Early handover preparation and cancelation based on measurement event prediction

Abstract

A method performed by a user equipment (UE) includes determining a triggering condition for a measurement event prediction is fulfilled, and performing an inference operation in which measurements performed by the UE are applied to a machine learning (ML) model to determine the measurement event prediction indicating the measurement event is predicted to occur. The method includes reporting first information indicating that the measurement event is predicted to occur, and performing an evaluation of the measurement event prediction for a time duration for verification of the measurement event prediction. And the method includes reporting second information triggered by expiration of the time duration for the verification of the measurement event prediction, the second information indicating an accuracy of the measurement event prediction based on the evaluation, and whether the measurement event has occurred or not occurred.

Description

EARLY HANDOVER PREPARATION AND CANCELATION BASED ON MEASUREMENT EVENT PREDICTIONTECHNOLOGICAL FIELD

[0001] The present disclosure relates generally to telecommunications and, in particular, to early handover preparation in a telecommunications system.BACKGROUND

[0002] Telecommunications systems can be seen as facilities that enable communications between two or more entities such as between two user equipment, between a user equipment and a base station, between two base stations, a user equipment and a network function of a communication network and / or a base station and other nodes. A telecommunications system can include a communication network and one or more user equipment. The communication sessions may comprise, for example, communication of data for carrying communications such as voice, video, electronic mail (email), text message, multimedia and / or content data and so on. Non-limiting examples of services provided comprise two-way or multi-way calls, data communication or multimedia services and access to a data network system, such as the Internet.

[0003] In a telecommunications system that includes a wireless communication network, at least a part of a communication session between at least two stations occurs over a wireless link. Examples of wireless communication networks comprise public land mobile networks (PLMN), satellite-based communication networks and different wireless local networks, for example wireless local area networks (WLAN). Some wireless communication networks can be divided into cells, and are therefore often referred to as cellular networks.

[0004] A user can access the telecommunications system by means of an appropriate communication device or terminal. A communication device of a user may be referred to as user equipment (UE) or user device. A communication device is provided with an appropriate signal receiving and transmitting apparatus for enabling communications, for example enabling access to a communication network or communications directly with other users. The communication device may access a carrier provided by, for example, a base station of a cell, and transmit and / or receive communications on the carrier.

[0005] Telecommunications systems have evolved through multiple generations, each bringing advancements in speed, capacity, and functionality. The Evolved Packet System (EPS) represents the 4G architecture, which includes Long-Term Evolution (LTE) and LTE-Advanced (LTE-A) as its radio accesstechnologies. The 5G System (5GS) builds upon EPS, introducing 5G New Radio (5G NR) for enhanced mobile broadband, massive machine-type communications, and ultra-reliable low-latency communications. The future 6G System (6GS) is expected to further revolutionize telecommunications with even more advanced capabilities. These systems are interconnected, with 5GS designed to interwork with EPS for seamless service continuity. The 3rd Generation Partnership Project (3GPP) plays a crucial role in developing and maintaining standards for these telecommunications systems, ensuring global interoperability and evolution from Universal Mobile Telecommunications System (UMTS) (3G) through to the ongoing development of 6G technologies.BRIEF SUMMARY

[0006] Example implementations of the present disclosure are directed to telecommunications and, in particular, to early handover preparation in a telecommunications system. The present disclosure includes, without limitation, the following example implementations.

[0007] Some example implementations provide an apparatus to implement a user equipment (UE), the apparatus comprising: at least one memory configured to store instructions; and at least one processing circuitry configured to access the at least one memory, and execute the instructions to cause the apparatus to at least: determine a triggering condition for a measurement event prediction is fulfilled; perform an inference operation in which measurements performed by the UE are applied to a machine learning (ML) model to determine the measurement event prediction indicating the measurement event is predicted to occur; report to a network first information indicating that the measurement event is predicted to occur; perform an evaluation of the measurement event prediction for a time duration for verification of the measurement event prediction; and report to the network second information triggered by expiration of the time duration for the verification of the measurement event prediction, the second information indicating an accuracy of the measurement event prediction based on the evaluation, and whether the measurement event has occurred or not occurred.

[0008] Some example implementations provide a method performed by a user equipment (UE), the method comprising: determining a triggering condition for a measurement event prediction is fulfilled; performing an inference operation in which measurements performed by the UE are applied to a machine learning (ML) model to determine the measurement event prediction indicating the measurement event is predicted to occur; reporting to a network first information indicating that the measurement event is predicted to occur; performing an evaluation of the measurement event prediction for a time duration for verification ofthe measurement event prediction; and reporting to the network second information triggered by expiration of the time duration for the verification of the measurement event prediction, the second information indicating an accuracy of the measurement event prediction based on the evaluation, and whether the measurement event has occurred or not occurred.

[0009] Some example implementations provide an apparatus to implement a radio access network (RAN) node, the apparatus comprising: at least one memory configured to store instructions; and at least one processing circuitry configured to access the at least one memory, and execute the instructions to cause the apparatus to at least: configure a user equipment (UE) with an event-triggered measurement reporting configuration according to which the UE is to perform an inference operation in which measurements performed by the UE are applied to a machine learning (ML) model to determine a measurement event prediction for a measurement event; receive from the UE first information including information for the measurement event prediction indicating that the measurement event is predicted to occur; initiate early handover preparation with one or more candidate RAN nodes based the first information; receive from the UE second information indicating an accuracy of the measurement event prediction based on an evaluation of the measurement event prediction for a time duration for verification of the measurement event prediction, the second information also indicating whether the measurement event has occurred or not occurred; and make a determination whether to continue or terminate the early handover preparation based on the second information.

[0010] Some example implementations provide a method performed by a radio access network (RAN) node, the method comprising: configuring a user equipment (UE) with an event-triggered measurement reporting configuration according to which the UE is to perform an inference operation in which measurements performed by the UE are applied to a machine learning (ML) model to determine a measurement event prediction for a measurement event; receiving from the UE first information including information for the measurement event prediction indicating that the measurement event is predicted to occur; initiating early handover preparation with one or more candidate RAN nodes based the first information; receiving from the UE second information indicating an accuracy of the measurement event prediction based on an evaluation of the measurement event prediction for a time duration for verification of the measurement event prediction, the second information also indicating whether the measurement event has occurred or not occurred; and making a determination whether to continue or terminate the early handover preparation based on the second information.

[0011] Some example implementations provide an apparatus to implement a user equipment (UE), the apparatus comprising: at least one memory configured to store instructions; and at least one processing circuitry configured to access the at least one memory, and execute the instructions to cause the apparatus to at least: determine a triggering condition for a measurement event prediction is fulfilled; perform an inference operation in which measurements performed by the UE are applied to a machine learning (ML) model to determine measurement predictions from which the measurement event prediction is made, and the measurement event prediction indicates that the measurement event is predicted to occur; report to a network first information indicating that the measurement event is predicted to occur; perform an evaluation of the measurement event prediction for a time duration for verification of the measurement event prediction; and report to the network second information triggered by expiration of the time duration for the verification of the measurement event prediction, the second information indicating an accuracy of the measurement event prediction based on the evaluation, and whether the measurement event has occurred or not occurred.

[0012] Some example implementations provide a method performed by a user equipment (UE), the method comprising: determining a triggering condition for a measurement event prediction is fulfilled; performing an inference operation in which measurements performed by the UE are applied to a machine learning (ML) model to determine measurement predictions from which the measurement event prediction is made, and the measurement event prediction indicates that the measurement event is predicted to occur; reporting to a network first information indicating that the measurement event is predicted to occur; performing an evaluation of the measurement event prediction for a time duration for verification of the measurement event prediction; and reporting to the network second information triggered by expiration of the time duration for the verification of the measurement event prediction, the second information indicating an accuracy of the measurement event prediction based on the evaluation, and whether the measurement event has occurred or not occurred.

[0013] Some example implementations provide an apparatus to implement a radio access network (RAN) node, the apparatus comprising: at least one memory configured to store instructions; and at least one processing circuitry configured to access the at least one memory, and execute the instructions to cause the apparatus to at least: configure a user equipment (UE) with an event-triggered measurement reporting configuration according to which the UE is to perform an inference operation in which measurements performed by the UE are applied to a machine learning (ML) model to determine measurement predictions from which the measurement event prediction is made; receive from the UE first information including information for the measurement event prediction indicating that the measurement event is predicted to occur;initiate early handover preparation with one or more candidate RAN nodes based the first information; receive from the UE second information indicating an accuracy of the measurement event prediction based on an evaluation of the measurement event prediction for a time duration for verification of the measurement event prediction, the second information also indicating whether the measurement event has occurred or not occurred; and make a determination whether to continue or terminate the early handover preparation based on the second information.

[0014] Some example implementations provide a method performed by a radio access network (RAN) node, the method comprising: configuring a user equipment (UE) with an event-triggered measurement reporting configuration according to which the UE is to perform an inference operation in which measurements performed by the UE are applied to a machine learning (ML) model to determine measurement predictions from which the measurement event prediction is made; receiving from the UE first information including information for the measurement event prediction indicating that the measurement event is predicted to occur; initiating early handover preparation with one or more candidate RAN nodes based the first information; receiving from the UE second information indicating an accuracy of the measurement event prediction based on an evaluation of the measurement event prediction fora time duration for verification of the measurement event prediction, the second information also indicating whether the measurement event has occurred or not occurred; and making a determination whether to continue or terminate the early handover preparation based on the second information.

[0015] These and other features, aspects, and advantages of the present disclosure will be apparent from a reading of the following detailed description together with the accompanying figures, which are briefly described below. The present disclosure includes any combination of two, three, four or more features or elements set forth in this disclosure, regardless of whether such features or elements are expressly combined or otherwise recited in a specific example implementation described herein. The present disclosure is intended to be read holistically such that any separable features or elements of the disclosure, in any of its aspects and example implementations, should be viewed as combinable unless the context of the disclosure clearly dictates otherwise.

[0016] It will therefore be appreciated that this Brief Summary is provided merely for purposes of summarizing some example implementations so as to provide a basic understanding of some aspects of the disclosure. Accordingly, it will be appreciated that the above described example implementations are merely examples and should not be construed to narrow the scope or spirit of the disclosure in any way. Other example implementations, aspects and advantages will become apparent from the following detaileddescription taken in conjunction with the accompanying figures which illustrate, by way of example, the principles of some described example implementations.BRIEF DESCRIPTION OF THE FIGURE(S)

[0017] Having thus described example implementations of the disclosure in general terms, reference will now be made to the accompanying figures, which are not necessarily drawn to scale, and wherein:

[0018] FIG. 1 illustrates a telecommunications system that includes one or more public land mobile networks (PLMNs) coupled to one or more external data networks, according to some example implementations of the present disclosure;

[0019] FIG. 2 illustrates a PLMN, according to some example implementations;

[0020] FIG. 3 is a diagram of a procedure for (inter-node) handover;

[0021] FIG. 4 is a diagram of a procedure for L1 / L2-triggered mobility, also known as lower-layer triggered mobility (LTM);

[0022] FIG. 5 is a diagram of a framework for A3 measurement event triggered reporting for handover preparation;

[0023] FIGS. 6A and 6B are diagrams of a framework for measurement event prediction triggered reporting for early handover preparation, according to some example implementations;

[0024] FIGS. 7A, 7B and 7C are diagrams of verification of a measurement event prediction according to an indirect approach in which the measurement event prediction is made from measurement predictions, according to some example implementations;

[0025] FIG. 8 is a diagram of a procedure for handover including measurement event prediction triggered reporting for early handover preparation, according to some example implementations;

[0026] FIG. 9 is a diagram of a procedure for LTM including measurement event prediction triggered reporting for early handover preparation, according to some example implementations;

[0027] FIG. 10 is a flowchart illustrating various steps in a method performed by a user equipment (UE), according to various example implementations;

[0028] FIG. 11 is a flowchart illustrating various steps in a method performed by a radio access network (RAN) node, according to various example implementations;

[0029] FIG. 12 is a flowchart illustrating various steps in a method performed by a UE, according to various example implementations;

[0030] FIG. 13 is a flowchart illustrating various steps in a method performed by a RAN node, according to various example implementations; and

[0031] FIG. 14 illustrates an apparatus according to some example implementations.DETAILED DESCRIPTION

[0032] Some implementations of the present disclosure will now be described more fully hereinafter with reference to the accompanying figures, in which some, but not all implementations of the disclosure are shown. Indeed, various implementations of the disclosure may be embodied in many different forms and should not be construed as limited to the implementations set forth herein; rather, these example implementations are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. Like reference numerals refer to like elements throughout. Unless specified otherwise or clear from context, references to first, second or the like should not be construed to imply a particular order but are merely utilized to distinguish one item or operation from another.

[0033] As used herein, unless specified otherwise or clear from context, the “or” of a set of operands is the “inclusive or” and thereby true if and only if one or more of the operands is true, as opposed to the “exclusive or” which is false when all of the operands are true. Thus, for example, “[A] or [B]” is true if [A] is true, or if [B] is true, or if both [A] and [B] are true. Further, the articles “a” and “an” mean “one or more,” unless specified otherwise or clear from context to be directed to a singular form. Furthermore, it should be understood that unless otherwise specified, the terms “data,” “content,” “digital content,” “information,” and similar terms may be at times used interchangeably. The term “network” may refer to a group of interconnected computers including clients and servers; and within a network, these computers may be interconnected directly or indirectly by various means including via one or more switches, routers, gateways, access points or the like.

[0034] The present disclosure discusses telecommunication systems and mobile or cellular networks and user equipment thereof, and while specific terms may be used, are broadly applicable across various technologies. For instance, while the present disclosure may reference radio access technologies such as 5G NR and 5G Advanced, the present disclosure is equally relevant to next generation radio access technologies, such as 6G. Example implementations of the present disclosure described herein also mention public land mobile networks (PLMNs) and mobile network operators (MNOs), but example implementations are similarly applicable to standalone non-public networks (SNPNs).

[0035] Although some examples and figures focus on radio access networks (RANs) and in particular radio access networks that operate in accordance with the 3GPP standard for 5G NR (generally referred to as 3GPP access or 3GPP access networks), example implementations are applicable to any type of access networks. The applicability to any type of access network includes not only 3GPP access networks but also non-3GPP access networks, such as wireline access, untrusted non-3GPP access network, and trusted non-3GPP access network using wireless access gateway function (W-AGF), non-3GPP interworking function (N3IWF), ortrusted non-3GPP gateway function (TNGF) to connect to a core network (e.g., a 5G core network (5GC) or a 6G core network (6GC)) of a mobile or cellular network.

[0036] Further, 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); (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); or (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.

[0037] The above 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 device, or other computing or network device.

[0038] FIG. 1 illustrates a telecommunications system 100 according to various example implementations of the present disclosure. Examples of suitable telecommunications systems include UMTS, EPS and 5GS, as well as the future 6GS. The telecommunications system (otherwise referred to as a system) generally includes one or more mobile or cellular networks, and these mobile or cellular networks may interwork between telecommunications systems. As shown, for example, the system includes one or more PLMNs 102 coupled to one or more other external data networks 104 - notably including a wide area network (WAN) such as the Internet. As will be appreciated, a PLMN may be a standalone PLMN that includes a 5GC,or may be a non-standalone PLMN that includes both an Evolved Packet Core (EPC) and a 5GC connected to a RAN.

[0039] Each ofthe PLMNs 102 includes a core network (CN) 106, such as the EPC, the 5GC, ora 6GC; and each CN is coupled to one or more RANs 108 that implement one or more radio access technologies (RATs). Examples of these RANs include the evolved UMTS terrestrial radio access network (E-UTRAN) of 4G LTE, the next generation (NG) radio access network (NG-RAN) of 5G NR, and the 6G RAN. As used herein, a “network device” refers to any suitable device of a RAN or a core network of a telecommunications system. Examples of suitable network devices are described in greater detail below.

[0040] Examples of RATs include 3GPP radio access technologies such as GSM, CDMA2000 1xEV-DO (HRPD), CDMA2000 1x (1xRTT), UTRA, E-UTRA, 5G NR, 5G Advanced, and 6G. Other examples of RATs include IEEE 802 technologies such as IEEE 802.11 (Wi-Fi), IEEE 802.15 (including 802.15.1 (WPAN / Bluetooth), 802.15.4 (Zigbee) and 802.15.6 (WBAN)), Bluetooth, Bluetooth Low Energy (BLE), ultra wideband (UWB), and the like. Generally, a RAT may refer to any 2G, 3G, 4G, 5G, 6G or higher generation RAT and their different versions, as well as to any other RAT that may be arranged to interwork with such a RAT to provide access to the CN 106 of a MNO.

[0041] The telecommunications system 100 also includes one or more communication devices that may be varyingly known as user equipment (UE) 110, terminal device, terminal equipment, mobile station or the like. The UE is generally a device configured to communicate with a network device (e.g., an access node such as a RAN node of RAN 108) or a or a further UE in the telecommunications system. The UE may be a portable computer (e.g., laptop, notebook, tablet computer), mobile phone (e.g., cell phone, smartphone), wearable computer (e.g., smartwatch), or the like. In other examples, the UE may be an Internet of things (loT) device, an industrial loT (lloT device), a vehicle equipped with a vehicle-to-everything (V2X) communication technology, or the like. In some examples, as referenced by 3GPP, the UE may be a narrowband loT (NB-loT) device, an enhanced machine-type communication (eMTC) device, a reduced capability (RedCap) device, an ambient loT device, or the like.

[0042] In operation, these UEs 110 may connect to one or more RAN nodes of the RANs 108 according to their particular RATs to thereby access a particular CN 106 of a PLMN 102, or to access one or more of the external data networks 104 (e.g., the Internet) or services provided by the PLMN. The external data network may provide Internet access, or 3rd party services. For example, the International Telecommunication Union (ITU) has classified 5G mobile network services (e.g., services provided by a 5G mobile network) into three categories: enhanced mobile broadband (eMBB), ultra-reliable and low-latencycommunications (URLLC), and massive machine type communications (mMTC) or massive internet of things (MIoT).

[0043] In various examples, a RAN 108 may be configured to provide one or more macrocells, microcells, picocells, femtocells or the like. The RAN may generally include one or more RAN nodes that interact with UEs 110. In various examples, a RAN node may be referred to as a base station (BS), access point (AP), base transceiver station (BTS). Examples of RAN nodes include a Node B (NB), evolved NB (eNB), macro BS, NB (MNB) or eNB (MeNB), home BS, NB (HNB) or eNB (HeNB), next generation NB (gNB), enhanced gNB (en-gNB), next generation eNB (ng-eNB), 6G NB (6gNB), or the like. The term ‘gNB’ in 5G NR may correspond to the eNB in 4G LTE. Also, a NG-RAN node may refer to a gNB or a ng-eNB. And unless otherwise specified, a gNB in 5G NR or a 6gNB in 6G may at times be more generally referred to as a (6)gNB or more simply a gNB.

[0044] The RAN 108 may include some type of network controlling / governing entity responsible for control of the RAN nodes. The network controlling / governing entity and RAN node may be separate or integrated into a single apparatus. The network controlling / governing entity may include processing circuity configured to carry out various management functions for controlling RAN nodes of the RAN. The processing circuity may be associated with a memory, computer-readable storage medium or a data storage device comprising a database for maintaining information required in the various management functions.

[0045] FIG. 2 illustrates an example of a PLMN 102, such as 4G LTE, 5G NR or 6G PLMN that communicates with a UE 110 and an external data network 104 of the telecommunications system 100. As shown, the RAN 108 (e.g., E-UTRAN, NG-RAN, 6G RAN) includes one or more RAN nodes 202 configured to connect one or more UEs to the RAN to thereby access the CN 106 (e.g., EPC, 5GC, 6GC). In 4G LTE, the UE, E-UTRAN and EPC compose EPS. Similarly, in 5G NR, the UE, NG-RAN and 5GC compose the 5GS. And in 6G, the UE, 6G RAN and 6GC compose the 6GS.

[0046] In some implementations, operations of a gNB or other RAN node may be distributed or functionally split into components including one or more remote radio head (RRHs) or radio units (RUs), and a baseband unit (BBU); and in some implementations, the BBU may be split into a central / centralized unit (CU) (central node) and one or more distributed units (DUs) (distributed node). The CU may be, for example, a server, host or node. In some implementations, the RRH / RU and DU may be collocated ata network device. It is also possible that operations of a gNB or RAN node may be distributed among a plurality of servers, hosts or nodes.

[0047] It should also be understood that the distribution of work between core network operations and RAN node operations may vary depending on implementation. A 5G or 6G network architecture, for example, may be based on a so-called CU-DU split. One gNB-CU (a CU 204) may control one or more gNB-DUs (DUs 206). The gNB-CU may control a plurality of spatially separated gNB-DUs, acting at least as transmit / receive (Tx / Rx) nodes. In some example implementations, however, the gNB-DUs may include, for example, a radio link control (RLC), medium access control (MAC) layer and a physical (PHY) layer, whereas the gNB-CU may include the layers above the RLC layer, such as a packet data convergence protocol (PDCP) layer, a radio resource control (RRC), and an internet protocol (IP) layer. Other functional splits are also possible. It is considered that skilled person is familiar with the open systems interconnection (OSI) model and the functionalities within each layer.

[0048] In some example implementations, the server or CU 204 may generate a virtual network through which the server communicates with the radio node. In general, virtual networking may involve a process of combining hardware and software network resources and network functionality into a single, software-based administrative entity, a virtual network. Such virtual network may provide flexible distribution of operations between the server and the radio head / node. In practice, any digital signal processing task may be performed in either the CU or the DU 206, and the boundary where the responsibility is shifted between the CU and the DU may be selected according to implementation.

[0049] For a UE 110 in an RRC connected state, it is generally desirable to keep the UE’s traffic uninterrupted when the UE moves within a cell (at times referred to as a radio cell) or across different radio cells of one or more RAN nodes 202. To continuously monitor the UE’s radio link condition toward a serving radio cell provided by a serving RAN node, the UE may be configured to measure received signal level and quality from the serving radio cell as well as a list of configured neighboring radio cells, and report the results to the RAN node periodically and / or whenever a configured measurement event is met / fulfilled. These measurements may then be evaluated at the RAN node, and may result in a handover (HO) of the UE from the serving radio cell provided by the serving RAN node (a source RAN node, or more generally a source node) to a new radio cell provided by a target RAN node (a target RAN node, or more generally a target node). The mobility of a UE may also be provided by a so-called conditional handover (CHO) procedure, a lower-layer triggered mobility (LTM) procedure, or the like.

[0050] FIG. 3 is a diagram of a conventional (inter-node) handover procedure involving a UE 110, a source RAN node 202A (source node) that is currently serving (connected to) the UE, and one or more candidate RAN nodes that are potential target RAN nodes 202B for handover of the UE. As shown, the UEat step 301 may be configured, such as by an RRC reconfiguration message, to report measurements of one or more neighboring radio cells, such as on an event basis. Once the event condition holds, the UE may at step 302 send (transmit) a measurement report indicating relevant measurements for one or more radio cells provided by the candidate RAN node(s). Depending on various configurations and requirements, the measurement may be performed on any of a number of suitable objects. Based on measurements performed and reported by the UE and other UEs served by the source RAN node, the source RAN node may be configured to derive information, such as a number of actively connected UEs, number of RRC connections, number of physical resource blocks (PRBs) in use, the transport network load (TNL) capacity, or the like.

[0051] The source RAN node 202A may at step 303 decide to initiate the handover procedure, and initiate a handover preparation in which the source RAN node at step 304 sends (transmits) a handover request message with a current configuration of the UE 110 towards the candidate (target) RAN node 206B controlling a target radio cell. In some cases, the handover request message may be sent over an Xn interface between the source RAN node and the candidate RAN node, such as according to a procedure referred to as Xn handover. In some possible cases where there is no Xn interface between these two nodes, the candidate RAN node may be accessed over AMF, such as according to a procedure referred to as NGAP handover.

[0052] The candidate (target) RAN node 202B may perform admission control, such as to accept or reject the handover request, and at step 305 provide a handover request acknowledgement (ACK) message comprising a configuration of initial access resources for the UE 110 in case of acceptance. This configuration may comprise, for example, a cell radio network temporary identifier (C-RNTI), a contention-free random access (CFRA) preamble, a data radio bearer (DRB) configuration, quality of service (QoS) flow to DRB mapping, UE capability related features enabled by the candidate RAN node, or the like. The source RAN node 202A may then at step 306 send (transmit) a handover command message that comprises the configuration for the target radio cell of the target RAN node towards the UE.

[0053] Upon receipt of the handover command from the source node 206A, the UE 110 may at steps 307, 308 and 309 obtain downlink (DL) and uplink (UL) synchronization with the target RAN node 202B, and thereafter complete the handover procedure. As shown, in some examples, the handover command may be provided at step 306 by a RRC reconfiguration message; and in some of these examples, the handover procedure may comprise a random access procedure for handover, comprising DL and UL synchronization and random access channel (RACH) access to the target RAN node, and random access response (RAR)message from the target RAN node. The UE may then send (transmit) a RRC reconfiguration complete message to the target RAN node to complete the handover procedure.

[0054] Mainstream mobility has typically been conducted using higher layer (L3 or RRC controlled) mobility. LTM moves the execution of the ‘handover1from one cell to another from higher layers (L3), such as RRC, to lower layers. These lower layers may be either PHY (layer 1 or L1) or MAC (layer 2 or L2). LTM may reduce latency, overhead and interruption time when compared to L3 handover based mobility. In a CU-DU split architecture, LTM may support one or more of intra-DU mobility, intra-CU inter-DU mobility, or inter-CU inter-DU mobility.

[0055] FIG. 4 illustrates a diagram of a procedure for LTM procedure of a UE 110 in a RRC connected state with a RAN node 202, which has been proposed. During LTM preparation, as shown at step 401, the UE sends a L3 measurement report to the RAN node, which decides to use LTM and initiate LTM candidate preparation. The RAN node at step 402 sends a RRC reconfiguration message to the UE, including candidate configurations of one or more candidate cells (at times referred to as LTM candidate cells). In the context of LTM, a candidate cell is a cell configured by the RAN node for potential a cell switch, and that may be later selected by the RAN node (among one or more candidate cells) for the cell switch. The RRC reconfiguration message may also include a configuration of L1 measurement reporting for LTM execution. The UE stores the candidate configurations, and the UE at step 403 sends a RRC reconfiguration complete message to the RAN node.

[0056] An optional early synchronization of the UE 110 with the candidate cell(s) follows LTM preparation. As shown at steps 404A and 404B, the UE 110 performs DL and may perform UL synchronization with the candidate cell(s). For DL synchronization, the RAN node 202 may perform an early activation of configured transmission configuration indicator (TCI) states for the candidate cell(s), such as via a MAC control element (MAC CE) or other control message. During early UL synchronization, a timing advance (TA) of respective one or more of the candidate cell(s) may be acquired, such as via contention free random access (CFRA).

[0057] During LTM execution, the UE 110 may be configured to perform L1 or L3 measurements on the configured candidate cell(s), and the UE at step 405 sends L1 / L3 measurement reports to the RAN node 202. The RAN node decides to execute a cell switch (more generally a handover), and selects one of the candidate cell(s) as a target cell for the cell switch. L1 / L3 measurement reports may also be used by the RAN node to select candidate cells and corresponding TCI states for early DL synchronization or / and to select candidate cells and CFRA configuration, like SSB identifier (ID) to trigger RACH procedure by a PDCCH order.

[0058] The RAN node 202 at step 406 transmits a cell switch command, such as a MAC CE, to trigger cell switch. The cell switch command may indicate a target configuration identifier (ID) which indicates the index of the candidate configuration of the target cell. The cell switch command may also indicate a beam indicated with a TCI state, or beams indicated with DL and UL TCI states, and TA value for the target cell, if available. The UE switches to the candidate configuration of the target cell; and if the TA of the target cell (from step 404) is no longer available (or otherwise not acquired), the UE at step 407 initiates a RACH procedure with the target cell to acquire the TA of the target cell. In some cases, the cell switch command may include CFRA RACH related parameters for the UE to perform the RACH procedure. The UE then at step 408 indicates successful completion of the cell switch.

[0059] In many conventional handover (HO), CHO, LTM and other mobility scenarios, the decision whether or not to handover a UE 110 is taken by the serving RAN node 202 based on measurement reports from the UE. There are multiple measurement items (RSRP, RSRQ, SINR) and multiple ways (periodic, event triggered) to measure the signal quality of the serving cell and neighbor cells. Examples of measurement items include reference signal received power (RSRP), reference signal received quality (RSRQ), and signal-to-interference-plus-noise ratio (SINR).

[0060] In an ideal case, the serving RAN node 202 may allow the UE 110 to report serving cell and neighbor cell signal quality and trigger the handoverwith a single measurement, but in practice this can create overload conditions due to unnecessary ping pong handovers. As solution to avoid such situation, 3GPP specifications have proposed a set of predefined measurement report mechanisms to be performed by UE. The report type of these predefined measurement reports type is called an “event” (also at times referred to as a measurement event, and the type of event that a UE reports is specified by RRC signaling message sent by the serving RAN node.

[0061] In 3GPP, the following events are currently defined for 5G NR.Event A1: (serving becomes better than threshold)Event A2: (serving becomes worse than threshold)Event A3: (neighbor becomes offset better than SpCell)Event A4: (neighbor becomes better than threshold)Event A5: (SpCell becomes worse than as first threshold and neighbor becomes better than a second threshold)Event A6: (neighbor becomes offset better than SCell)Event B1 : (Inter-RAT neighbor becomes better than threshold)Event B2: (PCell becomes worse than a first threshold and inter-RAT neighbor becomes better than second threshold)

[0062] A handover procedure may be initiated if the defined conditions about the received signal quality are satisfied according to an event. In the case of an A3 event, for example, a handover may begin within the A3 event if the quality of received signal from a neighbor RAN node 202 is better than that of serving RAN node plus a pre-defined threshold. The A3 event (and other similar events) may also have an associated time-to-trigger (TTT) interval, which is considered as the time to be sure about start of handover procedure. That is, the UE waits for the TTT before sending any report or handover request to the RAN node. In practice, the TTT is often defined by the MNO to prevent the ping-pong handovers.

[0063] An event may also be specified with entering and leaving conditions. In this regard, the UE may consider the entering condition for the A3 event to be satisfied when condition A3-1 is fulfilled, and consider the leaving condition for the A3 event to be satisfied when condition A3-2 is fulfilled. The A3-1 (entering condition) and A3-2 (leaving condition) may be expressed as inequalities as follows:Inequality A3-1 (Entering condition)Mn + Ofn + Ocn - Hys > Mp + Ofp + Ocp + OffInequality A3-2 (Leaving condition)Mn + Ofn + Ocn - Hys < Mp + Ofp + Ocp + OffIn the respective conditions, Mn is the measurement result of the neighbor cell, not taking into account any offsets. Ofn is the measurement object specific offset of the reference signal of the neighbor cell. Ocn is the cell specific offset of the neighbor cell, and set to zero if not configured for the neighbor cell. Mp is the measurement result of the SpCell, not taking into account any offsets. Ofp is the measurement object specific offset of the SpCell. Ocp is the cell specific offset of the SpCell, and is set to zero if not configured for the SpCell. Hys is the hysteresis parameter for the event. Off is the offset parameter for the event.

[0064] For Release 19, 3GPP has studied a number of artificial intelligence (Al) / machine learning (ML) enhancements, including the use of AI / ML for mobility in 5G NR. One of the objectives of the study is to evaluate AI / ML-based radio resource management (RRM) measurement and measurement event prediction, including measurement event predictions (UE-sided model). Another of the objectives of the study is to study the need or benefits of any other UE assistance information for network -sided models.

[0065] FIG. 5 is a diagram of a framework for measurement A3 event triggered reporting for handover preparation. The handover preparation is initiated between a source RAN node 202 and a target RAN node based on the A3 event triggered measurement reporting mechanism. The framework is relatively static, asthe source RAN node must wait until the measurement report is sent and received after the TTT has expired. Example implementations of the present disclosure therefore provide solution(s) that enable the use of AI / ML to assist the UE 110 in predicting the measurement event, which may in turn enable the RAN node to initiate early handover preparation. The solution(s) provided by some example implementations address when to start a measurement event prediction-based early handover preparation at a source RAN node based on event prediction results received from the UE. Additionally or alternatively, the solution(s) may address how a measurement event may affect the measurement event prediction based on early handover preparation. Even further, the solution(s) may address control signaling, such as dedicated RRC information element (IE) and lower-layer control signaling, for the UE to enable the measurement event prediction and reporting.

[0066] According to some example implementations, as described in greater detail below, a RAN node 202 of a RAN 108 may configure a UE 110 with an event-triggered measurement reporting configuration. Based on the event-triggered measurement reporting configuration, the UE may determine a triggering condition for a measurement event prediction is fulfilled. The UE may perform an inference operation using a ML model (also referred to as an AI / ML model) to make a measurement event prediction for a measurement event based on measurements performed by the UE, such as according to a direct (1-step) approach or an indirect (2-step) approach. These measurements may include, for example, radio resource management (RRM) measurements.

[0067] In the direct approach, measurements performed by the UE 110 may be applied to the ML model to determine the measurement event prediction. In some examples of the direct approach, a binary classification ML model (or other suitable ML model) may be trained to predict whether (or not) a measurement event will occur within a configured prediction window. In the direct approach, the ML model may map measurements performed by the UE to the measurement event prediction.

[0068] In the indirect approach, measurements performed by the UE 110 may be applied to the ML model to determine measurement predictions (e.g., RRM measurement predictions), and the measurement event prediction may then be made from the measurement predictions. In some examples of the indirect approach, a regression ML model (or other suitable ML model) may be trained to predict (future) measurements, and a measurement event may be predicted in a separate step based on the predicted measurements by applying the measurement event condition or an approximation of it to the predicted measurements. In the indirect approach, measurements performed by the UE may be mapped to measurement predictions from which a measurement event prediction may be made. In either the direct or indirect approach, the focus is on UE-side measurement event prediction.

[0069] Regardless of the particular approach according to which the measurement event prediction is made, the UE 110 may report to the RAN 108 (RAN node 202) first information indicating whether the measurement event is predicted to occur, such as by an acknowledgement (ACK) or negative acknowledgement (NACK). In some examples, the first information may indicate a prediction window for the inference operation. And in some examples involving the indirect approach for the measurement event prediction, the first information may also include the measurement predictions.

[0070] The RAN node 202 may receive the first information from the UE 110; and when the first information indicates the measurement event is predicted to occur, the RAN node may be triggered by the first information to initiate early handover preparation with one or more candidate RAN nodes based on the first information.

[0071] The UE 110 may perform an evaluation of the measurement event prediction for a time duration for verification of the measurement event prediction, and report to the RAN 108 (e.g., RAN node 202) second information triggered by expiration of the time duration for the verification of the measurement event prediction. The second information may indicate an accuracy of the measurement event prediction based on the evaluation, and whether the measurement event has occurred or not occurred (e.g., upon expiration of the TTT associated with the measurement event). In some examples, the second information may be expressed as a compound two-bit signal, including a first bit set to indicate whether the measurement event prediction is accurate (e.g., true) or not accurate (e.g., false), and a second bit set to indicate whether the measurement event has occurred or not occurred. In some other examples, the second information may be expressed as a more generalized N-bit signal based on more than one threshold for accuracy of the measurement event prediction.

[0072] The RAN node 202 may receive the second information from the UE 110, make a determination whether to continue or terminate the early handover preparation based on the second information. When the second information indicates the measurement event prediction is not accurate or that the measurement event has not occurred, the RAN node may make the determination to terminate (and then terminate) the early handover preparation.

[0073] When the second information indicates the measurement event prediction is accurate and that the measurement event has occurred, the RAN node 202 may make the determination to continue the early handover preparation. In the case of HO of the UE 110, the RAN node may send the UE (and the UE may receive) a RRC reconfiguration message including a handover command for a handover of the UE to one of the candidate RAN node(s). In the case of CHO or LTM, the RAN node may send the UE (and the UE mayreceive) a configuration for LTM preparation or CHO preparation forthe UE, and the configuration may include candidate configuration(s) for the candidate RAN node(s).

[0074] FIGS. 6A and 6B are diagrams of a framework for measurement event prediction triggered reporting for early handover preparation, according to some example implementations. The diagrams illustrate time sequences at the UE 110 (in FIG. 6B) and the RAN node 202 (in FIG. 6A). Assume for purposes of illustration that the measurement event prediction is made according to the indirect approach in which an inference operation is performed to determine measurement predictions, and the measurement event prediction is the made from the measurement predictions.

[0075] As shown in FIG. 6B at the UE 110, a triggering condition for a measurement event prediction may be fulfilled at time tO. In some examples, the triggering condition for the measurement event prediction is an entering for the measurement event (e.g., A3-1 (entering condition) for an A3 event). In some of these examples, the triggering condition for the measurement event prediction is determined to be fulfilled when the entering condition forthe measurement event is determined to be fulfilled, such as based on an evaluation of measurements performed by the UE 110. In some other examples, the triggering condition for the measurement event prediction may be configured to be fulfilled before the entering condition for the measurement event is fulfilled.

[0076] When the triggering condition for the measurement event prediction is determined to be fulfilled, the UE 110 may buffer measurements performed by the UE within an observation window, such as a timeseries of radio measurements (e.g., RRM measurements) from serving and neighbor cells for an A3 event. The UE may make the measurement event prediction within a prediction window, based on the measurements performed by the UE in the observation window. In the indirect approach, the UE may apply the measurements to a ML model to determine measurement predictions, and the measurement event prediction may then be made from the measurement predictions. In some examples, the prediction window for the measurement event prediction may be aligned with the TTT associated with the measurement event. In other examples, the prediction window may be for a duration that is shorter or longer than the TTT.

[0077] The UE 110 may send first information to the RAN node 202 indicating whether the measurement event is predicted to occur or not occur. In some examples involving the indirect approach, the first information may include (1) the measurement predictions, (2) an indication (e.g., ACK / NACK) whether the measurement event is predicted to occur or not occur, and (3) an indication of the accuracy of the measurement prediction (e.g., in X%).

[0078] As shown in FIG. 6A at the RAN node 202, the first information indicating whether the measurement event is predicted to occur or not occur may be received. When the first information indicates (e.g, ACK) the measurement event is predicted to occur, the RAN node may be triggered by the first information to initiate early handover preparation with one or more candidate RAN nodes based on the first information. In some examples involving the indirect approach, the RAN node may initiate the early handover preparation based on the measurement predictions. When the first information is received, the RAN node may also startan early handover preparation timer, which in some examples is longerthan the TTT associated with the measurement event.

[0079] Returning to FIG. 6B, during a configured time duration for verification of the measurement event prediction, the UE 110 may perform an evaluation of the measurement event prediction. In some examples, the time duration may be aligned with either or both the prediction window or the TTT associated with the measurement event. In the evaluation, the UE may determine whether the measurement event prediction is maintained for the time duration for the verification based on the evaluation. In some examples involving the indirect approach, the UE may determine whether the measurement predictions deviate by more than a threshold deviation (e.g., thresholdMonitorRRMPredictiondB) from corresponding measurements performed by the UE during the time duration for the verification. In some of these examples, the UE may perform measurements during the time duration, and calculate a time series of delta values (e.g., mean average error (MAE) values) of the measurement predictions versus the measurements performed by the UE. The UE may in some of these examples later report the time series of delta values when those delta values are greater than the threshold deviation, which may indicate the measurement event prediction is not valid or otherwise accurate.

[0080] Upon expiration of the time duration for the verification, at time t1 , the UE 110 may be triggered to report second information to the RAN node 202. The second information may indicate an accuracy of the measurement event prediction based on the evaluation performed for the time duration. The second information may also indicate a status of the measurement event, such as whether the measurement event has occurred or not occurred. In some examples, the UE may skip, upon expiration of the TTT associated with the measurement event, a measurement report of the measurements performed by the UE, when the second information indicates the measurement event prediction is accurate.

[0081] In some examples, the second information may indicate that the measurement event prediction is accurate when the triggering condition is maintained for the time duration for the verification, and that the measurement event prediction is not accurate when the triggering condition is not maintained for the timeduration for the verification. In another example, the second information may indicate that the measurement event prediction is accurate when the measurement predictions do not deviate by more than the threshold deviation, and that the measurement event prediction is not accurate when the measurement predictions do deviate by more than the threshold deviation.

[0082] In some examples, the second information may be expressed as a compound two-bit signal, including a first bit set (1 or 0) to indicate whether the measurement event prediction is accurate or not accurate, and a second bit set (1 or 0) to indicate whether the measurement event has occurred or not occurred. In some other examples, the second information may be expressed as a more generalized N-bit signal based on more than one threshold for accuracy of the measurement event prediction.

[0083] In some examples, the RAN node 202 may configure the UE with event-triggered reporting in which the UE is to send a measurement report of the measurements performed by the UE, such as by uplink control information (UCI), MAC CE or L3 RRC message (e.g., UE assistance information (UAI)), when the measurement event prediction is indicated as not accurate. In some examples involving the indirect approach, instead of the measurements performed by the UE, the measurement report may include the time series of delta values when those delta values are greater than the threshold deviation (e.g., thresholdMonitorRRMPredictiondB), as indicated above.

[0084] As shown in FIG. 6B, at time t1, the RAN node 202 may receive, from the UE 110, the second information that indicates the accuracy of the measurement event prediction, and whether the measurement event has occurred or not occurred (e.g., upon expiration of the TTT associated with the measurement event).

[0085] When the second information indicates the measurement event prediction is accurate and the measurement event has occurred, while the early handover preparation is ongoing (or the early handover preparation timer is running), the RAN node 202 may continue the early handover preparation. In the case of HO of the UE, the RAN node may send the UE 110 a RRC reconfiguration message including a handover command for a handover of the UE to one of the candidate RAN node(s), without a measurement report from the UE. On the other hand, when the second information indicates the measurement event prediction is not accurate or that the measurement event has not occurred, the RAN node may make the determination to terminate (and then terminate) the early handover preparation (or terminate the early handover preparation timer). The RAN node may then in some examples initiate a legacy handover preparation procedure with a measurement report from the UE.

[0086] As indicated above, in the indirect approach for the measurement event prediction, the inference operation is performed to determine measurement predictions, such as a time-series of RRM measurementpredictions. This approach is intuitively different from the direct approach in which the inference operation is performed to more directly make the measurement event prediction. In some examples, then, evaluation of the measurement event prediction may include evaluation of the measurement predictions, and involve a threshold time distance from expiration of the TTT associated with the measurement event. This threshold time distance may at times be referred to as a time distance of measurement event (ETD), which may be defined as a time window starting from expiration of the TTT (e.g., t1) back to a time T 1 - ETD duration.

[0087] FIGS. 7A, 7B and 7C are diagrams of verification of a measurement event prediction according to the indirect approach, according to some example implementations. The diagrams are illustrated in the context of the A3 event in which measurements of the serving cell and a neighbor (candidate) cell are compared, with the neighbor cell being the one having the strongest predicted measurements among one or more neighbor (candidate) cells. As shown in FIG. 7A, within the duration of the TTT, the predicated measurements for the serving cell are always lower than the predicted measurements for the neighbor cell; and accordingly, the ETD may not be used, and the measurement event prediction may be indicated as accurate.

[0088] In FIGS. 7B and 7C, the predicted measurements for the serving cell crosses the predicted measurements for the neighbor cell. The UE 110 may determine the leaving condition for the measurement event (A3-2 for the A3 event) is fulfilled before expiration of the TTT. In particular, the UE may determine whether the leaving condition is satisfied within the ETD (as in FIG. 7B) or outside the ETD (as in FIG. 7C). When the leaving condition is satisfied within the ETD, the measurement event may be indicated as accurate (e.g., true). On the other hand, when the leaving condition is satisfied outside the ETD, the measurement event may be indicated as not accurate (e.g., false).

[0089] To further illustrate some example implementations, FIG. 8 is a diagram of a procedure for handover including measurement event prediction triggered reporting for early handover preparation. As shown, a UE 110 may at step 801 send UE capability information to the RAN 108 (source RAN node 202A) that indicates the UE supports ML-based measurement event prediction for early handover preparation. In some examples, the UE capability information may also indicate the UE supports UL signaling for the first information and second information to enable the start, continuation or termination of early handover preparation based on a measurement event prediction. The UE capability information may also in some examples indicate the UE supports a measurement reduction pattern for the indirect approach for the measurement event prediction, which may indicate a Y% reduction rate for reference signal transmission.Even further, in some examples, the UE capability information may indicate one or more other UE supported measurement event prediction-related configuration parameters.

[0090] The source RAN node may at step 802 send, to the UE 110, an event-triggered measurement reporting configuration for measurement event predictions for a measurement event (e.g., A3 event), such as by an RRC configuration message to the UE. In some examples involving the direct approach, the event-triggered measurement reporting configuration may indicate one or more time-domain parameters, such as an observation window for measurements performed by the UE for the inference operation, a prediction window for the inference operation, and / or a time duration for verification of the measurement event prediction. Additionally or alternatively, for example, the event-triggered measurement reporting configuration may indicate one or more reporting-related parameters, such as a trigger condition for the measurement event prediction, a measurement event configuration on which the measurement event prediction is to be made using the ML model, and / or a reporting condition for reporting the first information. The reporting-related parameters may also include, for example, reporting content, criteria and / or signal format.

[0091] In some examples involving the direct approach, the event-triggered measurement reporting configuration may indicate one or more time-domain parameters and / or reporting-related parameters, such as those indicated above. The event-triggered measurement reporting configuration may also indicate, for example, the threshold deviation (e.g., thresholdMonitorRRMPredictiondB) for the comparison of the measurement predictions with corresponding measurements. Additionally, for example, the event-triggered measurement reporting configuration may indicate the threshold time distance (e.g., ETD) (see FIGS. 7A-7C).

[0092] In both the direct and the indirect approach, in some examples, the prediction window may be configured to align with the time duration for verification of the measurement event prediction. This may ensure measurement event predictions are triggered for the ongoing events rather than past or future events. The observation window may be aligned with reference signals measured by the UE, such as synchronization signal / physical broadcast channel block (SSB) burst periodicity, channel state information reference signal (CSI-RS) periodicity, SSB measurement timing configuration (SMTC) window duration, or the like.

[0093] In some examples, the trigger condition for the measurement event prediction may be configured as the entering condition for the measurement event, or start of the TTT associated with the measurement event. In some examples, the RAN node 202 may configure a dedicated threshold or offset to be used to subject to an offset parameter (Off) for the event so that the measurement event prediction may be triggeredbefore the measurement event. In one example, this threshold / offset (e.g., offsetEventPredict) may be included in a measurement object (MeasObjectNR) for the measurements to be performed by the UE 110.

[0094] The source RAN node 202A may at step 803A transmit reference signals (RS) (e.g., SSB, CSI-RS) which may be measured by the UE 110. Similarly, the target RAN node may at step 803B transmit reference signals (e.g., SSB, CSI-RS) which may be measured by the UE.

[0095] The UE 110 may at step 804 monitor or otherwise evaluate the measurements performed by the UE, and determine that an entering condition for the measurement event is fulfilled. When the entering condition for the measurement event is also the triggering condition for a measurement event prediction, the UE may be triggered by the entering condition being fulfilled to perform the measurement event prediction. In another example in which the triggering condition is earlier than the entering condition, the UE may be triggered to perform the measurement event prediction before the entering condition is fulfilled. In some of these examples, the source RAN node 202A may configure the UE with a dedicated threshold / offset (e.g., offsetEventPredict as indicated above.

[0096] When the triggering condition is determined to be fulfilled, the UE 110 may at step 805 collect measurements performed by the UE (e.g., L1 / L3 RRM measurements) in an observation window (see FIG.6A), shown in FIG. 8 as T_observe. The UE may then at step 806 perform an inference operation in which the measurements performed by the UE are applied to a ML model for a measurement event prediction in a prediction window, shown in FIG. 8 as T_predict.

[0097] In the direct approach, the measurements may be applied to the ML model to determine the measurement event prediction. Results of the measurement event prediction in this case may indicate whether the measurement event is predicted to occur or not occur, with in some examples an X% prediction confidence probability. In the indirect approach, the measurements may be applied to the ML model to determine measurement predictions from which the measurement event prediction is made. In this case, the results of the measurement event prediction may include a similar indication whether the measurement event is predicted to occur or not occur, and may also include the measurement predictions. Such as with Y dB accuracy or Z% regression confidence probability.

[0098] The UE 110 may at step 807 send a first indication signal including first information to the source RAN node 202A. The first information may include the results of the measurement prediction, including an indication whether the measurement event is predicted to occur or not occur (e.g., ACK / NACK). In some examples, the first information may be carried by a UCI that includes a bit set to indicate whether the measurement event is predicted to occur or not occur. In some other examples, the first information may becarried by a MAC CE or L3 message, such as a measurement report. In yet another example, the first information may be carried by UAI in an RRC message. In some examples, the first information may imply that the TTT for the measurement event has started, and that the entering condition for the measurement event has been fulfilled.

[0099] The source RAN node 202A may receive the first indication signal including the first information; and at step 808A, the source RAN node may be triggered by the first information to initiate early handover preparation with the target RAN node 202B. In some examples involving the direct approach, the source RAN node may initiate the early handover preparation based on the measurements performed by the UE in the observation window until the time the entering condition for the measurement event is fulfilled. In some examples involving the indirect approach, the source RAN node may initiate the early handover preparation based on the measurements performed by the UE in the observation window until the time the entering condition for the measurement event is fulfilled, and the measurement predictions in the prediction window.

[0100] In a time duration for verification of the measurement event prediction, which may align with the TTT associated with the measurement event, the UE 110 may at step 808B perform an evaluation of the measurement event prediction. In some examples involving the indirect approach, the UE may determine whether the measurement predictions deviate by more than a threshold deviation (e.g., thresholdMonitorRRMPredictiondB) from corresponding measurements performed by the UE during the time duration for the verification. In some of these examples, the UE may perform measurements during the time duration, and calculate a time series of delta values (e.g., MAE values) of the measurement predictions versus the measurements performed by the UE for comparison with the threshold deviation. When the delta values are greater than the threshold deviation, the UE may in some examples report, at step 809, the time series of delta values, which may indicate the measurement event prediction is not valid or otherwise accurate, instead of reporting the measurements performed by the UE.

[0101] Upon expiration of the time duration for verification of the measurement event prediction, at step 809, the UE 110 may be triggered to send a second indication signal including first information to the source RAN node 202A. The second information may indicate, for example, an accuracy of the measurement event prediction, and whether the measurement event has occurred or not occurred. The second indication signal may in some examples imply the TTT has expired. In some examples, the UE may skip, upon expiration of the TTT associated with the measurement event, a measurement report of the measurements performed by the UE, when the second information indicates the measurement event prediction is accurate.

[0102] In some examples, the second information may be expressed as a compound two-bit signal, including a first bit set (1 or 0) to indicate whether the measurement event prediction is accurate or not accurate, and a second bit set (1 or 0) to indicate whether the measurement event has occurred or not occurred. In some examples in which the measurement event prediction is indicated as not accurate, the second information may include the time series of delta values (e.g., MAE values) that are greater than the threshold deviation (e.g., thresholdMonitorRRMPredictiondB). In various examples, the second information may be carried by a UCI, a MAC CE, an L3 message (e.g., a measurement report), or UAI in an RRC message.

[0103] The source RAN node 202A may receive the second indication signal including the second information; and at step 810, the source RAN node may continue to monitor the early handover preparation. The source RAN node may make a determination whether to continue or terminate the early handover preparation based on the second information. When the second information indicates the measurement event prediction is accurate and the measurement event has occurred (e.g., upon expiration of the TTT), the source RAN node may continue the early handover preparation. The source RAN node may perform an early handover execution based on the early handover preparation, and, at step 811, send the UE 110 a RRC reconfiguration message including a handover command for a handover of the UE to the target RAN node 202B.

[0104] When the second information indicates the measurement event prediction is not accurate or that the measurement event has not occurred (e.g., upon expiration of the TTT), the source RAN node 202A may make the determination to terminate (and then terminate) the early handover preparation. The source RAN node may then in some examples initiate a legacy handover preparation procedure with a measurement report from the UE 110. In some examples, an inter-RAN node level signaling exchange may occur between the source RAN node and the target RAN node 202B. In some of these examples, the source RAN node may send the target RAN node a message to cancel the early handover preparation. In some other examples, the source RAN node may send the target RAN node an empty message, which the target RAN node may interpret as cancelation of the early handover preparation.

[0105] FIG. 9 is a diagram of a procedure for LTM including measurement event prediction triggered reporting for early handover preparation, according to some example implementations. The procedure for LTM is described in the context of a CU-DU split architecture in which the RAN node 202 includes a CU 204 and one or more DUs 206 (not separately shown in FIG. 9). As shown, the procedure for LTM may includesteps 901, 902, 903, 904, 905 and 906, which may be the same as or similar to steps 801, 802, 803A / B, 804, 805 and 806 in the procedure for handover shown in FIG. 8 and described above.

[0106] The UE 110 may at step 907 send a first indication signal including first information to the RAN node 202 (e.g., a source DU 206). Similar to before, the first information may include the results of the measurement prediction, including an indication whether the measurement event is predicted to occur or not occur (e.g., ACK / NACK). In various examples, the first information may be carried by a UCI, a MAC CE, an L3 message (e.g., a measurement report), or UAI in an RRC message.

[0107] The source DU 206 of the RAN node 202 may receive the first indication signal including the first information; and at step 908A, the source DU may be triggered by the first information to initiate early LTM candidate preparation with a target DU (of the same or another RAN node). In some examples involving the direct approach, the source DU may initiate the early LTM candidate preparation based on the measurements performed by the UE in the observation window until the time the entering condition for the measurement event is fulfilled. In some examples involving the indirect approach, the source DU may initiate the early LTM candidate preparation based on the measurements performed by the UE in the observation window until the time the entering condition for the measurement event is fulfilled, and the measurement predictions in the prediction window.

[0108] In a time duration for verification of the measurement event prediction, which may align with the TTT associated with the measurement event, the UE 110 may at step 908B perform an evaluation of the measurement event prediction. In some examples involving the indirect approach, the UE may determine whether the measurement predictions deviate by more than a threshold deviation (e.g., thresholdMonitorRRMPredictiondB) from corresponding measurements performed by the UE during the time duration for the verification. In some of these examples, the UE may perform measurements during the time duration, and calculate a time series of delta values (e.g., MAE values) of the measurement predictions versus the measurements performed by the UE for comparison with the threshold deviation. When the delta values are greater than the threshold deviation, the UE may in some examples report, at step 909, the time series of delta values, which may indicate the measurement event prediction is not valid or otherwise accurate, instead of reporting the measurements performed by the UE.

[0109] Upon expiration of the time duration for verification of the measurement event prediction, at step 909, the UE 110 may be triggered to send a second indication signal including first information to the source RAN node 202 (e.g., source DU 206). The second information may indicate, for example, an accuracy of the measurement event prediction, and whether the measurement event has occurred or not occurred. Thesecond indication signal may in some examples imply the TTT has expired. In some examples, the UE may skip, upon expiration of the TTT associated with the measurement event, a measurement report of the measurements performed by the UE, when the second information indicates the measurement event prediction is accurate.

[0110] In some examples, the second information may be expressed as a compound two-bit signal, including a first bit set (1 or 0) to indicate whether the measurement event prediction is accurate or not accurate, and a second bit set (1 or 0) to indicate whether the measurement event has occurred or not occurred. In some examples in which the measurement event prediction is indicated as not accurate, the second information may include the time series of delta values (e.g., MAE values) that are greater than the threshold deviation (e.g., thresholdMonitorRRMPredictiondB). In various examples, the second information may be carried by a UCI, a MAC CE, an L3 message (e.g., a measurement report), or UAI in an RRC message.

[0111] The source RAN node 202 (e.g., source DU 206) may receive the second indication signal including the second information; and at step 910, the source DU may continue to monitor the early LTM candidate preparation. The source DU may make a determination whether to continue or terminate the early LTM candidate preparation based on the second information. When the second information indicates the measurement event prediction is accurate and the measurement event has occurred (e.g., upon expiration of the TTT), the source DU may continue the early LTM candidate preparation. The source DU may initiate the early DL / UL synchronization based and, at step 911, send the UE 110 a configuration for LTM preparation including early LTM candidates, such as in a RRC reconfiguration message to the UE.

[0112] When the second information indicates the measurement event prediction is not accurate or that the measurement event has not occurred (e.g., upon expiration of the TTT), the source RAN node 202 (e.g., source DU 206) may make the determination to terminate (and then terminate) the early LTM candidate preparation. The source DU may then in some examples initiate a legacy handover preparation procedure with a measurement report from the UE 110. In some examples, an inter-RAN node level signaling exchange may occur between the source DU and the target DU. In some of these examples, the source DU may send the target DU a message to cancel the early LTM candidate preparation. In some other examples, the source DU may send the target DU an empty message, which the target DU may interpret as cancelation of the early LTM candidate preparation.

[0113] Upon receiving the message from the source DU 206 to cancel the early LTM candidate preparation, the target RAN node 202 (e.g., DU or CU 204) may stop a monitoring procedure for reception ofa configured grant (CG) (if configured towards the UE 110). In another example, when UE is instructed to perform RACH-less execution of a mobility procedure with dynamic grant (DG), target RAN node may optimize the resources at the target RAN node and stop scheduling the DG.

[0114] In some examples, even if the second information indicates the measurement event prediction is not accurate or that the measurement event has not occurred, the source RAN node 202 may override termination of the early handover preparation. This may be suitable for deployments in which the handover preparation is fast, such as in a monolithic RAN node architecture, and for cases involving load balancing between cells when the network initiates early preparation based on the first information. In some of these examples, the source RAN node may override termination of the early handover preparation, such as based on actual load at the source RAN node and the target RAN node. The source RAN node may notify the UE 110 that the early handover preparation will not be terminated, which may thereby reduce overhead and allow more accurate management of the load between the RAN nodes.

[0115] FIG. 10 is a flowchart illustrating various steps in a method 1000 performed by a user equipment (UE), according to various example implementations. The method includes determining a triggering condition for a measurement event prediction is fulfilled, as shown at block 1002. The method includes performing an inference operation in which measurements performed by the UE are applied to a machine learning (ML) model to determine the measurement event prediction indicating the measurement event is predicted to occur, as shown at block 1004. The method includes reporting to a network first information indicating that the measurement event is predicted to occur, as shown at block 1006. The method includes performing an evaluation of the measurement event prediction for a time duration for verification of the measurement event prediction, as shown at block 1008. And the method includes reporting to the network second information triggered by expiration of the time duration for the verification of the measurement event prediction, the second information indicating an accuracy of the measurement event prediction based on the evaluation, and whether the measurement event has occurred or not occurred, as shown at block 1010.

[0116] In some examples, the method 1000 further includes sending UE capability information to the network that indicates the UE supports ML-based measurement event prediction for early handover preparation. In some of these examples, the first information is reported to the network at block 1006 to trigger the network to initiate early handover preparation when the measurement event is predicted to occur.

[0117] In some examples, the method 1000 further includes receiving from the network an event-triggered measurement reporting configuration. In some of these examples, the inference operation is performed at block 1004 according to the event-triggered measurement reporting configuration.

[0118] In some examples, the triggering condition for the measurement event prediction is an entering for the measurement event. In some of these examples, determining the triggering condition is fulfilled at block 1002 includes determining the entering condition for the measurement event is fulfilled based on an evaluation of measurements performed by the UE.

[0119] In some examples, the triggering condition for the measurement event prediction is configured to be fulfilled before an entering for the measurement event is fulfilled.

[0120] In some examples, the time duration for the verification of the measurement event prediction is aligned with a time-to-trigger (TTT) associated with the measurement event.

[0121] In some examples, performing the evaluation of the measurement event prediction atblock 1008 includes determining whether the measurement event prediction is maintained for the time duration for the verification based on an evaluation of further measurements performed by the UE.

[0122] In some examples, second information indicates that the measurement event prediction is accurate when the measurement event prediction is maintained for the time duration for the verification, and that the measurement event prediction is not accurate when the triggering condition is not maintained for the time duration for the verification.

[0123] In some examples, the second information indicates the measurement event prediction is accurate and that the measurement event has occurred. In some of these examples, the method 1000 further includes receiving from the network a radio resource control (RRC) reconfiguration message including a handover command for a handover of the UE.

[0124] In some examples, the second information indicates the measurement event prediction is accurate and that the measurement event has occurred. In some of these examples, the method 1000 further includes receiving from the network a configuration for lower-layer triggered mobility (LTM) preparation or conditional handover (CHO) preparation for the UE.

[0125] FIG. 11 is a flowchart illustrating various steps in a method 1100 performed by a radio access network (RAN) node, according to various example implementations. The method includes configuring a user equipment (UE) with an event-triggered measurement reporting configuration according to which the UE is to perform an inference operation in which measurements performed by the UE are applied to a machine learning (ML) model to determine a measurement event prediction for a measurement event, as shown at block 1102. The method includes receiving from the UE first information including information for the measurement event prediction indicating that the measurement event is predicted to occur, as shown at block 1104. The method includes initiating early handover preparation with one or more candidate RAN nodesbased the first information, as shown at block 1106. The method includes receiving from the UE second information indicating an accuracy of the measurement event prediction based on an evaluation of the measurement event prediction for a time duration for verification of the measurement event prediction, the second information also indicating whether the measurement event has occurred or not occurred, as shown at block 1108. And the method includes making a determination whether to continue or terminate the early handover preparation based on the second information, as shown at block 1110.

[0126] In some examples, the method 1100 further includes receiving UE capability information from the UE that indicates the UE supports ML-based measurement event prediction for early handover preparation. In some of these examples, the UE is configured at block 1102 with the event-triggered measurement reporting configuration based on the UE capability information.

[0127] In some examples, the event-triggered measurement reporting configuration indicates at least one of a trigger condition for the measurement event prediction, an observation window for measurements performed by the UE for the inference operation, a prediction window for the inference operation, a time duration for verification of the measurement event prediction, a measurement event configuration on which the measurement event prediction is to be made using the ML model, or a reporting condition for reporting the first information.

[0128] In some examples, the first information includes the measurements performed by the UE, and the early handover preparation is initiated at block 1106 based on the measurements.

[0129] In some examples, the second information indicates the measurement event prediction is not accurate or that the measurement event has not occurred, and the determination is made at block 1110 to terminate the early handover preparation. In some of these examples, the method further includes terminating the early handover preparation based on the determination.

[0130] In some examples, the second information includes further measurements performed by the UE within time duration for verification. In some of these examples, the method 1100 further includes initiating an handover preparation based on the further measurements.

[0131] In some examples, the second information indicates the measurement event prediction is accurate and that the measurement event has occurred, and the determination is made at block 1110 to continue the early handover preparation. In some of these examples, the method 1100 further includes sending to the UE a radio resource control (RRC) reconfiguration message including a handover command for a handover of the UE to one of the one or more candidate RAN nodes.

[0132] In some examples, the second information indicates the measurement event prediction is accurate and that the measurement event has occurred, and the determination is made at block 1110 to continue the early handover preparation. In some of these examples, the method 1100 further includes sending to the UE a configuration for lower-layer triggered mobility (LTM) preparation or conditional handover (CHO) preparation for the UE, and the configuration includes one or more candidate configurations for the one or more candidate RAN nodes.

[0133] FIG. 12 is a flowchart illustrating various steps in a method 1200 performed by a user equipment (UE), according to various example implementations. The method includes determining a triggering condition for a measurement event prediction is fulfilled, as shown at block 1202. The method includes performing an inference operation in which measurements performed by the UE are applied to a machine learning (ML) model to determine measurement predictions from which the measurement event prediction is made, and the measurement event prediction indicates that the measurement event is predicted to occur, as shown at block 1204. The method includes reporting to a network first information indicating that the measurement event is predicted to occur, as shown at block 1206. The method includes performing an evaluation of the measurement event prediction for a time duration for verification of the measurement event prediction, as shown at block 1208. And the method includes reporting to the network second information triggered by expiration of the time duration for the verification of the measurement event prediction, the second information indicating an accuracy of the measurement event prediction based on the evaluation, and whether the measurement event has occurred or not occurred, as shown at block 1210.

[0134] In some examples, the method 1200 further includes sending UE capability information to the network that indicates the UE supports ML-based measurement event prediction for early handover preparation. In some of these examples, the first information is reported to the network at block 1210 to trigger the network to initiate early handover preparation when the measurement event is predicted to occur.

[0135] In some examples, the method 1200 further includes receiving from the network an event-triggered measurement reporting configuration. In some of these examples, the inference operation is performed at block 1204 according to the event-triggered measurement reporting configuration.

[0136] In some examples, the triggering condition for the measurement event prediction is an entering for the measurement event. In some of these examples, determining the triggering condition is fulfilled at block 1202 includes determining the entering condition for the measurement event is fulfilled based on an evaluation of measurements performed by the UE.

[0137] In some examples, the triggering condition for the measurement event prediction is configured to be fulfilled before an entering for the measurement event is fulfilled.

[0138] In some examples, performing the evaluation of the measurement event prediction atblock 1208 includes determining whether the measurement predictions deviate by more than a threshold deviation from corresponding measurements performed by the UE during the time duration for the verification.

[0139] In some examples, the second information indicates that the measurement event prediction is accurate when the measurement predictions do not deviate by more than the threshold deviation, and that the measurement event prediction is not accurate when the measurement predictions do deviate by more than the threshold deviation.

[0140] In some examples, the time duration for the verification of the measurement event prediction is aligned with a time-to-trigger (TTT) associated with the measurement event.

[0141] In some examples, the triggering condition for the measurement event prediction is an entering for the measurement event in which the TTT associated with the measurement event is started. In some of these examples, performing the evaluation of the measurement event prediction at block 1208 includes determining whether a leaving condition for the measurement event is satisfied before expiration of the TTT based on an evaluation of the measurement event predictions.

[0142] In some examples, whether the leaving condition is satisfied is determined within a threshold time distance from the expiration of the TTT.

[0143] In some examples, the second information indicates the measurement event prediction is accurate and that the measurement event has occurred. In some of these examples, the method 1200 further includes receiving from the network a radio resource control (RRC) reconfiguration message including a handover command for a handover of the UE.

[0144] In some examples, the second information indicates the measurement event prediction is accurate and that the measurement event has occurred. In some of these examples, the method 1200 further includes receiving from the network a configuration for lower-layer triggered mobility (LTM) preparation or conditional handover (CHO) preparation for the UE.

[0145] FIG. 13 is a flowchart illustrating various steps in a method 1300 performed by a radio access network (RAN) node, according to various example implementations. The method includes configuring a user equipment (UE) with an event-triggered measurement reporting configuration according to which the UE is to perform an inference operation in which measurements performed by the UE are applied to a machine learning (ML) model to determine measurement predictions from which the measurement event prediction ismade, as shown at block 1302. The method includes receiving from the UE first information including information for the measurement event prediction indicating that the measurement event is predicted to occur, as shown at block 1304. The method includes initiating early handover preparation with one or more candidate RAN nodes based the first information, as shown at block 1306. The method includes receiving from the UE second information indicating an accuracy of the measurement event prediction based on an evaluation of the measurement event prediction for a time duration for verification of the measurement event prediction, the second information also indicating whether the measurement event has occurred or not occurred, as shown at block 1308. And the method includes making a determination whether to continue or terminate the early handover preparation based on the second information, as shown at block 1310.

[0146] In some examples, the method 1300 further includes receiving UE capability information from the UE that indicates the UE supports ML-based measurement event prediction for early handover preparation. In some of these examples, the UE is configured at block 1302 with the event-triggered measurement reporting configuration based on the UE capability information.

[0147] In some examples, the event-triggered measurement reporting configuration indicates at least one of a trigger condition for the measurement event prediction, an observation window for measurements performed by the UE for the inference operation, a prediction window for the inference operation, a time duration for verification of the measurement event prediction, a measurement event configuration on which the measurement event prediction is to be made using the ML model, or a reporting condition for reporting the first information.

[0148] In some examples, the event-triggered measurement reporting configuration further indicates a threshold deviation for a comparison of the measurement predictions with corresponding measurements performed by the UE during the time duration for the verification of the measurement event prediction.

[0149] In some examples, the first information includes the measurements performed by the UE and the measurement predictions. In some of these examples, the early handover preparation is initiated at block 1306 based on the measurements and the measurement predictions.

[0150] In some examples, the second information indicates the measurement event prediction is not accurate or that the measurement event has not occurred, and the determination is made to terminate at block 1310 the early handover preparation. In some of these examples, the method 1300 further includes terminating the early handover preparation based on the determination.

[0151] In some examples, the second information includes further measurements performed by the UE within time duration for verification. In some of these examples, the method 1300 further includes initiating a handover preparation based on the further measurements.

[0152] In some examples, the second information indicates the measurement event prediction is accurate and that the measurement event has occurred, and the determination is made at block 1310 to continue the early handover preparation. In some of these examples, the method 1300 further includes sending to the UE a radio resource control (RRC) reconfiguration message including a handover command for a handover of the UE to one of the one or more candidate RAN nodes.

[0153] In some examples, the second information indicates the measurement event prediction is accurate and that the measurement event has occurred, and the determination is made at block 1310 to continue the early handover preparation. In some of these examples, the method 1300 further includes sending to the UE a configuration for lower-layer triggered mobility (LTM) preparation or conditional handover (CHO) preparation for the UE, and the configuration includes one or more candidate configurations for the one or more candidate RAN nodes.

[0154] According to example implementations of the present disclosure, a telecommunications system 100 or PLMN 102, and components thereof such as UE 110, CN 106, RAN 108, RAN node 202, CU 204 and / or DU 206, may be implemented by various means. Means for implementing the system and its components may include hardware, firmware, software, or combinations thereof. In some examples, one or more apparatuses may be configured to function as or otherwise implement the system and its components shown and described herein. In examples involving more than one apparatus, the respective apparatuses may be connected to or otherwise in communication with one another in a number of different manners, such as directly or indirectly via a wired or wireless network or the like.

[0155] According to some example implementations, at least some of the method 1000 described with respect to FIG. 10 may be carried out by an apparatus comprising means for performing functions corresponding steps of the method. Similarly, at least some of the method 1100 described with respect to FIG. 11 may be carried out by an apparatus comprising means for performing functions corresponding steps of the method. At least some of the method 1200 described with respect to FIG. 12 may be carried out by an apparatus comprising means for performing functions corresponding steps of the method. And at least some of the method 1300 described with respect to FIG. 13 may be carried out by an apparatus comprising means for performing functions corresponding steps of the method. Examples of a suitable apparatus may include a user equipment, user device, user terminal or the like. Other examples of a suitable apparatus may includea RAN node (e.g., ng-eNB, gNB, gNB-DU, gNB-CU) or any suitable apparatus, such as a server, host or node.

[0156] FIG. 14 illustrates an apparatus 1400 in which means for performing various operations includes hardware, alone or under direction of one or more computer programs from a computer-readable storage medium or other memory, such as computer memory, according to some example implementations of the present disclosure. The apparatus may include one or more of each of a number of components such as, for example, processing circuitry 1402 connected to computer-readable storage medium or other memory 1404.

[0157] The processing circuitry 1402 may be composed of one or more processors alone or in combination with one or more computer-readable storage media. The processing circuitry is generally any piece of computer hardware that is capable of processing information such as, for example, data, computer programs, computer code and / or other suitable electronic information. The processing circuitry is composed of a collection of electronic circuits some of which may be packaged as an integrated circuit or multiple interconnected integrated circuits (an integrated circuit at times more commonly referred to as a “chip”). The processing circuitry may be configured to execute computer programs, which may be stored onboard the processing circuitry or otherwise stored in the memory 1404 (of the same or another apparatus).

[0158] The processing circuitry 1402 may comprise a number of processors, a multi-core processor or some other type of processor, such as a central processing unit, a graphics processing unit, a tensor processing, unit, or an accelerator, depending on the particular implementation. Further, the processing circuitry may be implemented using a number of heterogeneous processor systems in which a main processor is present with one or more secondary processors on a single chip. As another illustrative example, the processing circuitry may be a symmetric multi-processor system containing multiple processors of the same type. In yet another example, the processing circuitry may be embodied as or otherwise include one or more application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or the like. Thus, although the processing circuitry may be capable of executing a computer program to perform one or more functions, the processing circuitry of various examples may be capable of performing one or more functions without the aid of a computer program. In either instance, the processing circuitry may be appropriately programmed to perform functions or operations according to example implementations of the present disclosure.

[0159] The memory 1404 is generally any piece of computer hardware that is capable of storing information such as, for example, data, computer programs, instructions 1406 (e.g., computer-readable program code) and / or other suitable information either on a temporary basis and / or a permanent basis. Thememory may include volatile and / or non-volatile memory, and may be fixed or removable. Examples of suitable memory include recording media, random access memory (RAM), read-only memory (ROM), a hard drive, a flash memory, a thumb drive, a removable computer diskette, an optical disk or some combination thereof.

[0160] The memory 1404 is a non-transitory device capable of storing information. One example of a suitable memory is a computer-readable storage medium, which is distinguishable from a computer-readable transmission medium capable of carrying information from one location to another. Examples of suitable computer-readable transmission media comprise electronic carrier signals, telecommunications signals, or some combination thereof. As used herein, the term “non-transitory” 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 versus ROM). A computer-readable medium as described herein generally refers to a computer-readable storage medium or computer-readable transmission medium. A computer-readable medium is any entity or device capable in which information, such as one or more computer programs or portions thereof, may be stored and carried.

[0161] In addition to the memory 1404 (e.g., computer-readable storage medium), the processing circuitry 1402 may also be connected to one or more interfaces for displaying, transmitting and / or receiving information. The interfaces may include a communications interface 1408 and / or one or more user interfaces. The communications interface may be configured to transmit and / or receive information, such as to and / or from other apparatus(es), network(s) or the like. The communications interface may be configured to transmit and / or receive information by physical (wired) and / or wireless communications links. Examples of suitable communication interfaces include a network interface controller (NIC), wireless NIC (WNIC) or the like.

[0162] The user interfaces may include a display 1410 and / or one or more user input interfaces 1412. The display may be configured to present or otherwise display information to a user, suitable examples of which include a liquid crystal display (LCD), light-emitting diode (LED) display, organic LED (OLED) display, active-matrix OLED (AMOLED) or the like. The user input interfaces may be wired or wireless, and may be configured to receive information from a user into the apparatus, such as for processing, storage and / or display. Suitable examples of user input interfaces include a microphone, image or video capture device, keyboard or keypad, joystick, touch-sensitive surface (separate from or integrated into a touchscreen), biometric sensor or the like. The user interfaces may furtier include one or more interfaces for communicating with peripherals such as printers, scanners or the like.

[0163] Execution of the instructions 1406 by the processing circuitry 1402, or storage of the instructions in the memory 1404, supports combinations of operations for implementing example implementations of thepresent disclosure. In this manner, an apparatus 1400 may comprise at least one processing circuitry and at least one memory coupled to the at least one processing circuitry, where the at least one processing circuitry is configured to execute instructions stored in the at least one memory. It will also be understood that one or more functions, and combinations of functions, may be implemented by special purpose hardware-based computer systems and / or processing circuitry which perform the specified functions, or combinations of special purpose hardware and program code instructions.

[0164] Some example implementations of the present disclosure may also be carried out in the form of a computer process defined by one or more computer programs or portions thereof. Example implementations of the present disclosure may be carried out by executing at least one portion of a computer program comprising instructions. The computer program may be in source code form, object code form, or in some intermediate form. The computer program may be stored in a computer-readable medium that is readable by a computer, processing circuitry or other suitable apparatus. As indicated above, for example, the computer program may be stored in a memory, such as a computer-readable storage medium. Additionally or alternatively, for example, the computer program may be stored in a computer-readable transmission medium. The coding of software for carrying out example implementations of the present disclosure is well within the scope of a person of ordinary skill in the art.

[0165] As will be appreciated, any suitable instructions may be loaded onto a computer, a processor, a processing circuitry or other programmable apparatus from a memory or a computer-readable medium (e.g . , computer-readable storage medium, computer-readable transmission medium) to produce a particular machine, such that the particular machine becomes a means for implementing the functions specified herein. The instructions may also be stored in a computer-readable medium that can direct a computer, a processor, a processing circuitry or other programmable apparatus to function in a particular manner to thereby generate a particular machine or particular article of manufacture. In some examples, the instructions stored in the computer-readable medium may produce an article of manufacture, where the article of manufacture becomes a means for implementing functions described herein. The instructions may be retrieved from a computer-readable medium and loaded into a computer, processor, processing circuitry or other programmable apparatus to configure the computer, processor, processing circuitry or other programmable apparatus to execute operations to be performed on or by the computer, processor, processing circuitry or other programmable apparatus.

[0166] Retrieval, loading and execution of instructions comprising program code instructions may be performed sequentially such that one instruction is retrieved, loaded and executed at a time. In some exampleimplementations, retrieval, loading and / or execution may be performed in parallel such that multiple instructions are retrieved, loaded, and / or executed together. Execution of the program code instructions may produce a computer-implemented process such that the instructions executed by the computer, processor, processing circuitry or other programmable apparatus provide operations for implementing functions described herein.

[0167] Many modifications and other implementations of the disclosure set forth herein will come to mind to one skilled in the art to which the disclosure pertains having the benefit of the teachings presented in the foregoing description and the associated figures. Therefore, it is to be understood that the disclosure is not to be limited to the specific implementations disclosed and that modifications and other implementations are intended to be included within the scope of the appended claims. Moreover, although the foregoing description and the associated figures describe example implementations in the context of certain example combinations of elements and / or functions, it should be appreciated that different combinations of elements and / or functions may be provided by alternative implementations without departing from the scope of the appended claims. In this regard, for example, different combinations of elements and / or functions than those explicitly described above are also contemplated as may be set forth in some of the appended claims. Although specific terms are employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation.

Claims

WHAT IS CLAIMED IS:

1. A method performed by a user equipment (UE), the method comprising:determining a triggering condition for a measurement event prediction is fulfilled;performing an inference operation in which measurements performed by the UE are applied to a machine learning (ML) model to determine the measurement event prediction indicating the measurement event is predicted to occur;reporting to a network first information indicating that the measurement event is predicted to occur; performing an evaluation of the measurement event prediction for a time duration for verification of the measurement event prediction; andreporting to the network second information triggered by expiration of the time duration for the verification of the measurement event prediction, the second information indicating an accuracy of the measurement event prediction based on the evaluation, and whether the measurement event has occurred or not occurred.

2. The method of claim 1, wherein the method further comprises sending UE capability information to the network that indicates the UE supports ML-based measurement event prediction for early handover preparation, andwherein the first information is reported to the network to trigger the network to initiate early handover preparation when the measurement event is predicted to occur.

3. The method of claim 1 or claim 2, wherein the method further comprises receiving from the network an event-triggered measurement reporting configuration, and the inference operation is performed according to the event-triggered measurement reporting configuration.

4. The method of any of claims 1 to 3, wherein the triggering condition for the measurement event prediction is an entering for the measurement event, andwherein determining the triggering condition is fulfilled includes determining the entering condition for the measurement event is fulfilled based on an evaluation of measurements performed by the UE.

5. The method of any of claims 1 to 4, wherein the triggering condition for the measurement event prediction is configured to be fulfilled before an entering for the measurement event is fulfilled.-39-6. The method of any of claims 1 to 5, wherein the time duration for the verification of the measurement event prediction is aligned with a time-to-trigger (TTT) associated with the measurement event.

7. The method of any of claims 1 to 6, wherein performing the evaluation of the measurement event prediction includes determining whether the measurement event prediction is maintained for the time duration for the verification based on an evaluation of further measurements performed by the UE.

8. The method of claim 7, wherein second information indicates that the measurement event prediction is accurate when the measurement event prediction is maintained for the time duration for the verification, and that the measurement event prediction is not accurate when the triggering condition is not maintained for the time duration for the verification.

9. The method of any of claims 1 to 8, wherein the second information indicates the measurement event prediction is accurate and that the measurement event has occurred, and wherein the method further comprises receiving from the network a radio resource control (RRC) reconfiguration message including a handover command for a handover of the UE.

10. The method of any of claims 1 to 9, wherein the second information indicates the measurement event prediction is accurate and that the measurement event has occurred, and wherein the method further comprises receiving from the network a configuration for lower-layer triggered mobility (LTM) preparation or conditional handover (CHO) preparation for the UE.

11. A method performed by a radio access network (RAN) node, the method comprising: configuring a user equipment (UE) with an event-triggered measurement reporting configuration according to which the UE is to perform an inference operation in which measurements performed by the UE are applied to a machine learning (ML) model to determine a measurement event prediction for a measurement event;receiving from the UE first information including information for the measurement event prediction indicating that the measurement event is predicted to occur;-40-initiating early handover preparation with one or more candidate RAN nodes based the first information;receiving from the UE second information indicating an accuracy of the measurement event prediction based on an evaluation of the measurement event prediction for a time duration for verification of the measurement event prediction, the second information also indicating whether the measurement event has occurred or not occurred; andmaking a determination whether to continue or terminate the early handover preparation based on the second information.

12. The method of claim 11, wherein the method further comprises receiving UE capability information from the UE that indicates the UE supports ML-based measurement event prediction for early handover preparation, andwherein the UE is configured with the event-triggered measurement reporting configuration based on the UE capability information.

13. The method of claim 11 or claim 12, wherein the event-triggered measurement reporting configuration indicates at least one of:a trigger condition for the measurement event prediction;an observation window for measurements performed by the UE for the inference operation;a prediction window for the inference operation;a time duration for verification of the measurement event prediction;a measurement event configuration on which the measurement event prediction is to be made using the ML model; ora reporting condition for reporting the first information.

14. The method of any of claims 11 to 13, wherein the first information includes the measurements performed by the UE, and the early handover preparation is initiated based on the measurements.

15. The method of any of claims 11 to 14, wherein the second information indicates the measurement event prediction is not accurate or that the measurement event has not occurred, and the determination is made to terminate the early handover preparation, andwherein the method further comprises terminating the early handover preparation based on the determination.

16. The method of claim 15, wherein the second information includes further measurements performed by the UE within time duration for verification, and the method further comprises initiating an handover preparation based on the further measurements.

17. The method of any of claims 11 to 16, wherein the second information indicates the measurement event prediction is accurate and that the measurement event has occurred, and the determination is made to continue the early handover preparation, andwherein the method further comprises sending to the UE a radio resource control (RRC) reconfiguration message including a handover command for a handover of the UE to one of the one or more candidate RAN nodes.

18. The method of any of claims 11 to 17, wherein the second information indicates the measurement event prediction is accurate and that the measurement event has occurred, and the determination is made to continue the early handover preparation, andwherein the method further comprises sending to the UE a configuration for lower-layer triggered mobility (LTM) preparation or conditional handover (CHO) preparation for the UE, and the configuration includes one or more candidate configurations for the one or more candidate RAN nodes.

19. An apparatus comprising:at least one memory configured to store instructions; andat least one processing circuitry configured to access the at least one memory, and execute the instructions to cause the apparatus to perform the method of any of claims 1 to 18.

20. A computer-readable medium comprising instructions that, in response to execution by at least one processing circuitry, causes an apparatus to perform the method of any of claims 1 to 18.

Images