Measurement event prediction based mobility optimization

Abstract

A method performed by a user equipment (UE) is provided. The method includes sending UE capability information to a network that indicates the UE supports machine learning (ML)-based measurement event prediction, and that indicates the ML model is available in the UE and trained for an inference operation. The method includes receiving an event-triggered measurement reporting configuration from the network for reporting measurement event predictions for a measurement event according to the UE capability information. The method includes performing the inference operation according to the event-triggered measurement reporting configuration in which a measurement event prediction is made using a ML model to which measurements performed by the UE are applied. And the method includes reporting the measurement event prediction or the measurement event to the network for evaluation.

Description

MEASUREMENT EVENT PREDICTION BASED MOBILITY OPTIMIZATIONTECHNOLOGICAL FIELD

[0001] The present disclosure relates generally to telecommunications and, in particular, to measurement events in a telecommunications system.BACKGROUND

[0002] A telecommunications system can be seen as a facility that enables communication sessions between two or more entities such as user terminals, base stations and / or other nodes by providing carriers between the various entities involved in the communications path. A telecommunications system can be provided for example by means of a communication network and one or more compatible communication devices. 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 wireless telecommunications system, at least a part of a communication session between at least two stations occurs over a wireless link. Examples of wireless telecommunications systems comprise public land mobile networks (PLMN), satellite based communication systems and different wireless local networks, for example wireless local area networks (WLAN). Some wireless systems can be divided into cells, and are therefore often referred to as cellular systems.

[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 withother users. The communication device may access a carrier provided by a station, for example a base station of a cell, and transmit and / or receive communications on the carrier.

[0005] The telecommunications system and associated devices typically operate in accordance with a given standard or specification which sets out what the various entities associated with the communication system are permitted to do and how operations should be achieved. Communication protocols and / or parameters which shall be used for connection of the various entities are also typically defined. One example of a telecommunications system is the Universal Mobile Telecommunications System (UMTS). Other examples of telecommunications systems are Long-Term Evolution (LTE), LTE Advanced and the so-called 5G or New Radio (NR) networks. NR is being standardized by the 3rd Generation Partnership Project (3GPP).BRIEF SUMMARY

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

[0007] Some example implementations provide an apparatus implemented by 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: send UE capability information to a network that indicates the UE supports machine learning (ML)-based measurement event prediction, and that indicates the ML model is available in the UE and trained for the inference operation; receive an event-triggered measurement reporting configuration from the network for reporting measurement event predictions for a measurement event according to the UE capability information; perform an inference operation according to the event-triggered measurement reporting configuration in which a measurement event prediction is made using a ML model to which measurements performed by the UE are applied; and report the measurement event prediction or the measurement event to the network for evaluation.

[0008] Some example implementations provide a method performed by a user equipment (UE), the method comprising: sending UE capability information to a network that indicates the UE supports machine learning (ML)-based measurement event prediction, and that indicates the ML model is available in the UE and trained for the inference operation; receiving an event-triggered measurement reporting configuration from the network for reporting measurement event predictions for a measurement event according to the UE capability information; performing an inference operation according to the event-triggered measurement reporting configuration in which a measurement event prediction is made using a ML model to which measurements performed by the UE are applied; and reporting the measurement event prediction or the measurement event to the network for evaluation.

[0009] Some example implementations provide a computer-readable storage medium that is non-transitory and has instructions stored therein that, in response to execution by at least one processing circuitry, causes an apparatus implemented by a user equipment (UE) to at least: send UE capability information to a network that indicates the UE supports machine learning (ML)-based measurement event prediction, and that indicates the ML model is available in the UE and trained for the inference operation; receive an event-triggered measurement reporting configuration from the network for reporting measurement event predictions for a measurement event according to the UE capability information; perform an inference operation according to the event-triggered measurement reporting configuration in which a measurement event prediction is made using a ML model to which measurements performed by the UE are applied; and report the measurement event prediction or the measurement event to the network for evaluation.

[0010] Some example implementations provide an apparatus implemented by 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: send UE capability information to a network that indicates the UE supports machine learning (ML)-based measurement event prediction, and that indicates the ML model is available in the UE and trained for the inference operation; receive an event-triggered measurementreporting configuration from the network for reporting measurement event predictions for a measurement event according to the UE capability information; perform an inference operation according to the event-triggered measurement reporting configuration in which a measurement event prediction is made using a ML model to which measurements performed by the UE are applied; and send a layer 3 (L3) measurement report, user assistance information (UAI) or uplink control information (UCI) to the network to report the measurement event prediction or the measurement event for evaluation.

[0011] Some example implementations provide a method performed by a user equipment (UE), the method comprising: sending UE capability information to a network that indicates the UE supports machine learning (ML)-based measurement event prediction, and that indicates the ML model is available in the UE and trained for the inference operation; receiving an event-triggered measurement reporting configuration from the network for reporting measurement event predictions for a measurement event according to the UE capability information; performing an inference operation according to the event-triggered measurement reporting configuration in which a measurement event prediction is made using a ML model to which measurements performed by the UE are applied; and sending a layer 3 (L3) measurement report, user assistance information (UAI) or uplink control information (UCI) to the network to report the measurement event prediction or the measurement event for evaluation.

[0012] Some example implementations provide a computer-readable storage medium that is non-transitory and has instructions stored therein that, in response to execution by at least one processing circuitry, causes an apparatus implemented by a user equipment (UE) to at least: send UE capability information to a network that indicates the UE supports machine learning (ML)-based measurement event prediction, and that indicates the ML model is available in the UE and trained for the inference operation; receive an event-triggered measurement reporting configuration from the network for reporting measurement event predictions for a measurement event according to the UE capability information; perform an inference operation according to the event-triggered measurement reporting configuration in which a measurement event prediction is made using a ML model to which measurements performed by the UE are applied; and send a layer 3 (L3) measurement report, user assistance information (UAI) or uplink controlinformation (UCI) to the network to report the measurement event prediction or the measurement event for evaluation.

[0013] Some example implementations provide an apparatus implemented by 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: send UE capability information to a network that indicates the UE supports machine learning (ML)-based measurement event prediction, and that indicates the ML model is available in the UE and trained for the inference operation; receive an event-triggered measurement reporting configuration from the network for reporting measurement event predictions for a measurement event according to the UE capability information; perform an inference operation according to the event-triggered measurement reporting configuration in which a measurement event prediction is made using a ML model to which measurements performed by the UE are applied; and send a medium access control (MAC) control element (CE) to the network to report the measurement event prediction or the measurement event for evaluation.

[0014] Some example implementations provide a method performed by a user equipment (UE), the method comprising: sending UE capability information to a network that indicates the UE supports machine learning (ML)-based measurement event prediction, and that indicates the ML model is available in the UE and trained for the inference operation; receiving an event-triggered measurement reporting configuration from the network for reporting measurement event predictions for a measurement event according to the UE capability information; performing an inference operation according to the event-triggered measurement reporting configuration in which a measurement event prediction is made using a ML model to which measurements performed by the UE are applied; and sending a medium access control (MAC) control element (CE) to the network to report the measurement event prediction or the measurement event for evaluation.

[0015] Some example implementations provide a computer-readable storage medium that is non-transitory and has instructions stored therein that, in response to execution by at least one processing circuitry, causes an apparatus implemented by a user equipment(UE) to at least: send UE capability information to a network that indicates the UE supports machine learning (ML)-based measurement event prediction, and that indicates the ML model is available in the UE and trained for the inference operation; receive an event-triggered measurement reporting configuration from the network for reporting measurement event predictions for a measurement event according to the UE capability information; perform an inference operation according to the event-triggered measurement reporting configuration in which a measurement event prediction is made using a ML model to which measurements performed by the UE are applied; and send a medium access control (MAC) control element (CE) to the network to report the measurement event prediction or the measurement event for evaluation.

[0016] Some example implementations provide an apparatus implemented by 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: send UE capability information to a network that indicates the UE supports machine learning (ML)-based measurement event prediction, and that indicates the ML model is available in the UE and trained for the inference operation; receive an event-triggered measurement reporting configuration from the network for reporting measurement event predictions for a measurement event according to the UE capability information; perform an inference operation according to the event-triggered measurement reporting configuration in which a measurement event prediction is made using a ML model to which measurements performed by the UE are applied; and send a dedicated message to the network to report the measurement event prediction or the measurement event for evaluation.

[0017] Some example implementations provide a method performed by a user equipment (UE), the method comprising: sending UE capability information to a network that indicates the UE supports machine learning (ML)-based measurement event prediction, and that indicates the ML model is available in the UE and trained for the inference operation; receiving an event-triggered measurement reporting configuration from the network for reporting measurement event predictions for a measurement event according to the UE capability information; performing an inference operation according to the event-triggered measurement reporting configuration in which a measurementevent prediction is made using a ML model to which measurements performed by the UE are applied; and sending a dedicated message to the network to report the measurement event prediction or the measurement event for evaluation.

[0018] Some example implementations provide a computer-readable storage medium that is non-transitory and has instructions stored therein that, in response to execution by at least one processing circuitry, causes an apparatus implemented by a user equipment (UE) to at least: send UE capability information to a network that indicates the UE supports machine learning (ML)-based measurement event prediction, and that indicates the ML model is available in the UE and trained for the inference operation; receive an event-triggered measurement reporting configuration from the network for reporting measurement event predictions for a measurement event according to the UE capability information; perform an inference operation according to the event-triggered measurement reporting configuration in which a measurement event prediction is made using a ML model to which measurements performed by the UE are applied; and send a dedicated message to the network to report the measurement event prediction or the measurement event for evaluation.

[0019] 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.

[0020] 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 followingdetailed description 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)

[0021] 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:

[0022] 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;

[0023] FIG. 2 illustrates a deployment of a PLMN, according to some example implementations;

[0024] FIG. 3 is a signaling chart of a conventional handover procedure;

[0025] FIG. 4 is a graph illustrating an A3 event;

[0026] FIG. 5 is a graph illustrating the A3 event, including trigger and cancelation conditions for the event;

[0027] FIG. 6 illustrates measurement event prediction according to direct and indirect approaches, according to various example implementations;

[0028] FIG. 7 illustrates a training module for a machine learning (ML) binary classification model on A3 measurement event prediction;

[0029] FIGS. 8 and 9 are signaling charts of a portion of a handover procedure including measurement event prediction in which a measurement event is predicted to occur (FIG. 8) and predicted to not occur (FIG. 9), according to some example implementations;

[0030] FIGS. 10 A, 10B, 10C and 10D are flowcharts illustrating various steps in a method performed by a UE, according to various example implementations; and

[0031] FIG. 11 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 allimplementations 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.

[0033] Unless specified otherwise or clear from context, references to first, second or the like should not be construed to imply a particular order. A feature described as being above another feature (unless specified otherwise or clear from context) may instead be below, and vice versa; and similarly, features described as being to the left of another feature else may instead be to the right, and vice versa. Also, while reference may be made herein to quantitative measures, values, geometric relationships or the like, unless otherwise stated, any one or more if not all of these may be absolute or approximate to account for acceptable variations that may occur, such as those due to engineering tolerances or the like.

[0034] 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.

[0035] The present disclosure discusses systems and architectures that, while specific terms may be used, are broadly applicable across various technologies. For instance, while the present disclosure may reference technologies from 3 GPP such as Global System for Mobile Communications (GSM), UMTS, LTE, LTE Advanced, 5GNR, 5GAdvanced, and 6G, the present disclosure is equally relevant to non-3GPP technologies like IEEE 802, Bluetooth, and Bluetooth Low Energy. 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) and the private entities operating these networks. Furthermore, although some examples and figures focus on radio access networks (RANs) and 3 GPP access, example implementations are applicable to any type of network access. This includes not only 5G or 6G 3GPP access but also non-3GPP access, such as wireline access, untrusted non-3GPP access, and trusted non-3GPP access using wireless access gateway function (W-AGF), non-3GPP interworking function (N3IWF), or trusted non-3GPP gateway function (TNGF) to connect to a 5G or 6G core 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. The telecommunications system generally includes one or more telecommunications networks. 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. Each of the PLMNs includes a core network (CN) 106 backbone such as the Evolved Packet Core (EPC) of LTE, the 5G core network (5GC) or the like; and each of the core networks and the Internet are coupled to one or more RANs 108, air interfaces or the like that implement one or more radio access technologies (RATs). As used herein, a “network device” refers to any suitable device at a network side of a telecommunications network. Examples of suitable network devices are described in greater detail below.

[0039] In addition, the system includes one or more radio units 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 or a further UE in a telecommunications network. 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 (IIoT device), a vehicle equipped with a vehicle-to-everything (V2X) communication technology, or the like. In some examples, as referenced by 3 GPP, the UE may be a narrowband loT (NB-IoT) device, an enhanced machine-type communication (eMTC) device, a reduced capability (RedCap) device, an ambient loT device, or the like.

[0040] In operation, these UEs 110 may be configured to connect to one or more of the RANs 108 according to their particular radio access technologies 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). The external data network may be configured to provide Internet access, operator services, 3rd party services, etc. For example, the International Telecommunication Union (ITU) has classified 5G mobile network services into three categories: enhanced mobile broadband (eMBB), ultra- reliable and low-latency communications (URLLC), and massive machine type communications (mMTC) or massive internet of things (MIoT).

[0041] Examples of radio access technologies include 3 GPP radio access technologies such as GSM, UMTS, LTE, LTE Advanced, 5GNR, 5G Advanced, and 6G. Other examples of radio access technologies 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 radio access technology may refer to any 2G, 3G, 4G, 5G, 6G or higher generation mobile communication technology and their different versions, as well as to any other wireless radio access technology that may be arranged to interwork with such a mobile communication technology to provide access to the CN 106 of a mobile network operator (MNO).

[0042] In various examples, a RAN 108 may be configured as one or more macrocells, microcells, picocells, femtocells or the like. The RAN may generally include one or more radio access nodes that are configured to interact with UEs 110. In various examples, a radio access node may be referred to as a base station (BS), access point (AP), base transceiver station (BTS), 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), or the like. The RAN may include some type of network controlling / governing entity responsible for control of the radio access nodes. The network controlling / governing entity and radio access 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, etc. The processing circuity may be associated with a memory, computer- readable storage medium or database for maintaining information required in the management functions.

[0043] A RAN 108 may be centralized or distributed. In various examples, components of a RAN may be interconnected by Ethernet, Gigabit Ethernet, Asynchronous Transfer Mode (ATM), optical fiber, dark fiber, passive wavelength division multiplexing (WDM), WDM passive optical network (WDM-PON), optical transport network (OTN), time sensitive networking (TSN) and / or any other data link layer network, possibly including radio links. The RAN may be connected to a CN 106 through one or more gateways, network functions or the like.

[0044] As will be appreciated, a PLMN 102 may be deployed in a number of different manners. In a 4GLTE deployment, the EPC is the CN 106, and the evolved UMTS terrestrial radio access network (E-UTRAN) is the RAN 108; and the E-UTRAN includes one or more eNBs (radio access nodes) configured to connect UEs 110 to the E- UTRAN to thereby access the EPC. FIG. 2 illustrates a deployment 200, such as a 5G or 6G deployment. As shown, the 5GC 202 is the CN, and the next generation (NG) radio access network (NG-RAN) 204 is the RAN; and the NG-RAN includes one or more gNBs 206 (radio access nodes) configured to connect UEs 110 to the NG-RAN to thereby access the 5GC. The term ‘gNB’ in 5G may correspond to the eNB in 4G LTE.

[0045] Some 4G LTE and 5G deployments are considered standalone (SA) deployments. Other deployments combine 4G LTE and 5G technologies, and are referred to as non-standalone (NSA) deployments. In some deployments, the E-UTRAN includes one or more ng-eNBs that are configured to communicate with the 5GC, and that may also be configured to communicate with one or more gNBs. Similarly, in another deployment, the NG-RAN may include one or more en-gNBs that are configured to communicate with the EPC, and that may also be configured to communicate with one or more eNBs. In various instances, a single UE 110, a dual-mode or multimode UE, may support multiple (two or more) RANs — thereby being configured to connect to multiple RANs, such as 4G LTE and 5G.

[0046] In various instances, a single UE 110, a dual-mode or multimode UE, may support carrier aggregation (CA), dual-connectivity (DC) or multi-connectivity (MC). In this regard, CA allows the UE to simultaneously connect to cells on multiple carriers, enabling the UE to reach higher throughputs, as well as fast-time-scale load-balancing across multiple carriers. AUE will generally have a primary cell, known as a PCell, which is typically the cell through which the UE first connects to the NG-RAN 204. The RAN (typically via the PCell) may provide the UE additional configuration information to enable it to simultaneously connect to additional cells on carriers other than the PCell, which are known as the UE’s secondary cells or SCells.

[0047] The PCell radio access node may be referred to as a master node (MN), and the SCell radio access node may be referred to as a secondary node (SN). Relatedly, a master cell group (MCG) refers to a group of serving cells associated with the MN, andthe MCG includes PCell). A secondary cell group (SCG) refers to a group of serving cells associated with the SN, and the SCG includes a primary cell referred to as the primary secondary cell (PSCell). A special cell (SpCell) refers to the PCell of the MCG or the PSCell of the SCG

[0048] In some deployments, such as deployment 200, operations of the gNB 206 or other radio access node may be carried out, at least partly, in a central / centralized unit (CU), such as a server, host or node, operationally coupled to a distributed unit (DU), such as a radio head / node. It is also possible that node operations may be distributed among a plurality of servers, hosts or nodes. It should also be understood that the distribution of work between 5GC 202 (or other CN) operations and gNB (or other radio access node) operations may vary depending on implementation.

[0049] A 5G network architecture may be based on a so-called CU-DU split. One gNB-CU (central node) may control one or more gNB-DUs. 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 (also called DU) may include, for example, a radio link control (RLC) layer, medium access control (MAC) layer and a physical (PHY) layer, whereas the gNB-CU (also called a CU) may include the layers above the RLC layer, such as a packet data convergence protocol (PDCP) layer, a radio resource control (RRC) layer, and an internet protocol (IP) layer. Other functional splits are also possible. It is considered that a skilled person is familiar with the open systems interconnection (OSI) model and the functionalities within each layer.

[0050] In some example implementations, the server or CU 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, and the boundary where the responsibility is shifted between the CU and the DU may be selected according to implementation.

[0051] Although only one gNB 206 is shown in FIG. 2, the deployment may comprise multiple gNBs, and at least some of the gNBs may be connected to one anotherby a network interface, such as an Xn interface. Similarly, the gNBs may be connected to the 5GC 202 by a network interface. In 5GNR, the network interface between a gNB and the 5GC is referred to as the NG interface, which is a network interface between the gNB and an access and mobility management function (AMF) of the 5GC. These and other network interfaces may support the exchange of signaling messages between network entities. The signaling messages may be formatted according to an application layer protocol, such as the NG application protocol (NGAP) for the NG interface between the gNB and the 5GC.

[0052] 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 gNBs 206. To continuously monitor the UE’s radio link condition toward a serving radio cell provided by a serving gNB, 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 gNB periodically and / or whenever a configured measurement event is met / fulfilled. These measurements may then be evaluated at the gNB, and may result in a handover (HO) of the UE from the serving radio cell provided by the serving gNB (a source gNB, or more generally a source node) to a new radio cell provided by a target gNB (a target gNB, or more generally a target node).

[0053] FIG. 3 is a signaling chart 300 of a conventional (inter-node) handover procedure involving a UE 110, a source gNB 206A (source node) that is currently serving (connected to) the UE, and one or more candidate gNBs that are potential target gNBs 206B for handover of the UE. As shown, the UE at step 301 may be configured, such as by an RRC reconfiguration, 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 gNB(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 gNB, the source gNB may be configured to derive information, such as a numberof actively connected UEs, number of RRC connections, number of physical resource blocks (PRBs) in use, the transport network load (TNL) capacity, or the like.

[0054] The source gNB 206A may at step 303 decide to initiate the handover procedure, and initiate a handover preparation in which the source gNB at step 304 sends (transmits) a handover request message with a current configuration of the UE 110 towards the candidate (target) gNB 206B controlling a target radio cell. In some cases, the handover request message may be sent over an Xn interface between the source gNB and the candidate gNB, 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 gNB may be accessed over AMF, such as according to a procedure referred to as NGAP handover.

[0055] The candidate (target) gNB 206B 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-RNU), 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 gNB, or the like. The source gNB 206A may then at step 306 send (transmit) a handover command message that comprises the configuration for the target radio cell of the target gNB towards the UE.

[0056] 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 gNB 206B, and thereafter complete the handover procedure. As shown, in some examples, the handover command may be provided at step 306 by a RRC reconfiguration; and in some of these examples, the handover procedure may comprise a random access procedure for handover, comprising downlink (DL) and uplink (UL) synchronization and random access channel (RACH) access to the target gNB, and random access response (RAR) message from the target gNB. The UE may then send (transmit) a RRC reconfiguration complete message to the target gNB to complete the handover procedure.

[0057] In many conventional handover and other mobility scenarios, the decision whether or not to handover a UE 110 is taken by the serving gNB 206 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).

[0058] In an ideal case, the serving gNB 206 may allow the UE 110 to report serving cell and neighbor cell signal quality and trigger the handover with a single measurement, but in practice this can create overload conditions due to unnecessary ping pong handovers. As solution to avoid such situation, 3 GPP 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 gNB.

[0059] In 3 GPP, the following events are currently defined for 5GNR.Event Al : (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 B 1 : (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)

[0060] A handover procedure may be initiated if the defined conditions about the received signal quality are satisfied according to an event. FIG. 4 is a graph illustrating an A3 event. In this context, a handover may begin within the A3 event if the quality of received signal from a neighbor gNB 206 is better than that of serving gNB plus a predefined threshold. Also shown is a time-to-trigger (TTT) interval, which is considered asthe 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 gNB. In practice, the TTT is often defined by the MNO to prevent the ping-pong handovers.

[0061] An event may also be specified with trigger (entering) and cancelation (leaving) conditions. FIG. 5 is a graph illustrating the trigger and cancelation conditions for the A3 event. As shown in FIGS. 4 and 5, the UE may consider the triggering condition for the A3 event to be satisfied when condition A3- 1 is fulfilled, and consider the cancelation condition for the A3 event to be satisfied when condition A3 -2 is fulfilled. The A3-1 (triggering condition) and A3 -2 (cancelation condition) may be expressed as inequalities as follows:Inequality A3-1 (Triggering condition)Mn + Ofh + Ocn - Hys > Mp + Ofp + Ocp + Off Inequality A3 -2 (Cancelation condition)Mn + Ofh + Ocn - Hys < Mp + Ofp + Ocp + OffIn the respective conditions, Mn is the measurement result of the neighboring cell, not taking into account any offsets. Ofn is thee 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.

[0062] For Release 19, 3 GPP 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 event prediction, including measurement events prediction (UE-sided model).

[0063] Example implementations of the present disclosure provide solutions that enable the use of past measurements and events that have happened to build AI / ML models (at times more simply referred to as ML models) to predict measurement events such as A3 events. In addition to measurement event predictions, some exampleimplementations also provide procedures, coordination between the UE 110 and network (e.g., gNB 206), and related signaling to enhance the handover process. The solutions of some example implementations may lead to fewer radio link failures (RLF), reduction of unnecessary handovers and ping-pong effects. The solutions may also enable a reduction in the TTT, which may also lead to improvements in the handover process.

[0064] According to some example implementations, the handover process may be improved for a measurement event prediction that includes a prediction indicating either the measurement event is predicted to occur (event prediction = true) or not occur (event prediction = false). In some cases, then, the ML model may predict a measurement event will occur. In other cases, the ML model may predict that the measurement event will not occur.

[0065] A measurement event prediction may be made in a number of different manners. Two approaches according to some example implementations are shown in FIG. 6, namely, a direct (1-step) approach 602 and an indirect (2-step) approach 604. In 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 (e.g., cell-level layer 3 (L3) measurements) performed by the UE 110 to a measurement event prediction.

[0066] In the indirect approach 604, 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 110 may be mapped to measurement predictions from which a measurement event prediction may be determined. In either the direct or indirect approach, the focus is on UE-side measurement event prediction.

[0067] The first step in enabling the measurement event prediction is data collection for ML model training. A sequence for training data collection will now be described. Although not otherwise referenced, it should be understood, that in the sequence, training data may also be collected during inference since the ground truth will be known. Thesequence according to some examples is described specifically for collecting training data, where batch reporting may be used to reduce the required signaling.

[0068] According to the sequence for training data collection of some example implementations, the UE 110 may at step 1 provide the gNB 206 (network) UE capability information that indicates the UE has the capability to collect data and use the measurement event prediction mechanism. In some examples, the UE capability information may include information about a required or preferred measurement configuration for the measurement event prediction.

[0069] The gNB 206 may prepare a configuration based on the UE capability information, and the gNB may at a step 2 send the configuration to the UE 110. The configuration may include, for example, measurement objects to measure. The configuration may include a measurement reporting configuration which may include a measurement event configuration. In the direct approach, this measurement event configuration may be used for labeling. The configuration may also include a trigger condition for making the measurement event prediction, which may also be used to determine the training data collection. This may be, for example, the entering condition of the configured measurement event. The configuration may further include a prediction window, which in some examples may be aligned to the TTT of the configured measurement event.

[0070] The UE 110 may at a step 3 collect the measurements based on the selected approach (direct or indirect) and the configuration. In the case of the direct approach, the UE may keep a buffer of time series of measurements, and store the time series of measurements only when the trigger condition is met. In the case of the indirect approach, a similar method may be applied, or the training data for the measurement event prediction may be collected separately.

[0071] In a step 4 of the sequence for training data collection, the collected measurements may be labeled according to a measurement event outcome for the collected measurements. In this regard, the UE 110 may send and record a measurement event report when the trigger condition is maintained for the duration of the TTT, and measurement event therefore occurs. If the trigger condition is not maintained for the duration of the TTT, and the cancelation condition is met, the UE may record that the exitcondition is met. In either case, the UE may at a step 5 send the collected and labeled measurements as training data to a ML training host, which may use the training data to build a ML model.

[0072] FIG. 7 illustrates a training module 700 for a ML binary classification model on A3 measurement event prediction. As shown, input data 702 includes a measurement window for layer 1 (LI) / L3 measurement data collection. Here, the measurement data may be prepared for the ML model. In one example, L3 cell level RSRP (measured from all the configured gNBs) from a prior 1000 millisecond (ms) time window may be used for input. The measurement data collection may be triggered when A3 event is entered (or TTT triggered). The input data also includes a preprocessing at which raw measurement data may be cleaned and transformed, and relevant features extracted. In particular, for example, interpolating missing measurement values may be interpolated and added before training data is fed into the ML model.

[0073] The ML model is shown next. In the direct approach, for example, a random forest classifier 704 may be used to handle the binary classification task for the current use case, namely, A3 event prediction. Corresponding hyper-parameters for the random forest classifier may include, for example, a number of trees in the forest, a maximum number of features considered for splitting a node, a maximum number of levels in each decision tree, a method for sampling data points, etc. A grid search may be used for hyper parameters optimization.

[0074] In the indirect approach, for example, a regression model may be trained to predict future measurement values from a time series of past measurements. This may include, for example, linear regression or recurrent neural networks. A measurement event condition may be applied in a second step on top of the predicted measurements to predict the occurrence of the measurement event. The regression model may be validated based on the collected ground truth measurement events.

[0075] The training module 700 as shown also includes an output window 706. Here, the ML model may output the reporting measurement event prediction which indicates whether a measurement event is predicted to occur (true) or predicted to not occur (false). In particular, the reporting event prediction may indicate true when an A3 event ispredicted to occur within the configured prediction window, or indicate false when no A3 event is predicted to occur within the configured prediction window.

[0076] In the inference phase, the ML model for measurement event prediction is trained and deployed in the UE 110 to make predictions. In some examples, the UE may send UE capability information to the network (e.g., gNB 206) that indicates the UE supports ML-based measurement event prediction, and that indicates the ML model is available in the UE and trained for an inference operation. More specifically, for example, the UE capability information may indicate supported trigger condition(s), supported observation window(s), supported prediction window(s), and / or the supported measurement event configuration(s) that can be predicted, e.g., type, offset, hysteresis, TTT

[0077] In the direct approach, in some examples, the UE 110 may only be able to predict measurement events based on the measurement event configurations it was trained with. In the indirect approach, the measurement event prediction may be made by applying configured measurement event configuration on top of predicted measurements, which may allow for configuring different measurement event configurations for the predictions without training an ML model for each configuration. The UE may still indicate, however, measurement event configurations that the approach was validated with.

[0078] In some examples, the supported measurement event configuration(s) may include one or more accuracy metrics, such as a confusion matrix of the model performance. In this regard, the confusion matrix may be used to derive metrics, such as precision, recall and F-l score. In other examples, accuracy metric(s) may be directly communicated by the UE to the network through signaling. Examples of this, include, for example, an L3 measurement report that includes the accuracy metric(s), user assistance information (UAI), or uplink control information (UCI).

[0079] According to the UE capability information, the network (e.g., gNB 206) may send the UE 110 an event- triggered measurement reporting configuration to configure the UE to report measurement event predictions. The event-triggered measurement reporting configuration may include, for example, a trigger condition for making a prediction, a reporting condition (e.g., a confidence threshold to control the true / false positive rate),the observation window, the prediction window, and / or the predicted measurement event configuration. In the direct approach, the predicted measurement event configuration may be selected among those indicated in the UE capability information. In the indirect approach, the measurement event configuration may be explicitly configured (e.g., type, offset, hysteresis, TTT etc.).

[0080] The UE 110 may perform the inference operation according to the event according to the event-triggered measurement reporting configuration in which measurement event prediction(s) are made using the ML model to which measurements performed by the UE are applied. The UE may report the measurement event predict! on(s) or the measurement event to the network (e.g., gNB 206) for evaluation. In some examples, the UE may send L3 measurement report(s), UAI or UCI to report the measurement event prediction(s). In other examples, the UE may send MAC CE(s) to report the measurement event prediction(s). And in yet other examples, the UE may send dedicated message(s) to report the measurement event prediction(s).

[0081] As indicated above, a measurement event prediction may include a prediction that indicates whether the measurement event (e.g., A3 event) is predicted to occur (true) or predicted to not occur (false). In some examples, the UE 110 may also send the network a confidence metric about the accuracy of the prediction, such as in the form of a probability.

[0082] In some examples, the UE 110 may also include an indication of a time (e.g., a time stamp) at which the measurement event is predicted to occur. The UE may send this indication and other appropriate metrics in a number of different manners, like the measurement event prediction. In some examples, the prediction and appropriate metrics may be sent in the L3 measurement report, the UAI or the UCI. In other examples, the prediction and appropriate metrics may be sent using MAC CE. And in yet other examples, the prediction and appropriate metrics may be sent using a dedicated (new) message for the measurement event prediction.

[0083] In some examples, the UE 110 may (by network configuration) wait until a triggering condition (e.g., A3-1) for the measurement event is satisfied (determined based on evaluation of measurements performed by the UE), when the measurement event is predicted to occur. The UE may be triggered by the triggering condition to start a shorterTTT than a TTT associated with the measurement event. In these examples, the TTT associated with the measurement event may be provided by a predicted measurement event UE-side (PME-U) configuration. The UE may then report the measurement event when the shorter TTT expires (the reporting triggered by expiration of the shorter TTT).

[0084] In some examples, the UE 110 may determine that the triggering condition (e.g., A3-1) for the measurement event (e.g., A3) is satisfied based on evaluation of measurements performed by the UE. The UE may start a TTT associated with the measurement event when the prediction indicates the measurement event is predicted to not occur, or a shorter TTT when the prediction indicates the measurement event is predicted to occur. The UE may then report the measurement event or the measurement event prediction when the TTT or the shorter TTT expires.

[0085] To further illustrate some example implementations, FIG. 8 is a signaling chart 800 of a portion of a handover procedure including measurement event prediction in which a measurement event is predicted to occur, according to some example implementations. As shown, the UE 110 may at step 801 send PME-U capability to the source gNB 206A. The PME-U capability may include UE capability information that indicates the UE supports ML-based measurement event prediction, and that indicates the ML model is available in the UE and trained for an inference operation. In return, the source gNB may at step 801 send a PME-U configuration to the UE. The PME-U configuration may include an event-triggered measurement reporting configuration to configure the UE to report measurement event predictions.

[0086] The UE 110 may at steps 803 and 804 take and buffer measurements, and determine that that a triggering condition for the measurement event is satisfied. The UE may at step 805 perform an inference operation during which a prediction is made that the measurement event is predicted to occur (true). The UE may be triggered by the measurement event to start a shorter TTT than a TTT 812 associated with the measurement event. The UE may then at step 806 report the measurement event when the shorter TTT expires. The UE may report the measurement event one or more times.

[0087] The source gNB 206A may at step 807 decide to initiate the handover procedure based on the measurement report, and initiate a handover preparation in which the source gNB at step 808 sends a handover request message with a currentconfiguration of the UE 110 towards the candidate (target) gNB 206B controlling a target radio cell. The candidate (target) gNB may perform admission control, and at step 809 provide a handover request acknowledgement (ACK) message comprising a configuration of initial access resources for the UE in case of acceptance. The source gNB 206A may then at step 810 send a handover command message that comprises the configuration for the target radio cell of the target gNB towards the UE. The handover may then be executed, such as in the manner described above in FIG. 3.

[0088] FIG. 9 is a signaling chart 900 of a portion of a handover procedure including measurement event prediction in which a measurement event is predicted to occur, according to some example implementations. In this case, the UE may at step 905 perform an inference operation during which a prediction is made that the measurement event is predicted to occur (false). The UE may be triggered by the measurement event to start the TTT 812 associated with the measurement event. In the event the triggering condition for the measurement event is maintained for the duration of the TTT, the UE may at step 806 report the measurement event when the TTT expires. The procedure may then continue as described above.

[0089] FIGS. 10A- 10D are flowcharts illustrating various steps in a method 1000 performed by a user equipment (UE), according to various example implementations. The method includes sending at block 1002 UE capability information to a network that indicates the UE supports machine learning (ML)-based measurement event prediction, and that indicates the ML model is available in the UE and trained for the inference operation. The method includes receiving an event-triggered measurement reporting configuration from the network for reporting measurement event predictions for a measurement event according to the UE capability information, as shown at block 1004 of FIG. 10A. The method includes performing an inference operation according to the event-triggered measurement reporting configuration in which a measurement event prediction is made using a ML model to which measurements performed by the UE are applied, as shown at block 1006. And the method includes reporting the measurement event prediction or the measurement event to the network for evaluation, as shown at block 1008. In some examples, a layer 3 (L3) measurement report, user assistance information (UAI) or uplink control information (UCI) is sent to the network to report themeasurement event prediction or the measurement event for evaluation. In other examples, a medium access control (MAC) control element (CE) is sent to the network to report the measurement event prediction or the measurement event for evaluation.

[0090] In some examples, the method 1000 further includes performing measurements according to the event-triggered measurement configuration, as shown at block 1010 of FIG. 10B. In some of these examples, the method also includes evaluating the measurements to make a determination whether the measurement event is fulfilled, as shown at block 1012. And the method includes collecting training data including the measurements and the determination for training the ML model to perform the inference operation, as shown at block 1014.

[0091] In some examples, the UE capability information also indicates at least one of one or more trigger conditions supported for the inference operation; one or more observations windows supported for measurements for the inference operation; one or more prediction windows supported for the inference operation; or one or more measurement event configurations supported by the ML model.

[0092] In some examples, the event-triggered measurement reporting configuration indicates at least one of a trigger condition for performing the inference operation; an observation window for measurements for the inference operation; a prediction window for the inference operation; 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 outcome of the inference operation.

[0093] In some examples, the measurement event prediction includes a prediction indicating whether the measurement event is predicted to occur or not occur.

[0094] In some examples, the prediction indicates the measurement event is predicted to occur, and the measurement event prediction is reported (e.g., L3 measurement report, UAI, UCI, MAC CE) to the network with an indication of a time at which the measurement event is predicted to occur.

[0095] In some examples, the prediction indicates the measurement event is predicted to occur. In some of these examples, the method 1000 further includes making a determination that a triggering condition for the measurement event has occurred is satisfied based on an evaluation of measurements performed by the UE, as shown atblock 1016 of FIG. 10C. The method includes starting a shorter time-to-trigger (TTT) than a TTT associated with the measurement event triggered by the determination, as shown at block 1018. And reporting the measurement event prediction or the measurement event (e.g., L3 measurement report, UAI, UCI, MAC CE) at block 1008 includes reporting the measurement event to the network triggered by expiration of the shorter TTT.

[0096] In some examples, the prediction indicates the measurement event is predicted to not occur. In some of these examples, the method 1000 further includes starting a time- to-trigger (TTT) associated with the measurement event triggered by the prediction, as shown at block 1020 of FIG. 10D. And reporting the measurement event prediction or the measurement event (e.g., L3 measurement report, UAI, UCI, MAC CE) at block 1008 includes reporting the measurement event to the network triggered by expiration of the TTT.

[0097] According to example implementations of the present disclosure, a telecommunications system 100 or PLMN 102, and its components such as a UE 110, CN 106, RAN 108, 5GC 202 and / or gNB 206, 206A, 206B, 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.

[0098] According to some example implementations, at least some of the method 1000 described with respect to FIGS. 10A-10D 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.

[0099] FIG. 11 illustrates an apparatus 1100 in which means for performing various functions 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. Generally, an apparatus of example implementations of the present disclosure may comprise, include or be embodied in one or more fixed or portable electronic devices. Examples of suitable electronic devices include a wearable computer, mobile phone, portable computer, desktop computer, workstation computer, server (server computer) or the like. The apparatus may include one or more of each of a number of components such as, for example, processing circuitry 1102 connected to computer-readable storage medium or other memory 1104.

[0100] The processing circuitry 1102 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 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 1104 (of the same or another apparatus).

[0101] The processing circuitry 1102 may be a number of processors, a multi-core processor or some other type of processor, 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 ASICs, 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.

[0102] The memory 1104 is generally any piece of computer hardware that is capable of storing information such as, for example, data, computer programs, instructions 1106 (e.g., computer-readable program code) and / or other suitable information either on a temporary basis and / or a permanent basis. The memory may include volatile and / or nonvolatile 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.

[0103] The memory 1104 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.

[0104] In addition to the memory 1104 (e.g., computer-readable storage medium), the processing circuitry 1102 may also be connected to one or more interfaces for displaying, transmitting and / or receiving information. The interfaces may include a communications interface 1108 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.

[0105] The user interfaces may include a display 1110 and / or one or more user input interfaces 1112. The display may be configured to present or otherwise displayinformation 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 further include one or more interfaces for communicating with peripherals such as printers, scanners or the like.

[0106] Execution of the instructions 1106 by the processing circuitry 1102, or storage of the instructions in the memory 1104, supports combinations of operations for implementing example implementations of the present disclosure. In this manner, an apparatus 1100 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.

[0107] 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.

[0108] As will be appreciated, any suitable instructions may be loaded onto a computer, 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 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, processing circuitry or other programmable apparatus to configure the computer, processing circuitry or other programmable apparatus to execute operations to be performed on or by the computer, processing circuitry or other programmable apparatus.

[0109] 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 example implementations, 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, processing circuitry or other programmable apparatus provide operations for implementing functions described herein.

[0110] As explained above and reiterated below, the present disclosure includes, without limitation, the following example implementations.

[0111] Clause 1. A method performed by a user equipment (UE), the method comprising: sending UE capability information to a network that indicates the UE supports machine learning (ML)-based measurement event prediction, and that indicates the ML model is available in the UE and trained for the inference operation; receiving an event-triggered measurement reporting configuration from the network for reporting measurement event predictions for a measurement event according to the UE capabilityinformation; performing an inference operation according to the event-triggered measurement reporting configuration in which a measurement event prediction is made using a ML model to which measurements performed by the UE are applied; and reporting the measurement event prediction or the measurement event to the network for evaluation.

[0112] Clause 2. The method of clause 1, wherein the method further comprises: performing measurements according to the event-triggered measurement configuration; evaluating the measurements to make a determination whether the measurement event is fulfilled; and collecting training data including the measurements and the determination for training the ML model to perform the inference operation.

[0113] Clause 3. The method of clause 1 or clause 2, wherein the UE capability information also indicates at least one of: one or more trigger conditions supported for the inference operation; one or more observations windows supported for measurements for the inference operation; one or more prediction windows supported for the inference operation; or one or more measurement event configurations supported by the ML model.

[0114] Clause 4. The method of any of clauses 1 to 3, wherein the event-triggered measurement reporting configuration indicates at least one of: a trigger condition for performing the inference operation; an observation window for measurements for the inference operation; a prediction window for the inference operation; 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 outcome of the inference operation.

[0115] Clause 5. The method of any of clauses 1 to 4, wherein the measurement event prediction includes a prediction indicating whether the measurement event is predicted to occur or not occur.

[0116] Clause 6. The method of clause 5, wherein the prediction indicates the measurement event is predicted to occur, and the measurement event prediction is reported to the network with an indication of a time at which the measurement event is predicted to occur.

[0117] Clause 7. The method of clause 5 or clause 6, wherein the prediction indicates the measurement event is predicted to occur, and the method further comprises: making a determination that a triggering condition for the measurement event is satisfied based onan evaluation of measurements performed by the UE; and starting a shorter time-to- trigger (TTT) than a TTT associated with the measurement event triggered by the determination, and wherein reporting the measurement event prediction or the measurement event includes reporting the measurement event to the network triggered by expiration of the shorter TTT.

[0118] Clause 8. The method of any of clauses 5 to 7, wherein the prediction indicates the measurement event is predicted to not occur, and the method further comprises starting a time-to-trigger (TTT) associated with the measurement event triggered by the prediction, and wherein reporting the measurement event prediction or the measurement event includes reporting the measurement event to the network triggered by expirati on of the TTT.

[0119] Clause 9. An 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 perform the method of any of clauses 1 to 8.

[0120] Clause 10. An apparatus comprising means for performing the method of any of clauses 1 to 8.

[0121] Clause 11. 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 clauses 1 to 8.

[0122] Clause 12. A computer-readable storage medium comprising instructions that, in response to execution by at least one processing circuitry, causes an apparatus to perform the method of any of clauses 1 to 8.

[0123] Clause 13. A computer program comprising instructions that, in response to execution by at least one processing circuitry, causes an apparatus to perform the method of any of clauses 1 to 8.

[0124] Clause 14. A method performed by a user equipment (UE), the method comprising: sending UE capability information to a network that indicates the UE supports machine learning (ML)-based measurement event prediction, and that indicates the ML model is available in the UE and trained for the inference operation; receiving an event-triggered measurement reporting configuration from the network for reportingmeasurement event predictions for a measurement event according to the UE capability information; performing an inference operation according to the event-triggered measurement reporting configuration in which a measurement event prediction is made using a ML model to which measurements performed by the UE are applied; and sending a layer 3 (L3) measurement report, user assistance information (UAI) or uplink control information (UCI) to the network to report the measurement event prediction or the measurement event for evaluation.

[0125] Clause 15. The method of clause 14, wherein the method further comprises: performing measurements according to the event-triggered measurement configuration; evaluating the measurements to make a determination whether the measurement event is fulfilled; and collecting training data including the measurements and the determination for training the ML model to perform the inference operation.

[0126] Clause 16. The method of clause 14 or clause 15, wherein the UE capability information also indicates at least one of: one or more trigger conditions supported for the inference operation; one or more observations windows supported for measurements for the inference operation; one or more prediction windows supported for the inference operation; or one or more measurement event configurations supported by the ML model.

[0127] Clause 17. The method of any of clauses 14 to 16, wherein the event-triggered measurement reporting configuration indicates at least one of: a trigger condition for performing the inference operation; an observation window for measurements for the inference operation; a prediction window for the inference operation; 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 outcome of the inference operation.

[0128] Clause 18. The method of any of clauses 14 to 17, wherein the measurement event prediction includes a prediction indicating whether the measurement event is predicted to occur or not occur.

[0129] Clause 19. The method of clause 18, wherein the prediction indicates the measurement event is predicted to occur, and the L3 measurement report, the UAI or the UCI includes an indication of a time at which the measurement event is predicted to occur.

[0130] Clause 20. The method of clause 18 or clause 19, wherein the prediction indicates the measurement event is predicted to occur, and the method further comprises: making a determination that a triggering condition for the measurement event is satisfied based on an evaluation of measurements performed by the UE; and starting a shorter time-to-trigger (TTT) than a TTT associated with the measurement event triggered by the determination, and wherein the L3 measurement report, the UAI or the UCI is sent to the network to report the measurement event, and the L3 measurement report, the UAI or the UCI is triggered by expiration of the shorter TTT.

[0131] Clause 21. The method of any of clauses 18 to 20, wherein the prediction indicates the measurement event is predicted to not occur, and the method further comprises starting a time-to-trigger (TTT) associated with the measurement event triggered by the prediction, and wherein the L3 measurement report, the UAI or the UCI is sent to the network to report the measurement event, and the L3 measurement report, the U AI or the UCI is triggered by expiration of the TTT.

[0132] Clause 22. An 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 perform the method of any of clauses 14 to 21.

[0133] Clause 23. An apparatus comprising means for performing the method of any of clauses 14 to 21.

[0134] Clause 24. 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 clauses 14 to 21.

[0135] Clause 25. A computer-readable storage medium comprising instructions that, in response to execution by at least one processing circuitry, causes an apparatus to perform the method of any of clauses 14 to 21.

[0136] Clause 26. A computer program comprising instructions that, in response to execution by at least one processing circuitry, causes an apparatus to perform the method of any of clauses 14 to 21.

[0137] Clause 27. A method performed by a user equipment (UE), the method comprising: sending UE capability information to a network that indicates the UEsupports machine learning (ML)-based measurement event prediction, and that indicates the ML model is available in the UE and trained for the inference operation; receiving an event-triggered measurement reporting configuration from the network for reporting measurement event predictions for a measurement event according to the UE capability information; performing an inference operation according to the event-triggered measurement reporting configuration in which a measurement event prediction is made using a ML model to which measurements performed by the UE are applied; and sending a medium access control (MAC) control element (CE) to the network to report the measurement event prediction or the measurement event for evaluation.

[0138] Clause 28. The method of clause 27, wherein the method further comprises: performing measurements according to the event-triggered measurement configuration; evaluating the measurements to make a determination whether the measurement event is fulfilled; and collecting training data including the measurements and the determination for training the ML model to perform the inference operation.

[0139] Clause 29. The method of clause 27 or clause 28, wherein the UE capability information also indicates at least one of: one or more trigger conditions supported for the inference operation; one or more observations windows supported for measurements for the inference operation; one or more prediction windows supported for the inference operation; or one or more measurement event configurations supported by the ML model.

[0140] Clause 30. The method of any of clauses 27 to 29, wherein the event-triggered measurement reporting configuration indicates at least one of: a trigger condition for performing the inference operation; an observation window for measurements for the inference operation; a prediction window for the inference operation; 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 outcome of the inference operation.

[0141] Clause 31. The method of any of clauses 27 to 30, wherein the measurement event prediction includes a prediction indicating whether the measurement event is predicted to occur or not occur.

[0142] Clause 32. The method of clause 31, wherein the prediction indicates the measurement event is predicted to occur, and the MAC CE includes an indication of a time at which the measurement event is predicted to occur.

[0143] Clause 33. The method of clause 31 or clause 32, wherein the prediction indicates the measurement event is predicted to occur, and the method further comprises: making a determination that a triggering condition for the measurement event is satisfied based on an evaluation of measurements performed by the UE; and starting a shorter time-to-trigger (TTT) than a TTT associated with the measurement event triggered by the determination, and wherein the MAC CE is sent to the network to report the measurement event, and the MAC CE is triggered by expiration of the shorter TTT.

[0144] Clause 34. The method of any of clauses 31 to 33, wherein the prediction indicates the measurement event is predicted to not occur, and the method further comprises starting a time-to-trigger (TTT) associated with the measurement event triggered by the prediction, and wherein the MAC CE is sent to the network to report the measurement event, and the MAC CE is triggered by expiration of the TTT.

[0145] Clause 35. An 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 perform the method of any of clauses 27 to 34.

[0146] Clause 36. An apparatus comprising means for performing the method of any of clauses 27 to 34.

[0147] Clause 37. 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 clauses 27 to 34.

[0148] Clause 38. A computer-readable storage medium comprising instructions that, in response to execution by at least one processing circuitry, causes an apparatus to perform the method of any of clauses 27 to 34.

[0149] Clause 39. A computer program comprising instructions that, in response to execution by at least one processing circuitry, causes an apparatus to perform the method of any of clauses 27 to 34.

[0150] Clause 40. A method performed by a user equipment (UE), the method comprising: sending UE capability information to a network that indicates the UE supports machine learning (ML)-based measurement event prediction, and that indicates the ML model is available in the UE and trained for the inference operation; receiving anevent-triggered measurement reporting configuration from the network for reporting measurement event predictions for a measurement event according to the UE capability information; performing an inference operation according to the event-triggered measurement reporting configuration in which a measurement event prediction is made using a ML model to which measurements performed by the UE are applied; and sending a dedicated message to the network to report the measurement event prediction or the measurement event for evaluation.

[0151] Clause 41. The method of clause 40, wherein the method further comprises: performing measurements according to the event-triggered measurement configuration; evaluating the measurements to make a determination whether the measurement event is fulfilled; and collecting training data including the measurements and the determination for training the ML model to perform the inference operation.

[0152] Clause 42. The method of clause 40 or clause 41, wherein the UE capability information also indicates at least one of: one or more trigger conditions supported for the inference operation; one or more observations windows supported for measurements for the inference operation; one or more prediction windows supported for the inference operation; or one or more measurement event configurations supported by the ML model.

[0153] Clause 43. The method of any of clauses 40 to 42, wherein the event-triggered measurement reporting configuration indicates at least one of: a trigger condition for performing the inference operation; an observation window for measurements for the inference operation; a prediction window for the inference operation; 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 outcome of the inference operation.

[0154] Clause 44. The method of any of clauses 40 to 43, wherein the measurement event prediction includes a prediction indicating whether the measurement event is predicted to occur or not occur.

[0155] Clause 45. The method of clause 44, wherein the prediction indicates the measurement event is predicted to occur, and the dedicated message includes an indication of a time at which the measurement event is predicted to occur.

[0156] Clause 46. The method of clause 44 or clause 45, wherein the prediction indicates the measurement event is predicted to occur, and the method further comprises:making a determination that a triggering condition for the measurement event is satisfied based on an evaluation of measurements performed by the UE; and starting a shorter time-to-trigger (TTT) than a TTT associated with the measurement event triggered by the determination, and wherein the dedicated message is sent to the network to report the measurement event, and the dedicated message is triggered by expiration of the shorter TTT.

[0157] Clause 47. The method of any of clauses 44 to 46, wherein the prediction indicates the measurement event is predicted to not occur, and the method further comprises starting a time-to-trigger (TTT) associated with the measurement event triggered by the prediction, and wherein the dedicated message is sent to the network to report the measurement event, and the dedicated message is triggered by expiration of the TTT.

[0158] Clause 48. An 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 perform the method of any of clauses 40 to 47.

[0159] Clause 49. An apparatus comprising means for performing the method of any of clauses 40 to 47.

[0160] Clause 50. 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 clauses 40 to 47.

[0161] Clause 51. A computer-readable storage medium comprising instructions that, in response to execution by at least one processing circuitry, causes an apparatus to perform the method of any of clauses 40 to 47.

[0162] Clause 52. A computer program comprising instructions that, in response to execution by at least one processing circuitry, causes an apparatus to perform the method of any of clauses 40 to 47.

[0163] 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 thespecific 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. An apparatus implemented by 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: send UE capability information to a network that indicates the UE supports machine learning (ML)-based measurement event prediction, and that indicates the ML model is available in the UE and trained for the inference operation; receive an event-triggered measurement reporting configuration from the network for reporting measurement event predictions for a measurement event according to the UE capability information; perform an inference operation according to the event-triggered measurement reporting configuration in which a measurement event prediction is made using a ML model to which measurements performed by the UE are applied; and report the measurement event prediction or the measurement event to the network for evaluation.

2. The apparatus of claim 1, wherein the at least one processing circuitry is configured to execute the instructions to cause the apparatus to further at least: perform measurements according to the event-triggered measurement configuration; evaluate the measurements to make a determination whether the measurement event is fulfilled; and collect training data including the measurements and the determination for training the ML model to perform the inference operation.

3. The apparatus of claim 1, wherein the UE capability information also indicates at least one of: one or more trigger conditions supported for the inference operation;one or more observations windows supported for measurements for the inference operation; one or more prediction windows supported for the inference operation; or one or more measurement event configurations supported by the ML model.

4. The apparatus of claim 1, wherein the event-triggered measurement reporting configuration indicates at least one of: a trigger condition for performing the inference operation; an observation window for measurements for the inference operation; a prediction window for the inference operation; 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 outcome of the inference operation.

5. The apparatus of claim 1, wherein the measurement event prediction includes a prediction indicating whether the measurement event is predicted to occur or not occur.

6. The apparatus of claim 5, wherein the prediction indicates the measurement event is predicted to occur, and the measurement event prediction is reported to the network with an indication of a time at which the measurement event is predicted to occur.

7. The apparatus of claim 5, wherein the prediction indicates the measurement event is predicted to occur, and the at least one processing circuitry is configured to execute the instructions to cause the apparatus to further at least: make a determination that a triggering condition for the measurement event is satisfied based on an evaluation of measurements performed by the UE; and start a shorter time-to-trigger (TTT) than a TTT associated with the measurement event triggered by the determination, andwherein the apparatus caused to report the measurement event prediction or the measurement event includes the apparatus caused to report the measurement event to the network triggered by expiration of the shorter TTT.

8. The apparatus of claim 5, wherein the prediction indicates the measurement event is predicted to not occur, and the at least one processing circuitry is configured to execute the instructions to cause the apparatus to further start a time-to- trigger (TTT) associated with the measurement event triggered by the prediction, and wherein the apparatus caused to report the measurement event prediction or the measurement event includes the apparatus caused to report the measurement event to the network triggered by expiration of the TTT.

9. A method performed by a user equipment (UE), the method comprising: sending UE capability information to a network that indicates the UE supports machine learning (ML)-based measurement event prediction, and that indicates the ML model is available in the UE and trained for the inference operation; receiving an event-triggered measurement reporting configuration from the network for reporting measurement event predictions for a measurement event according to the UE capability information; performing an inference operation according to the event-triggered measurement reporting configuration in which a measurement event prediction is made using a ML model to which measurements performed by the UE are applied; and reporting the measurement event prediction or the measurement event to the network for evaluation.

10. The method of claim 9, wherein the method further comprises: performing measurements according to the event-triggered measurement configuration; evaluating the measurements to make a determination whether the measurement event is fulfilled; andcollecting training data including the measurements and the determination for training the ML model to perform the inference operation.

11. The method of claim 9, wherein the UE capability information also indicates at least one of: one or more trigger conditions supported for the inference operation; one or more observations windows supported for measurements for the inference operation; one or more prediction windows supported for the inference operation; or one or more measurement event configurations supported by the ML model.

12. The method of claim 9, wherein the event-triggered measurement reporting configuration indicates at least one of: a trigger condition for performing the inference operation; an observation window for measurements for the inference operation; a prediction window for the inference operation; 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 outcome of the inference operation.

13. The method of claim 9, wherein the measurement event prediction includes a prediction indicating whether the measurement event is predicted to occur or not occur.

14. The method of claim 13, wherein the prediction indicates the measurement event is predicted to occur, and the measurement event prediction is reported to the network with an indication of a time at which the measurement event is predicted to occur.

15. The method of claim 13, wherein the prediction indicates the measurement event is predicted to occur, and the method further comprises:making a determination that a triggering condition for the measurement event is satisfied based on an evaluation of measurements performed by the UE; and starting a shorter time-to-trigger (TTT) than a TTT associated with the measurement event triggered by the determination, and wherein reporting the measurement event prediction or the measurement event includes reporting the measurement event to the network triggered by expiration of the shorter TTT.

16. The method of claim 13, wherein the prediction indicates the measurement event is predicted to not occur, and the method further comprises starting a time-to- trigger (TTT) associated with the measurement event triggered by the prediction, and wherein reporting the measurement event prediction or the measurement event includes reporting the measurement event to the network triggered by expiration of the TTT.

17. A computer-readable storage medium that is non-transitory and has instructions stored therein that, in response to execution by at least one processing circuitry, causes an apparatus implemented by a user equipment (UE) to at least: send UE capability information to a network that indicates the UE supports machine learning (ML)-based measurement event prediction, and that indicates the ML model is available in the UE and trained for the inference operation; receive an event-triggered measurement reporting configuration from the network for reporting measurement event predictions for a measurement event according to the UE capability information; perform an inference operation according to the event-triggered measurement reporting configuration in which a measurement event prediction is made using a ML model to which measurements performed by the UE are applied; and report the measurement event prediction or the measurement event to the network for evaluation.

18. The computer-readable storage medium of claim 17, wherein the measurement event prediction includes a prediction indicating whether the measurement event is predicted to occur or not occur.

19. The computer-readable storage medium of claim 18, wherein the prediction indicates the measurement event is predicted to occur, and the measurement event prediction is reported to the network with an indication of a time at which the measurement event is predicted to occur.

20. The computer-readable storage medium of claim 18, wherein the prediction indicates the measurement event is predicted to occur, and the computer- readable storage medium has further instructions stored therein that, in response to execution by the at least one processing circuitry, causes the apparatus to further at least: make a determination that a triggering condition for the measurement event is satisfied based on an evaluation of measurements performed by the UE; and start a shorter time-to-trigger (TTT) than a TTT associated with the measurement event triggered by the determination, and wherein the apparatus caused to report the measurement event prediction or the measurement event includes the apparatus caused to report the measurement event to the network triggered by expiration of the shorter TTT.

21. The computer-readable storage medium of claim 18, wherein the prediction indicates the measurement event is predicted to not occur, and the computer- readable storage medium has further instructions stored therein that, in response to execution by the at least one processing circuitry, causes the apparatus to further start a time-to-trigger (TTT) associated with the measurement event triggered by the prediction, and wherein the apparatus caused to report the measurement event prediction or the measurement event includes the apparatus caused to report the measurement event to the network triggered by expiration of the TTT.

Images