receives services therefrom. The network node may refer to a base station (BS) or an access point (AP), for example, a node B (NodeB or NB), an evolved NodeB (eNodeB or eNB), an NR NB (also referred to as a gNB), a Remote Radio Unit (RRU), a remote radio head (RRH), a relay, an Integrated Access and Backhaul (IAB) node, a low power node such as a femto, a pico, a non-terrestrial network (NTN) or non- ground network node such as a satellite network node, a low earth orbit (LEO) satellite and a geosynchronous earth orbit (GEO) satellite, an aircraft network node, and so forth, depending on the applied terminology and technology. In some example embodiments, low earth orbit (RAN) split architecture includes a Centralized Unit (CU) and a Distributed Unit (DU). In some other example embodiments, part of the radio access network node or full of the radio access network node may embarked on an airborne or space-borne NTN vehicle.

[0033] The term “terminal device” refers to any end device that may be capable of wireless communication. By way of example rather than limitation, a terminal device may also be referred to as a communication device, user equipment (UE), a Subscriber Station (SS), a Portable Subscriber Station, a Mobile Station (MS), or an Access Terminal (AT). The terminal device may include, but not limited to, a mobile phone, a cellular phone, a smart phone, voice over IP (VoIP) phones, wireless local loop phones, a tablet, a wearable terminal device, a personal digital assistant (PDA), portable computers, desktop computer, image capture terminal devices such as digital cameras, gaming terminal devices, music storage and playback appliances, vehicle-mounted wireless terminal devices, wireless endpoints, mobile stations, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), USB dongles, smart devices, wireless customer-premises equipment (CPE), an Internet of Things (loT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (e.g., remote surgery), an industrial device and applications (e.g., a robot and/or other wireless devices operating in an industrial and/or an automated processing chain contexts), a consumer electronics device, a device operating on commercial and/or industrial wireless networks, and the like. The terminal device may also correspond to a Mobile Termination (MT) part of an IAB node (e.g., a relay node). In the following description, the terms “terminal device”, “communication device”, “terminal”, “user equipment” and “UE” may be used interchangeably.

[0034] As used herein, the term “resource,” “transmission resource,” “resource block,” “physical resource block” (PRB), “uplink resource,” or “downlink resource” may refer to any resource for performing a communication, for example, a communication between a terminal device and a network node, such as a resource in time domain, a resource in frequency domain, a resource in space domain, a resource in code domain, or any other resource enabling a communication, and the like. In the following, unless explicitly stated, a resource in both frequency domain and time domain will be used as an example of a transmission resource for describing some example embodiments of the present disclosure. It is noted that example embodiments of the present disclosure are equally applicable to other resources in other domains.

[0035] FIG. 1 shows an example communication network 100 in which embodiments of the present disclosure may be implemented. As shown in FIG. 1, the communication network 100 may include a terminal device 110. Hereinafter the terminal device 110 may also be referred to as a UE.

[0036] The communication network 100 may further include network nodes 120-1 and 120- 2. Hereinafter the network node 120 may also be referred to as a gNB, respectively. As an example, the terminal device 110 may communicate with the network node 120-1 within a coverage of a cell 102 managed by the network node 120-1. If the radio link between the terminal device 110 and the network node 120-1 is getting worse, for example, due to the movement of the terminal device, a handover procedure may occur. After the handover successfully completes, the terminal device 110 may communicate with the network node 120-2 within a coverage of a cell 104 managed by the network node 120-2. In this handover procedure, the network node 120-1 may also be referred to as a source network node and the network node 120-2 may also be referred to as a target network node.

[0037] It is to be understood that the number of network nodes and terminal devices shown in FIG. 1 is given for the purpose of illustration without suggesting any limitations. The communication network 100 may include any suitable number of network nodes and terminal devices.

[0038] In some example embodiments, links from the network nodes 120-1 or 120-2 to the terminal device 110 may be referred to as a downlink (DL), while links from the terminal device 110 to the network nodes 120-1 or 120-2 may be referred to as an uplink (UL). In DL, the network nodes 120-1 or 120-2 is a transmitting (TX) device (or a transmitter) and the terminal device 110 is a receiving (RX) device (or receiver). In UL, the terminal device 110 is a TX device (or transmitter) and the network nodes 120-1 or 120-2 is a RX device (or a receiver).

[0039] Communications in the communication network 100 may be implemented according to any proper communication protocol(s), includes, but not limited to, cellular communication protocols of the first generation (1G), the second generation (2G), the third generation (3G), the fourth generation (4G), 5G, the sixth generation (6G), and the like, wireless local network communication protocols such as Institute for Electrical and Electronics Engineers (IEEE) 802.11 and the like, and/or any other protocols currently known or to be developed in the future. Moreover, the communication may utilize any proper wireless communication technology, includes but not limited to: Code Division Multiple Access (CDMA), Frequency Division Multiple Access (FDMA), Time Division Multiple Access (TDMA), FDD, TDD, Multiple-Input Multiple-Output (MIMO), Orthogonal Frequency Division Multiple (OFDM), Discrete Fourier Transform spread OFDM (DFT-s- OFDM) and/or any other technologies currently known or to be developed in the future.

[0040] As described above, the execution of handover may be delayed due to TTT (e.g., -200-300ms), offset (e.g., l-3dB), and signalling delays. On the other hand, shorter TTT and smaller offset may lead to too early triggering and/or triggering handover to suboptimal target. Mobility Robustness Optimization (MRO) tries to adjust handover parameters based on too early/too late handovers, but problem may be more complicated.

[0041] MRO algorithms are well-known methods for optimizing mobility parameters to improve mobility performance, e.g., minimize mobility-related failures and unnecessary handovers.

[0042] The common approach in MRO algorithms is to optimize the Cell Individual Offset (CIO) and TTT, i.e., the key parameters in controlling the HO procedure initiation. The network can control the handover procedure between any cell pair in the network by defining different CIO and TTT values. Different CIO and TTT configurations are needed for mobile terminals with different speeds. The faster the terminals are, the sooner the handover procedure must be started. This goal is achieved by either increasing the CIO (i.e., the offset between the measured signal power of the serving cell and the target cell) or decreasing the TTT (i.e., the interval, during which the trigger requirement is fulfilled). In contrast, in the cell boundaries dominated by slow users, the handover procedures are started relatively later by choosing the lower values for the CIO or higher TTT.

[0043] Whereas the speed of the mobile terminals plays an obvious role, it is not the only criteria. Slow mobile terminals may also be at risk (requiring earlier handovers) when moving through areas with significant propagation changes (e.g., very steep shadowing slope). Fast mobile terminals may not be at risk when moving through areas with little propagation changes (e.g., flat shadowing slopes). Hence, even if velocity could be instantaneously estimated with enough accuracy (which is extremely challenging or even impossible), velocity-based methods would not always react correctly. [0044] The mobility-related failures can be classified into four categories, namely Too Early (TE) handover failures, Too Late (TL) handover failures, Ping-pong (PP) handover failures and Wrong Cell (WC) Handover failures.

[0045] The TE handover failure happens when the UE handovers to target cell before the link quality of the target cell is not good enough. In one example, when the A3 entry condition has been met, the TTT timer expires, and UE performs the handover procedure. However, shortly after the handover, it experiences Radio Link Failure (RLF). In these cases, it is apparent that the handover procedure should have started relatively later. Hence, the MRO reduces the related CIO value. Another example of a too early initiated handover is the expiry of the timer T304, also called “Handover Failure”. This happens, when the target cell is not good enough, such that even the random access channel (RACH) is not successful.

[0046] In the TL handover failure, either UE did not even send out a measurement report (e.g., since the TTT timer did not expire before the RLF), or the measurement report or the handover command got lost due to degrading channel conditions, and thus the UE has not started the handover procedure. The solution for eliminating these failures is to start the handover relatively sooner, hence, the MRO increases the related CIO.

[0047] The PP handover failure refer to cases that the UE hands over to the target cell but shortly after it has to handover back to the source cell. This case is usually considered as another form of TE handover, although in some cases a ping-pong may also be necessary to avoid an RLF. The ping-pongs may happen, for example, when a UE is moving along a cell border area. For example, as shown in FIG. 1, the terminal device 110 may mover along the border area of the cell 102 and the cell 104. After a handover to the cell 104 completes, the terminal device 110 may handover back to the cell 102 within a short time period. This phenomenon may be considered as a ping-pong.

[0048] In the WC handover failure, RLF occurs in the target cell shortly after a handover has been completed, and the UE attempts to re-establish its radio link in a cell which is neither the source cell nor the target cell. Alternatively, the timer T304 expires during the handover procedure (i.e., “Handover failure”), and the UE attempts to re-establish its radio link in a cell which is neither the source cell nor the target cell.

[0049] Most mobility failures are caused by the failure of receiving the handover command on time from the source cell. To address this issue, conditional handover (CHO) has been introduced in NR where the handover preparation is de-coupled from the execution phase. Herein, the source node triggers the preparation of one or more target cells early when the UE still has a very good radio link to the source node. The source node provides the configurations of the prepared target cells to the UE along with a CHO execution condition that is associated with each prepared target cell. After receiving the configurations of the target cells, the UE evaluates the CHO execution conditions to trigger the handover execution when the condition is met.

[0050] While sometimes ping-pongs are necessary, each such handover has cost in terms of interruption time for the UE and signalling between the UE and the network. Therefore, it would be desirable to reduce the number of unnecessary ping-pong handovers or their cost.

[0051] It has been proposed that the ping-pongs may be predicted based on a machinelearning model. One challenge with ML based predictions is that they are predictions, i.e., stating that certain mobility events are more likely in the future, but typically it is not possible to make such predictions completely accurate. This uncertainty is not only because of the performance of the predictive ML model, but because there is inherently unpredictable behaviour in mobility situations.

[0052] A further problem with this is that the accuracy of a machine learning model can dramatically decrease, if there is significant data or concept shift compared to the data it was trained with. Such deteriorations can happen very suddenly, for example if there is a failure in the network causing cells or beams to go down. In this case, mobility decisions made directly based on the ML model can suddenly become catastrophically wrong.

[0053] Meanwhile, network reliability is usually the most important network metric. Therefore, for ML-based mobility optimization solutions, methods that are robust and tolerant against wrong predictions or complete failures of ML models are needed.

[0054] Therefore, a mechanism for reducing the cost of ping-pong handovers and the cost of deployment of localized machine-learning models may need to be further discussed.

[0055] The present disclosure proposes a solution of ping-pong handover cost reduction. In this solution, a source network node obtains, from a terminal device, a report of a mobility trigger event with a measurement report associated with a serving network node and one or more neighboring network nodes. The source network node determines whether a handover to at least one of the one or more neighboring network nodes, triggered by the mobility trigger event, is likely to lead to a ping-pong based on the measurement report and configure a handover command to the at least one of the one or more candidate network nodes. The handover command comprises at least one return condition for the terminal device to return to be served by the source network node and a timer for delaying resource release by the source network node. The source network node transmits to the terminal device, a handover command along with the configured timer and the at least one return condition.

[0056] Based on the solution, the training data collection, training and inference can all be done in the network and even in the source network node itself, making deployment and lifecycle management straightforward. Furthermore, the source network node reserves resources to mitigate the impact of a ping-pong only when one is likely instead of preparing for a ping-pong in every handover, which would waste a lot of source network node resources.

[0057] Example embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0058] Reference is now made to FIG. 2, which shows a signaling chart 200 for communication according to some example embodiments of the present disclosure. As shown in FIG. 2, the signaling chart 200 involves a terminal device 110 and a source network node 120-1 and a target network node 120-2. For the purpose of discussion, reference is made to FIG. 1 to describe the signaling chart 200. It would be appreciated that the target network node 120-2 may also act as a source network node in some cases and perform similar operations as described with respect to the source network node 120-1 below.

[0059] As shown in FIG. 2, the source network node 120-1 transmit (202), to the terminal device 110, a configuration for a measurement report. The configuration may indicate, to the terminal device 110, that the terminal device 110 should collect measurement results of a reference signal on the number of best network nodes (which may comprise a serving network node and one or more neighboring network nodes) within a time window with a measurement granularity.

[0060] For example, the measurement results of the reference signal may refer to a plurality of measurements on reference signal received power (RSRP), reference signal receiving quality (RSRQ) and/or signal to interference plus noise ratio (SINR).

[0061] In some embodiments, the configuration may indicate an event that may trigger the terminal device 110 to report the measurement report, for example, this event may be a selected mobility event, like A3, or a new event.

[0062] In some embodiments, the configuration may also indicate the time window for the measurements, the measurement granularity (or a measurement frequency) and/or the number of best network nodes (e.g., strongest cells) to be measured and reported. The best network nodes may comprise a network node current serving the terminal device, i.e., the source network node and one or more strongest neighbor network nodes. The one or more strongest neighbor network nodes hereinafter may also be referred to as one or more candidate network nodes for the handover of the terminal device 110.

[0063] Based on the configuration, the terminal device 110 may perform (204) corresponding measurements and collect samples of the measurements of the number of best network nodes triggered by the mobility event in the time window and with the measurement granularity that are indicated in the configuration and transmit (206), to the source network node 120-1, a measurement report at least comprising samples of measurement results of the number of best network nodes in the time window with the measurement granularity.

[0064] The source network node 120-1 then may determine (208) whether at least one of the best network nodes (i.e., candidate/neighboring network nodes for the handover) is likely to lead a ping-pong (i.e., is likely to suffer the ping-pong) based on the measurement report.

[0065] For example, a prediction of the ping-pong may be performed by the source network node 120-1 by using a machine-learning model deployed at the source network node 120-1, which may be implemented as a machine-learning-based predictive binary classifier or a support vector machines (SVM).

[0066] The machine learning model deployed at the source network node 120-1 may be trained for the prediction of the ping-pong. In the training phase, for example, terminal devices may be configured with a configuration to report the measurements that is used during the inference of the ping-pong. This configuration may be same as the configuration provided to the terminal device 110 as described above. Then the source network node 120- 1 may store these measurements as the training dataset.

[0067] Then the source network device 120-1 may keep observing whether at least one of the terminal devices returns back with ping-pong within a configured time window Tping-pong. Then the observation results and the measurements stored as the training dataset may be joined together, such that for each reported measurement sequence triggered by a trigger event, a label for if it led to a ping-pong or not can be created. Then the labelled dataset may be used to train the machine learning model for the prediction of the ping-pong.

[0068] Based on the well-trained machine learning model, the source network node 120-1 may determine whether at least one of the best network nodes is likely to suffer the ping- pong. In this situation, the received measurement report may be used as the input to the machine learning model for the prediction of the ping-pong and the output of the machine learning model may indicate whether the at least one of the best network nodes is likely to lead a ping-pong.

[0069] The machine learning model has been evaluated for two different approaches for mobility event prediction namely predicting the event directly from the input data, or a 2- step approach, where the future RSRP values of the input beams or cells are first predicted with a regression model and the predicted values are used in a 2^nd step to detect future mobility events, like ping-pongs.

[0070] FIG. 3 shows an example of the 2-step approach for ping-pong prediction according to some example embodiments of the present disclosure.

[0071] As shown, the measurement results received by the source network node 120-1, for example, samples of RSRP measurement results 301 within a time window may be provided to a RSRP prediction model 302 as input. The RSRP prediction model 302 may predict a set of further RSRP results (RSRP results within a predetermined time period after the handover completes) and provide the of further RSRP results to the ping-pong prediction model 303. Then the output 304 of the ping-pong prediction model 303 may indicate whether a handover back (i.e., ping-pong) will occur within the predetermined time period after the handover completes.

[0072] FIG. 4 shows an example of the direct prediction approach for ping-pong prediction according to some example embodiments of the present disclosure.

[0073] As shown, the measurement results received by the source network node 120-1, for example, samples of RSRP measurement results 401 within a time window may be provided to an input window 402 of the ping-pong prediction model 410. Then the Long Short Term Memory (LSTM) 403 layer of the ping-pong prediction model 410 may analyze the input by using a time sequence. The LSTM may be considered as Recursive Neural Network (RNN).

[0074] Then the analyzed input date may be provided from the LSTM layer 403 to one or more fully connected layers 404, to exact features as input for the binary classifier/ SVM 405. The binary classifier/ SVM 405 may output a result of the ping-pong status based on the input from the one or more fully connected layers 404, e.g., whether one or more network node is likely to suffer the ping-pong within a short time period after a handover completes.

[0075] In this way, a machine-learning based model deployed at the source network node 120-1 may help the source network node 120-1 to predict whether the handover is likely to suffer a risk of ping-ping. Based on the prediction result, the source network node 120-1 may further manage the handover to reduce the ping-pong cost.

[0076] Referring back to FIG. 2, if the source network node 120-1 determines that a handover to at least one of the one or more neighboring network nodes, triggered by the mobility trigger event, is likely to lead to a ping-pong, the source network node 120-1 may configure at least one return condition for the terminal device 110 to return to be served by the source network node 120-1 and a timer for delaying a release of resources by the source network node 120-1 which has been reserved for the handover back of the terminal device 110.

[0077] Additionally or optionally, the source network node 120-1 may also configure a timer for a validity of the configured timer for delaying a release of resources by the source network node 120-1 and the at least one return condition for the terminal device 110 to return to be served by the source network node 120-1 and provide the validity timer to the terminal device 110. For example, the validity timer can be set to be equal to the timer for delaying a release of resources by the source network node 120-1. As another option, from the terminal device’s point of view, the configured timer for delaying a release of resources by the source network node 120-1 may also be considered as indicating how long the selective activation configuration for returning back to the source node is valid.

[0078] The source network node 120-1 may transmit (210) to the terminal device 110, a handover command along with the configured timer and the at least one return condition. Furthermore, the source network node 120-1 may also configure the terminal device 110 with selective activation between the source network node 120-1 and the target network node 120- 2 including a time constrain (e.g., the timer) for the source network node 120-1 configuration activation. The selective activation configured by the source network node 120-1 may provide the terminal device 110 with its own conditional reconfiguration to be applied by the terminal device 110 in case it needs to switch back to the serving cell group, i.e., the source network node 120-1.

[0079] Additionally or optionally, the source network node 120-1 may inform (212), for example, via an Xn interface, the target network node 120-2 that the ping-pong has been predicted and/or the timer for delaying a release of resources by the source network node 120-1. [0080] Then the source network node 120-1 may prepare (214) itself for possible return of the terminal device 110 by not releasing all allocated resources, for example related to context of the terminal device 110 and admission control.

[0081] After a handover from the source network node 120-1 to the target network node 120-2 executes, if the return condition in the selective activation configuration is fulfilled before the timer expires, the terminal device 110 may activate (216) the source network node 120-1 configuration and returns to it.

[0082] In some embodiment, if the ping-pong is predicted, the source network node 120-1 may prepare the current serving cell (e.g., cell 102) as a CHO target and configure the corresponding CHO execution condition in the terminal device 110. If the terminal device 110 needs to return after a short duration in a cell managed by the target network node 120- 2 (e.g., cell 104) back to the current serving cell (e.g., cell 102), this can be done as a CHO execution. The timer for delaying a release of resources by the source network node 120-1 may be configured as an additional condition, after which the CHO condition is automatically released.

[0083] If the return condition in the selective activation configuration is not fulfilled after the timer expires, the terminal device 110 may remove (218) the source network node 120-1 from the selective activation list. Furthermore, the source network node 120-1 may release (220) any resources reserved for the terminal device 110.

[0084] Although the ping-pong prediction may be performed by a machine learning based model deployed at the source network node 120-1, the machine learning based model for the ping-pong prediction may also be implemented at the terminal device 110.

[0085] In this situation, the configuration for measurements of the terminal device, which may be configured by the source network node 120-1, may comprise an event to trigger the terminal device to report of an observation whether at least one of the one or more candidate network nodes is likely to lead the ping-pong.

[0086] After the prediction has been performed, the terminal device 110 may report the indication that at least one of the one or more candidate network nodes indicates the occurrence of the ping-pong to the source network node 120-1. Meanwhile, additionally or optionally, the terminal device 110 may also determine the timer for delaying a release of resources by the source network node 120-1. In this case, the terminal device 110 may transmit the indication that at least one of the one or more candidate network nodes is likely to lead the ping-pong and the timer to the to the source network node 120-1, for example, along with the measurement report.

[0087] Based on the solution of the present disclosure, training data collection, training and inference may all be done in the network node or a terminal device, which makes the deployment and life-cycle management straightforward. Furthermore, the mechanism proposed by the present disclosure may avoid the cost loss due to a false prediction, for example by configuring a time for delaying a release of resources. Compared to the risking causing an RLF, the cost of the machine-learning prediction inaccuracies is low. If the ping- pong is predicted, but it doesn’t happen, the source network node may unnecessarily keep resources for the terminal device after the timer expires.

[0088] FIG. 5 shows a flowchart of an example method 500 of ping-pong handover cost reduction according to some example embodiments of the present disclosure. The method 500 may be implemented at the source network node 120-1 as shown in FIG. 1. For the purpose of discussion, the method 500 will be described with reference to FIG.l.

[0089] At 510, the source network node 120-1 obtains, from a terminal device, a report of a mobility trigger event with a measurement report associated with a serving network node and one or more neighboring network nodes.

[0090] At 520, the source network node 120-1 determines, based on the measurement report, whether a handover to at least one of the one or more neighboring network nodes, triggered by the mobility trigger event, is likely to lead to a ping-pong.

[0091] At 530, the source network node 120-1 configures, based on the determination, at least at least one return condition for the terminal device to return to be served by the source network node 120-1 and a timer for delaying resource release by the source network node 120-1, which may be considered for indicating how long the selective activation configuration for returning back to the source node is valid from the terminal device’s point of view.

[0092] At 540, the source network node 120-1 transmits to the terminal device, a handover command along with the configured timer and the at least one return condition.

[0093] In some example embodiments, the measurement report comprises measurement results of a reference signal on the number of best network nodes within a time window with a measurement granularity. [0094] In some example embodiments, the source network node 120-1 may transmit, to a terminal device, a configuration for the measurement report at least indicating at least one of the following: an event for triggering the measurement report, the time window, the measurement granularity, or the number of best network nodes to be measured and reported.

[0095] In some example embodiments, the measurement report comprises at least one of the following: the measurement results of RSRP, the measurement results of RSRQ or the measurement results of SINR.

[0096] In some example embodiments, the source network node 120-1 may configure, a timer for a validity of the configured timer and the at least one return condition; and transmit, to the terminal device, the timer for the validity of the configured timer and the at least one return condition.

[0097] In some example embodiments, the measurement report comprises an indication that the handover to the at least one of the one or more neighboring network nodes, triggered by the mobility trigger event, is likely to lead to the ping-pong and/or a timer for delaying resource release by the source network node 120-1.

[0098] In some example embodiments, the source network node 120-1 may transmit, to a terminal device, a configuration for the measurement report at least indicating an event for triggering a report of the indication.

[0099] In some example embodiments, the source network node 120-1 may transmit, to the at least one of the one or more neighboring network nodes during a preparation procedure of the handover, an indication that the terminal device is possible to return to be served by the source network node 120-1 within the timer.

[00100] In some example embodiments, in accordance with a determination that the at least one return condition is not fulfilled after the timer expires, the source network node 120-1 may release resources reserved for the terminal device.

[00101] In some example embodiments, the at least one of the one or more candidate network nodes indicates the occurrence of the ping-pong is determined by inputting the measurement report to a machine learning model associated with a ping-pong prediction, and wherein the machine learning model is trained based on a set of history measurements on at least one reference candidate network node and an observation whether the ping-pong is likely to occur under the set of history measurements. [00102] FIG. 6 shows a flowchart of an example method 600 of ping-pong handover cost reduction according to some example embodiments of the present disclosure. The method 600 may be implemented at the terminal device 110 as shown in FIG. 1. For the purpose of discussion, the method 600 with be described with reference to FIG. 1.

[00103] At 610, the terminal node 110 transmits, to a source network node, a report of a mobility trigger event with a measurement report associated with a serving network node and one or more neighboring network nodes.

[00104] At 620, the terminal node 110 receives, from the source network node, for a handover triggered by the mobility trigger event along with at least a timer for delaying resource release by the source network node and at least one return condition for the terminal device to return to be served by the source network node, wherein the handover to at least one of the one or more neighboring network nodes is likely to lead to a ping-pong.

[00105] At 630, the terminal node 110 performs the handover based on the handover command, the timer and the at least one return condition.

[00106] In some example embodiments, the measurement report comprises measurement results of a reference signal on the number of best network nodes within a time window with a measurement granularity.

[00107] In some example embodiments, the terminal node 110 may receive, from the source network node, a configuration for the measurement report at least indicating at least one of the following: an event for triggering the measurement report, the time window, the measurement granularity, or the number of best network nodes to be measured and reported; and transmit the measurement report based on the configuration.

[00108] In some example embodiments, the measurement report comprises at least one of the following: the measurement results of RSRP, the measurement results of RSRQ or the measurement results of SINR.

[00109] In some example embodiments, the terminal node 110 may receive, from the source network node, a timer for a validity of the configured timer and the at least one return condition.

[00110] In some example embodiments, the measurement report comprises an indication that the handover to the at least one of the one or more neighboring network nodes, triggered by the mobility trigger event, is likely to lead to the ping-pong and/or a timer for delaying resource release by the source network node 120-1.

[00111] In some example embodiments, the terminal node 110 may receive, from the source network node, a configuration for the measurement report at least indicating an event for triggering a report of the observation; and transmit the measurement report based on the configuration.

[00112] In some example embodiments, in accordance with a determination that the at least one return condition is fulfilled before the timer expires, the terminal node 110 may return to the source network node by activating a configuration associated with the source network node.

[00113] In some example embodiments, in accordance with a determination that the at least one return condition is not fulfilled after the timer expires, the terminal node 110 may remove the source network node from a selective activation list for the handover.

[00114] In some example embodiments, the at least one of the one or more candidate network nodes indicates the occurrence of the ping-pong is determined by inputting the measurement report to a machine learning model associated with a ping-pong prediction, and wherein the machine learning model is trained based on a set of history measurements on at least one reference candidate network node and an observation whether the ping-pong is likely to occur under the set of history measurements.

[00115] In some example embodiments, an apparatus capable of performing the method 500 (for example, implemented at the source network node 120-1) may include means for performing the respective steps of the method 500. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.

[00116] In some example embodiments, the apparatus comprises means for obtaining, from a terminal device, a report of a mobility trigger event with a measurement report associated with a serving network node and one or more neighboring network nodes; means for determining, based on the measurement report, whether a handover to at least one of the one or more neighboring network nodes, triggered by the mobility trigger event, is likely to lead to a ping-pong; means for configuring, based on the determination, at least a timer for delaying resource release by the apparatus and at least one return condition for the terminal device to return to be served by the apparatus; and means for transmitting to the terminal device, a handover command along with the configured timer and the at least one return condition. [00117] In some example embodiments, the measurement report comprises measurement results of a reference signal on the number of best network nodes within a time window with a measurement granularity.

[00118] In some example embodiments, the apparatus further comprises means for transmitting, to a terminal device, a configuration for the measurement report at least indicating at least one of the following: an event for triggering the measurement report, the time window, the measurement granularity, or the number of best network nodes to be measured and reported.

[00119] In some example embodiments, the measurement report comprises at least one of the following: the measurement results of RSRP, the measurement results of RSRQ or the measurement results of SINR.

[00120] In some example embodiments, the apparatus further comprises means for configuring, to a terminal device, a timer for a validity of the configured timer and the at least one return condition; and means for transmitting, to the terminal device, the timer for the validity of the configured timer and the at least one return condition.

[00121] In some example embodiments, the measurement report comprises an indication that the handover to the at least one of the one or more neighboring network nodes, triggered by the mobility trigger event, is likely to lead to the ping-pong and/or a timer for delaying resource release by the apparatus.

[00122] In some example embodiments, the apparatus further comprises means for transmitting, to a terminal device, a configuration for the measurement report at least indicating an event for triggering a report of the indication.

[00123] In some example embodiments, the apparatus further comprises means for transmitting, to the at least one of the one or more neighboring network nodes during a preparation procedure of the handover, an indication that the terminal device is possible to return to be served by the apparatus within the timer.

[00124] In some example embodiments, the apparatus further comprises means for, in accordance with a determination that the at least one return condition is not fulfilled after the timer expires, releasing resources reserved for the terminal device.

[00125] In some example embodiments, the at least one of the one or more candidate network nodes indicates the occurrence of the ping-pong is determined by inputting the measurement report to a machine learning model associated with a ping-pong prediction, and wherein the machine learning model is trained based on a set of history measurements on at least one reference candidate network node and an observation whether the ping-pong is likely to occur under the set of history measurements.

[00126] In some example embodiments, an apparatus capable of performing the method 600 (for example, implemented at the terminal device 110) may include means for performing the respective steps of the method 600. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.

[00127] In some example embodiments, the apparatus comprises means for transmitting, to a source network node, a report of a mobility trigger event with a measurement report associated with a serving network node and one or more neighboring network nodes; means for receiving, from the source network node, a handover command for a handover triggered by the mobility trigger event along with at least a timer for delaying resource release by the source network node and at least one return condition for the terminal device to return to be served by the source network node, wherein the handover to at least one of the one or more neighboring network nodes is likely to lead to a ping-pong; and means for performing the handover based on the handover command, the timer and the at least one return condition.

[00128] In some example embodiments, the measurement report comprises measurement results of a reference signal on the number of best network nodes within a time window with a measurement granularity.

[00129] In some example embodiments, the apparatus comprises means for receiving, from the source network node, a configuration for the measurement report at least indicating at least one of the following: an event for triggering the measurement report, the time window, the measurement granularity, or the number of best network nodes to be measured and reported; and means for transmitting the measurement report based on the configuration.

[00130] In some example embodiments, the measurement report comprises at least one of the following: the measurement results of RSRP, the measurement results of RSRQ or the measurement results of SINR.

[00131] In some example embodiments, the apparatus comprises means for receiving, from the source network node, a timer for a validity of the configured timer and the at least one return condition.

[00132] In some example embodiments, the measurement report comprises an indication that the handover to the at least one of the one or more neighboring network nodes, triggered by the mobility trigger event, is likely to lead to the ping-pong and/or a timer for delaying resource release by the source network node.

[00133] In some example embodiments, the apparatus comprises means for receiving, from the source network node, a configuration for the measurement report at least indicating an event for triggering a report of the indication; and means for transmitting the measurement report based on the configuration.

[00134] In some example embodiments, the apparatus comprises means for, in accordance with a determination that the at least one return condition is fulfilled before the timer expires, return to the source network node by activating a configuration associated with the source network node.

[00135] In some example embodiments, the apparatus comprises means for, in accordance with a determination that the at least one return condition is not fulfilled after the timer expires, remove the source network node from a selective activation list for the handover.

[00136] In some example embodiments, the at least one of the one or more candidate network nodes indicates the occurrence of the ping-pong is determined by inputting the measurement report to a machine learning model associated with a ping-pong prediction, and wherein the machine learning model is trained based on a set of history measurements on at least one reference candidate network node and an observation whether the ping-pong is likely to occur under the set of history measurements.

[00137] FIG. 7 is a simplified block diagram of a device 700 that is suitable for implementing example embodiments of the present disclosure. The device 700 may be provided to implement a communication device, for example, the terminal device 110 or the source network node 120-1 as shown in FIG. 1. As shown, the device 700 includes one or more processors 710, one or more memories 720 coupled to the processor 710, and one or more communication modules 740 coupled to the processor 710.

[00138] The communication module 740 is for bidirectional communications. The communication module 740 has one or more communication interfaces to facilitate communication with one or more other modules or devices. The communication interfaces may represent any interface that is necessary for communication with other network elements. In some example embodiments, the communication module 740 may include at least one antenna. [00139] The processor 710 may be of any type suitable to the local technical network and may include one or more of the following: general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) and processors based on multicore processor architecture, as non-limiting examples. The device 700 may have multiple processors, such as an application specific integrated circuit chip that is slaved in time to a clock which synchronizes the main processor.

[00140] The memory 720 may include one or more non-volatile memories and one or more volatile memories. Examples of the non-volatile memories include, but are not limited to, a Read Only Memory (ROM) 724, an electrically programmable read only memory (EPROM), a flash memory, a hard disk, a compact disc (CD), a digital video disk (DVD), an optical disk, a laser disk, and other magnetic storage and/or optical storage. Examples of the volatile memories include, but are not limited to, a random access memory (RAM) 722 and other volatile memories that will not last in the power-down duration.

[00141] A computer program 730 includes computer executable instructions that are executed by the associated processor 710. The instructions of the program 730 may include instructions for performing operations/acts of some example embodiments of the present disclosure. The program 730 may be stored in the memory, e.g., the ROM 724. The processor 710 may perform any suitable actions and processing by loading the program 730 into the RAM 722.

[00142] The example embodiments of the present disclosure may be implemented by means of the program 730 so that the device 700 may perform any process of the disclosure as discussed with reference to FIG. 2 to FIG. 6. The example embodiments of the present disclosure may also be implemented by hardware or by a combination of software and hardware.

[00143] In some example embodiments, the program 730 may be tangibly contained in a computer readable medium which may be included in the device 700 (such as in the memory 720) or other storage devices that are accessible by the device 700. The device 700 may load the program 730 from the computer readable medium to the RAM 722 for execution. In some example embodiments, the computer readable medium may include any types of non- transitory storage medium, such as ROM, EPROM, a flash memory, a hard disk, CD, DVD, and the like. The term “non-transitory,” as used herein, is a limitation of the medium itself (i.e., tangible, not a signal) as opposed to a limitation on data storage persistency (e.g., RAM vs. ROM).

[00144] FIG. 8 shows an example of the computer readable medium 800 which may be in form of CD, DVD or other optical storage disk. The computer readable medium 800 has the program 730 stored thereon.

[00145] Generally, various embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. While various aspects of embodiments of the present disclosure are illustrated and described as block diagrams, flowcharts, or using some other pictorial representations, it is to be understood that the block, apparatus, system, technique or method described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.

[00146] Some example embodiments of the present disclosure also provide at least one computer program product tangibly stored on a computer readable medium, such as a non- transitory computer readable medium. The computer program product includes computerexecutable instructions, such as those included in program modules, being executed in a device on a target physical or virtual processor, to carry out any of the methods as described above. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, or the like that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or split between program modules as desired in various embodiments. Machine-executable instructions for program modules may be executed within a local or distributed device. In a distributed device, program modules may be located in both local and remote storage media.

[00147] Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. The program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, cause the functions/operations specified in the flowcharts and/or block diagrams to be implemented. The program code may execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[00148] In the context of the present disclosure, the computer program code or related data may be carried by any suitable carrier to enable the device, apparatus or processor to perform various processes and operations as described above. Examples of the carrier include a signal, computer readable medium, and the like.

[00149] The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable medium may include but not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the computer readable storage medium would include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD- ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[00150] Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are contained in the above discussions, these should not be construed as limitations on the scope of the present disclosure, but rather as descriptions of features that may be specific to particular embodiments. Unless explicitly stated, certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, unless explicitly stated, various features that are described in the context of a single embodiment may also be implemented in a plurality of embodiments separately or in any suitable sub-combination.

[00151] Although the present disclosure has been described in languages specific to structural features and/or methodological acts, it is to be understood that the present disclosure defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

WHAT IS CLAIMED IS:

1. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: obtain, from a terminal device, a report of a mobility trigger event with a measurement report associated with a serving network node and one or more neighboring network nodes; determine, based on the measurement report, whether a handover to at least one of the one or more neighboring network nodes, triggered by the mobility trigger event, is likely to lead to a ping-pong; configure, based on the determination, at least a timer for delaying resource release by the apparatus and at least one return condition for the terminal device to return to be served by the apparatus; and transmit, to the terminal device, a handover command along with the configured timer and the at least one return condition.

2. The apparatus of claim 1, wherein the measurement report comprises measurement results of a reference signal on the number of best network nodes within a time window with a measurement granularity.

3. The apparatus of claim 2, wherein the apparatus is caused to: transmit, to a terminal device, a configuration for the measurement report at least indicating at least one of the following: an event for triggering the measurement report, the time window, the measurement granularity, or the number of best network nodes to be measured and reported.

4. The apparatus of claim 2, wherein the measurement report comprises at least one of the following: the measurement results of reference signal received power, the measurement results of reference signal receiving quality, or the measurement results of signal to interference plus noise ratio.

5. The apparatus of claim 1, the apparatus is caused to: configure, a timer for a validity of the configured timer and the at least one return condition; and transmit, to the terminal device, the timer for the validity of the configured timer and the at least one return condition.

6. The apparatus of claim 1, wherein the measurement report comprises at least one of: an indication that the handover to the at least one of the one or more neighboring network nodes, triggered by the mobility trigger event, is likely to lead to the ping-pong; or a timer for delaying resource release by the apparatus.

7. The apparatus of claim 6, wherein the apparatus is caused to: transmit, to the terminal device, a configuration for the measurement report at least indicating an event for triggering a report of the indication.

8. The apparatus of claim any of claims 1-7, wherein the apparatus is caused to: transmit, to the at least one of the one or more neighboring network nodes during a preparation procedure of the handover, an indication that the terminal device is possible to return to be served by the apparatus within the timer.

9. The apparatus of any of claims 1-8, wherein the apparatus is caused to: in accordance with a determination that the at least one return condition is not fulfilled after the timer expires, release resources reserved for the terminal device.

10. The apparatus of claim 1, wherein the at least one of the one or more candidate network nodes indicates the occurrence of the ping-pong is determined by inputting the measurement report to a machine learning model associated with a ping-pong prediction, and wherein the machine learning model is trained based on a set of history measurements on at least one reference candidate network node and an observation whether the ping-pong is likely to occur under the set of history measurements.

11. An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: transmit, to a source network node, a report of a mobility trigger event with a measurement report associated with a serving network node and one or more neighboring network nodes; receive, from the source network node, a handover command for a handover triggered by the mobility trigger event along with at least a timer for delaying resource release by the source network node and at least one return condition for the terminal device to return to be served by the source network node, wherein the handover to at least one of the one or more neighboring network nodes is likely to lead to a ping-pong, and perform the handover based on the handover command, the timer and the at least one return condition.

12. The apparatus of claim 11, wherein the measurement report comprises measurement results of a reference signal on the number of best network nodes within a time window with a measurement granularity.

13. The apparatus of claim 12, wherein the apparatus is caused to: receive, from the source network node, a configuration for the measurement report at least indicating at least one of the following: an event for triggering the measurement report, the time window, the measurement granularity, the number of best network nodes to be measured and reported; and transmit the measurement report based on the configuration.

14. The apparatus of claim 12, wherein the measurement report comprises at least one of the following: the measurement results of reference signal received power, the measurement results of reference signal receiving quality, or the measurement results of signal to interference plus noise ratio.

15. The apparatus of claim 11, wherein the apparatus is caused to: receive, from the source network node, a timer for a validity of the configured timer and the at least one return condition.

16. The apparatus of claim 11, wherein the measurement report comprises at least one of: an indication that the handover to the at least one of the one or more neighboring network nodes, triggered by the mobility trigger event, is likely to lead to the ping-pong; or a timer for delaying resource release by the source network node.

17. The apparatus of claim 16, wherein the apparatus is caused to: receive, from the source network node, a configuration for the measurement report at least indicating an event for triggering a report of the indication; and transmit the measurement report based on the configuration.

18. The apparatus of any of claims 11-17, wherein the apparatus is caused to: in accordance with a determination that the at least one return condition is fulfilled before the timer expires, return to the source network node by activating a configuration associated with the source network node.

19. The apparatus of any of claims 11-17, wherein the apparatus is caused to: in accordance with a determination that the at least one return condition is not fulfilled after the timer expires, remove the source network node from a selective activation list for the handover.

20. The apparatus of claim 11, wherein the at least one of the one or more candidate network nodes indicates the occurrence of the ping-pong is determined by inputting the measurement report to a machine learning model associated with a ping-pong prediction, and wherein the machine learning model is trained based on a set of history measurements on at least one reference candidate network node and an observation whether the ping-pong is likely to occur under the set of history measurements.

21. A method comprising: obtaining, by a source network node and from a terminal device, a report of a mobility trigger event with a measurement report associated with a serving network node and one or more neighboring network nodes; determining, based on the measurement report, whether a handover to at least one of the one or more neighboring network nodes, triggered by the mobility trigger event, is likely to lead to a ping-pong; configuring, based on the determination, at least a timer for delaying resource release by the source network node and at least one return condition for the terminal device to return to be served by the source network node; and transmitting, to the terminal device, a handover command along with the configured timer and the at least one return condition.

22. A method comprising: transmitting, from a terminal device and to a source network node, a report of a mobility trigger event with a measurement report associated with a serving network node and one or more neighboring network nodes; receiving, from the source network node, a handover command for a handover triggered by the mobility trigger event along with at least a timer for delaying resource release by the source network node and at least one return condition for the terminal device to return to be served by the source network node, wherein the handover to at least one of the one or more neighboring network nodes is likely to lead to a ping-pong; and performing the handover based on the handover command, the timer and the at least one return condition.

23. An apparatus comprising: means for obtaining, from a terminal device, a report of a mobility trigger event with a measurement report associated with a serving network node and one or more neighboring network nodes; means for determining, based on the measurement report, whether a handover to at least one of the one or more neighboring network nodes, triggered by the mobility trigger event, is likely to lead to a ping-pong; means for configuring, based on the determination, at least a timer for delaying resource release by the apparatus and at least one return condition for the terminal device to return to be served by the apparatus; and means for transmitting to the terminal device, a handover command along with the configured timer and the at least one return condition.

24. An apparatus comprising: means for transmitting, to a source network node, a report of a mobility trigger event with a measurement report associated with a serving network node and one or more neighboring network nodes; means for receiving, from the source network node, a handover command, for a handover triggered by the mobility trigger event, along with at least a timer for delaying resource release by the source network node and at least one return condition for the terminal device to return to be served by the source network node, wherein the handover to at least one of the one or more neighboring network nodes is likely to lead to a ping-pong; and means for performing the handover based on the handover command.

25. A computer readable medium comprising instructions which, when executed by an apparatus, cause the apparatus to perform at least the method of claim 21 or the method of claim 22.