AI / ML-based mobility-related prediction for handover

Abstract

A source network node and a UE can obtain at least one mobility-related prediction associated with the UE or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network, and the source network node is able to hand over the UE from the source network node to the at least one target network node based on the at least one mobility-related prediction. The target network node can receive a handover request, obtain at least one mobility-related prediction associated with the UE or the target network node, and output a handover request ACK for transmission, the handover request ACK based at least in part on the at least one mobility-related prediction.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of U.S. patent application serial number 17 / 808,072, filed on June 21, 2022, entitled “AI / ML BASED MOBILITY RELATED PREDICTION FOR HANDOVER,” which is expressly incorporated herein by reference in its entirety. Technical Field

[0003] The present disclosure relates generally to communication systems, and more particularly, to a method of wireless communication including artificial intelligence (AI) or machine learning (ML) (AI / ML) based mobility-related prediction for handover procedures. Background Art

[0004] Wireless communication systems are widely deployed to provide a variety of telecommunication services, such as telephony, video, data, messaging, and broadcast. Typical wireless communication systems may employ multiple access technologies capable of supporting communication with multiple users by sharing available system resources. Examples of such multiple access technologies include code division multiple access (CDMA) systems, time division multiple access (TDMA) systems, frequency division multiple access (FDMA) systems, orthogonal frequency division multiple access (OFDMA) systems, single carrier frequency division multiple access (SC-FDMA) systems, and time division synchronous code division multiple access (TD-SCDMA) systems.

[0005] These multiple access technologies have been adopted in various telecommunication standards to provide a common protocol that enables different wireless devices to communicate at a city, country, region, and even global level. An example telecommunication standard is 5G New Radio (NR). 5G NR is part of the continuous mobile broadband evolution promulgated by the Third Generation Partnership Project (3GPP) to meet new requirements associated with latency, reliability, security, scalability (e.g., with the Internet of Things (IoT)) and other requirements. 5GNR includes services associated with enhanced mobile broadband (eMBB), massive machine type communication (mMTC), and ultra-reliable low latency communication (URLLC). Certain aspects of 5G NR may be based on 4G Long Term Evolution (LTE) standards. It is necessary to further improve 5G NR technology. In addition, these improvements may also be applicable to other multiple access technologies and telecommunication standards that employ these technologies. Summary of the invention

[0006] A simplified summary of one or more aspects is presented below to provide a basic understanding of these aspects. This summary is not an extensive review of all contemplated aspects. This summary neither identifies the key or important elements of all aspects, nor describes the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to a more detailed description presented later.

[0007] In one aspect of the present disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus may include a user equipment (UE), the user equipment (UE) being configured to: obtain at least one mobility-related prediction associated with the UE or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network; and handover from a source network node to a first target network node of the at least one target network node based on the at least one mobility-related prediction.

[0008] In one aspect of the present disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus may include a source network node, the source network node being configured to: obtain at least one mobility-related prediction associated with a UE or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network; and hand over the UE from the source network node to the at least one target network node based on the at least one mobility-related prediction.

[0009] In one aspect of the present disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus may include a target network node, the target network node being configured to: receive a handover request to handover a UE from a source network node; obtain at least one mobility-related prediction associated with the UE or the target network node, the at least one mobility-related prediction being derived by at least one neural network; and output a handover request ACK for transmission, the handover request ACK being based at least in part on the at least one mobility-related prediction.

[0010] To achieve the aforementioned and related purposes, one or more aspects include the features fully described below and particularly pointed out in the claims. The following description and the accompanying drawings set forth in detail some exemplary features of one or more aspects. However, these features indicate only some of the various ways in which the principles of the various aspects can be employed. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 is a diagram illustrating an example of a wireless communication system and an access network.

[0012] Figure 2A is a diagram illustrating an example of a first frame according to various aspects of the present disclosure.

[0013] Figure 2B is a diagram illustrating an example of DL channels within a subframe according to various aspects of the present disclosure.

[0014] Figure 2C is a diagram illustrating an example of a second frame according to various aspects of the present disclosure.

[0015] Figure 2D is a diagram illustrating an example of UL channels within a subframe according to various aspects of the present disclosure.

[0016] Figure 3 is a diagram illustrating an example of a base station and a user equipment (UE) in an access network.

[0017] Figure 4 is an example of an AI / ML algorithm for a method of wireless communication.

[0018] Figure 5 It is a call flow diagram of the handover procedure.

[0019] Figure 6 It is a call flow diagram of the handover procedure.

[0020] Figure 7 It is a call flow diagram of the handover procedure.

[0021] Figure 8 It is the call flow for which Radio Resource Management (RRM) measurements are relaxed.

[0022] Fig. 9 is a flow chart of a method of wireless communication.

[0023] Fig.10 is a flow chart of a method of wireless communication.

[0024] Fig.11 is a flow chart of a method of wireless communication.

[0025] Fig.12 is a flow chart of a method of wireless communication.

[0026] Fig.13 is a flow chart of a method of wireless communication.

[0027] Fig.14 is a flow chart of a method of wireless communication.

[0028] Fig.15 are diagrams illustrating examples of hardware implementations for example apparatuses and / or network entities.

[0029] Fig.16 is a diagram illustrating an example of a hardware implementation for an example network entity. DETAILED DESCRIPTION

[0030] In a handover procedure, a source network node and a user equipment (UE) may consider multiple parameters to a) determine whether to perform a handover procedure or b) determine a target network node to hand over the UE from the source network node. In some aspects of the current disclosure, the UE, the source network node, or the target network node may include a neural network or machine learning model for obtaining / deriving a prediction of mobility, and the source network node or the UE may perform a handover procedure based on the prediction of mobility to improve robustness and QoS / QoE during the handover procedure and reduce UE power consumption and network resource costs.

[0031] The specific embodiments described below in conjunction with the accompanying drawings are descriptions of various configurations and do not represent the only configurations in which the concepts described herein can be practiced. In order to provide a thorough understanding of the various concepts, the specific embodiments include specific details. However, these concepts can be practiced without these specific details. In some cases, well-known structures and components are shown in block diagram form to avoid obscuring such concepts.

[0032] Several aspects of telecommunication systems are presented with reference to various apparatuses and methods. These apparatuses and methods are described in the following detailed description and illustrated in the accompanying drawings by various blocks, components, circuits, processes, algorithms, etc. (collectively referred to as "elements"). These elements may be implemented using electronic hardware, computer software, or any combination thereof. Whether these elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system.

[0033] As an example, an element, or any part of an element, or any combination of elements can be implemented as a "processing system", which includes one or more processors. Examples of processors include microprocessors, microcontrollers, graphics processing units (GPUs), central processing units (CPUs), application processors, digital signal processors (DSPs), reduced instruction set computing (RISC) processors, systems on chip (SoCs), baseband processors, field programmable gate arrays (FPGAs), programmable logic devices (PLDs), state machines, gated logic components, discrete hardware circuits, and other suitable hardware configured to perform various functionalities described throughout the present disclosure. One or more processors in a processing system can execute software. Whether referred to as software, firmware, middleware, microcode, hardware description language, or other terms, software should be broadly interpreted as meaning instructions, instruction sets, codes, code segments, program codes, programs, subroutines, software components, applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, functions, or any combination thereof.

[0034] Thus, in one or more example aspects, specific implementations and / or use cases, the described functionality may be implemented in hardware, software, or any combination thereof. If implemented in software, the functionality may be stored or encoded as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media. Storage media may be any available media that can be accessed by a computer. As an example, such computer-readable media may include random access memory (RAM), read-only memory (ROM), electrically erasable programmable ROM (EEPROM), optical disk storage, magnetic disk storage, other magnetic storage devices, combinations of these types of computer-readable media, or any other medium that can be used to store computer-executable code in the form of instructions or data structures that can be accessed by a computer.

[0035] Although various aspects, specific implementations and / or use cases are described in this application by the illustration of some examples, additional or different aspects, specific implementations and use cases may be generated in many different arrangements and scenarios. The various aspects, specific implementations and / or use cases described herein can be implemented across many different platform types, devices, systems, shapes, sizes and packaging arrangements. For example, various aspects, specific implementations and / or use cases can be generated via integrated chip specific implementations and other devices based on non-module components (e.g., end-user devices, vehicles, communication equipment, computing equipment, industrial equipment, retail / purchase equipment, medical equipment, devices that enable artificial intelligence (AI), etc.). Although some examples may or may not be specifically for use cases or applications, the described examples may have wide applicability. Various aspects, specific implementations and / or use cases can be in the range from chip-level or modular components to non-modular, non-chip-level specific implementations, and further to the range of aggregated, distributed or original equipment manufacturer (OEM) equipment or systems in conjunction with one or more technologies herein. In some actual settings, the equipment combined with the various aspects and features described may also include additional components and features for implementing and practicing the claimed and described aspects. For example, the transmission and reception of wireless signals necessarily include multiple components for analog and digital purposes (e.g., hardware components including antennas, RF chains, power amplifiers, modulators, buffers, processors, interleavers, adders / summers, etc.) The various techniques described herein can be practiced in a wide variety of devices of various sizes, shapes, and configurations, chip-level components, systems, distributed arrangements, aggregated or disaggregated components, end-user devices, etc.

[0036] The deployment of a communication system (such as a 5G NR system) can be arranged in a variety of ways using various components or constituent parts. In a 5G NR system or network, a network node, a network entity, a mobility element of a network, a radio access network (RAN) node, a core network node, a network element, or a network equipment (such as a base station (BS), or one or more units (or one or more components) that perform base station functionality can be implemented in an aggregated or decomposed architecture. For example, a BS (such as a Node B (NB), an evolved NB (eNB), an NR BS, a 5G NB, an access point (AP), a transmit receive point (TRP), or a cell, etc.) can be implemented as an aggregated base station (also referred to as an independent BS or a monolithic BS) or a decomposed base station.

[0037] A converged base station may be configured to utilize a radio protocol stack physically or logically integrated within a single RAN node. A decomposed base station may be configured to utilize a protocol stack physically or logically distributed between two or more units, such as one or more central or centralized units (CUs), one or more distributed units (DUs), or one or more radio units (RUs). In some aspects, a CU may be implemented within a RAN node, and one or more DUs may be co-located with the CU, or alternatively, may be geographically or virtually distributed in one or more other RAN nodes. A DU may be implemented to communicate with one or more RUs. Each of a CU, a DU, and a RU may be implemented as a virtual unit, i.e., a virtual central unit (VCU), a virtual distributed unit (VDU), or a virtual radio unit (VRU).

[0038] Base station operation or network design may take into account the aggregated nature of base station functionality. For example, a disaggregated base station may be utilized in an integrated access backhaul (IAB) network, an open radio access network (O-RAN (network configuration such as that initiated by the O-RAN Alliance)), or a virtualized radio access network (vRAN, also known as a cloud radio access network (C-RAN)). Decomposition may include distributing functionality across two or more units at various physical locations, as well as virtually distributing functionality of at least one unit, which may enable flexibility in network design. Individual units of a disaggregated base station or disaggregated RAN architecture may be configured for wired or wireless communication with at least one other unit.

[0039] Figure 11 is a diagram 100 illustrating an example of a wireless communication system and an access network. The illustrated wireless communication system includes a disaggregated base station architecture. The disaggregated base station architecture may include one or more CUs 110 that may communicate directly with a core network 120 via a backhaul link, or indirectly with the core network 120 through one or more disaggregated base station units, such as a near real-time (near RT) RAN intelligent controller (RIC) 125 via an E2 link, or a non-real-time (non-RT) RIC 115 associated with a service management and orchestration (SMO) framework 105, or both. The CU 110 may communicate with one or more DUs 130 via corresponding midhaul links, such as an F1 interface. The DU 130 may communicate with one or more RUs 140 via corresponding fronthaul links. The RU 140 may communicate with corresponding UEs 104 via one or more radio frequency (RF) access links. In some implementations, a UE 104 may be served simultaneously by multiple RUs 140.

[0040] Each of the units (i.e., CU 110, DU 130, RU 140, and near-RT RIC 125, non-RT RIC 115, and SMO framework 105) may include or be coupled to one or more interfaces configured to receive or send signals, data, or information (collectively referred to as signals) via a wired or wireless transmission medium. Each of the units or an associated processor or controller that provides instructions to the communication interface of these units may be configured to communicate with one or more of the other units via a transmission medium. For example, these units may include a wired interface that is configured to receive signals or send signals to one or more of the other units via a wired transmission medium. Additionally, these units may include a wireless interface that may include a receiver, transmitter, or transceiver (such as an RF transceiver) configured to receive and / or send signals to one or more of the other units via a wireless transmission medium.

[0041] In some aspects, CU 110 may host one or more higher layer control functions. Such control functions may include radio resource control (RRC), packet data convergence protocol (PDCP), service data adaptation protocol (SDAP), etc. Each control function may be implemented using an interface that is configured to communicate signals with other control functions hosted by CU 110. CU 110 may be configured to handle user plane functionality (i.e., central unit-user plane (CU-UP)), control plane functionality (i.e., central unit-control plane (CU-CP)), or a combination thereof. In some specific implementations, CU 110 may be logically split into one or more CU-UP units and one or more CU-CP units. When implemented in an O-RAN configuration, the CU-UP unit may communicate bidirectionally with the CU-CP unit via an interface (such as an E1 interface). As needed, CU 110 may be implemented to communicate with DU 130 for network control and signaling.

[0042] DU 130 may correspond to a logical unit that includes one or more base station functions for controlling the operation of one or more RUs 140. In some aspects, DU 130 may host one or more of a radio link control (RLC) layer, a medium access control (MAC) layer, and one or more high physical (PHY) layers (such as modules for forward error correction (FEC) encoding and decoding, scrambling, modulation and demodulation, etc.) at least in part according to a functional split such as those defined by 3GPP. In some aspects, DU 130 may also host one or more low PHY layers. Each layer (or module) may be implemented using an interface that is configured to communicate signals with other layers (and modules) hosted by DU 130 or with control functions hosted by CU 110.

[0043] The lower layer functionality may be implemented by one or more RUs 140. In some deployments, the RU 140 controlled by the DU 130 may correspond to a logical node that hosts RF processing functions or low PHY layer functions (such as performing fast Fourier transform (FFT), inverse FFT (iFFT), digital beamforming, physical random access channel (PRACH) extraction and filtering, etc.), or both, based at least in part on functional splitting (such as lower layer functional splitting). In such an architecture, the RU 140 may be implemented to handle over-the-air (OTA) communications with one or more UEs 104. In some implementations, real-time and non-real-time aspects of control plane and user plane communications with the RU 140 may be controlled by the corresponding DU 130. In some scenarios, this configuration may enable the DU 130 and CU 110 to be implemented in a cloud-based RAN architecture (such as a vRAN architecture).

[0044] The SMO framework 105 may be configured to support RAN deployment and provisioning of non-virtualized network elements and virtualized network elements. For non-virtualized network elements, the SMO framework 105 may be configured to support the deployment of dedicated physical resources for RAN coverage requirements, which may be managed via an operation and maintenance interface (such as an O1 interface). For virtualized network elements, the SMO framework 105 may be configured to interact with a cloud computing platform (such as an open cloud (O-Cloud) 190) to perform network element lifecycle management (such as instantiating virtualized network elements) via a cloud computing platform interface (such as an O2 interface). Such virtualized network elements may include, but are not limited to, CU 110, DU 130, RU 140, and near-RT RIC 125. In some specific implementations, the SMO framework 105 may communicate with hardware aspects of the 4G RAN (such as an open eNB (O-eNB) 111) via the O1 interface. Additionally, in some specific implementations, the SMO framework 105 may communicate directly with one or more RUs 140 via the O1 interface. The SMO framework 105 may also include a non-RT RIC 115 configured to support the functionality of the SMO framework 105 .

[0045] The non-RT RIC 115 may be configured to include logic functions that enable non-real-time control and optimization of RAN elements and resources, artificial intelligence (AI) / machine learning (ML) (AI / ML) workflows including model training and updating, or policy-based guidance of applications / features in the near-RT RIC 125. The non-RT RIC 115 may be coupled to or in communication with the near-RT RIC 125 (such as via an AI interface). The near-RT RIC 125 may be configured to include logic functions that enable near-real-time control and optimization of RAN elements and resources via data collection and actions through an interface (such as via an E2 interface) that connects one or more CUs 110, one or more DUs 130, or both, and the O-eNB with the near-RT RIC 125.

[0046] In some implementations, in order to generate an AI / ML model to be deployed in the near-RT RIC 125, the non-RT RIC 115 may receive parameters or external enrichment information from an external server. Such information may be utilized by the near-RT RIC 125 and may be received from a non-network data source or from a network function at the SMO framework 105 or the non-RT RIC 115. In some examples, the non-RT RIC 115 or the near-RT RIC 125 may be configured to tune RAN behavior or performance. For example, the non-RT RIC 115 may monitor long-term trends and patterns of performance and employ AI / ML models to perform corrective actions through the SMO framework 105 (such as via reconfiguration of O1) or via the creation of RAN management policies (such as A1 policies).

[0047] At least one of the CU 110, the DU 130, and the RU 140 may be referred to as a base station 102. Therefore, the base station 102 may include one or more of the CU 110, the DU 130, and the RU 140 (each component is indicated by a dotted line to indicate that each component may be included in the base station 102 or may not be included in the base station). The base station 102 provides an access point to the core network 120 for the UE 104. The base station 102 may include a macro cell (a high-power cellular base station) and / or a small cell (a low-power cellular base station). Small cells include femto cells, pico cells, and micro cells. A network including both small cells and macro cells may be referred to as a heterogeneous network. A heterogeneous network may also include a home evolved Node B (eNB) (HeNB), which may provide services to a restricted group referred to as a closed subscriber group (CSG). The communication link between RU 140 and UE 104 may include uplink (UL) (also known as reverse link) transmission from UE 104 to RU 140 and / or downlink (DL) (also known as forward link) transmission from RU 140 to UE 104. The communication link may use multiple-input multiple-output (MIMO) antenna technology, including spatial multiplexing, beamforming and / or transmit diversity. The communication link may be through one or more carriers. For each carrier allocated in a carrier aggregation of up to Yx MHz (x component carriers) for transmission in each direction, the base station 102 / UE 104 may use a spectrum of up to Y MHz (e.g., 5MHz, 10MHz, 15MHz, 20MHz, 100MHz, 400MHz, etc.) bandwidth. These carriers may or may not be adjacent to each other. The allocation of carriers may be equivalent to DL and UL asymmetric (e.g., more or fewer carriers may be allocated to DL than to UL). Component carriers may include a primary component carrier and one or more secondary component carriers. The primary component carrier may be referred to as a primary cell (PCell) and the secondary component carrier may be referred to as a secondary cell (SCell).

[0048] Some UEs 104 may communicate with each other using a device-to-device (D2D) communication link 158. The D2D communication link 158 may use DL / UL wireless wide area network (WWAN) spectrum. The D2D communication link 158 may use one or more sidelink channels, such as a physical sidelink broadcast channel (PSBCH), a physical sidelink discovery channel (PSDCH), a physical sidelink shared channel (PSSCH), and a physical sidelink control channel (PSCCH). The D2D communication may be through a variety of wireless D2D communication systems, such as, for example, Bluetooth, Wi-Fi based on the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standard, LTE, or NR.

[0049] The wireless communication system may also include a Wi-Fi AP 150 that communicates with a UE 104 (also referred to as a Wi-Fi station (STA)) via a communication link 154, for example, in a 5 GHz unlicensed spectrum, etc. When communicating in an unlicensed spectrum, the UE 104 / AP 150 may perform a clear channel assessment (CCA) to determine whether a channel is available prior to communication.

[0050] The electromagnetic spectrum is typically subdivided into various categories, bands, channels, etc. based on frequency / wavelength. In 5G NR, two initial operating bands have been identified as frequency range designations FR1 (410 MHz-7.125 GHz) and FR2 (24.25 GHz-52.6 GHz). Although a portion of FR1 is greater than 6 GHz, FR1 is often referred to (interchangeably) as the "sub-6 GHz" band in various documents and articles. A similar naming issue sometimes occurs with respect to FR2, which is often (interchangeably) referred to as the "millimeter wave" band in documents and articles, although different from the extremely high frequency (EHF) band (30 GHz-300 GHz) identified as the "millimeter wave" band by the International Telecommunication Union (ITU).

[0051] Frequencies between FR1 and FR2 are generally referred to as mid-band frequencies. Recent 5G NR research has identified the operating bands for these mid-band frequencies as frequency range designation FR3 (7.125GHz-24.25GHz). The bands falling within FR3 can inherit FR1 characteristics and / or FR2 characteristics, so the features of FR1 and / or FR2 can be effectively extended to mid-band frequencies. In addition, higher frequency bands are currently being explored to extend 5G NR operations to more than 52.6GHz. For example, three higher operating bands have been identified as frequency range designations FR2-2 (52.6GHz-71GHz), FR4 (71GHz-114.25GHz) and FR5 (114.25GHz-300GHz). Each of these higher frequency bands falls within the EHF band.

[0052] In view of the above, unless otherwise specified, if the term "6 GHz or less" is used herein, it may broadly refer to frequencies that may be less than 6 GHz, may be within FR1, or may include mid-band frequencies. In addition, unless otherwise specified, if the term "millimeter wave" is used herein, it may broadly refer to frequencies that may include mid-band frequencies, may be within FR2, FR4, FR2-2, and / or FR5, or may be within the EHF band.

[0053] The base station 102 and the UE 104 may each include multiple antennas (such as antenna elements, antenna panels, and / or antenna arrays) to facilitate beamforming. The base station 102 may send a beamformed signal 182 to the UE 104 in one or more transmit directions. The UE 104 may receive the beamformed signal from the base station 102 in one or more receive directions. The UE 104 may also send a beamformed signal 184 to the base station 102 in one or more transmit directions. The base station 102 may receive the beamformed signal from the UE 104 in one or more receive directions. The base station 102 / UE 104 may perform beam training to determine the best receive direction and transmit direction for each of the base station 102 / UE 104. The transmit direction and receive direction of the base station 102 may be the same or different. The transmit direction and receive direction of the UE 104 may be the same or different.

[0054] The base station 102 may include and / or be referred to as a gNB, a Node B, an eNB, an access point, a base transceiver station, a radio base station, a radio transceiver, a transceiver function, a basic service set (BSS), an extended service set (ESS), a transmit receive point (TRP), a network node, a network entity, a network equipment, or some other suitable term. The base station 102 may be implemented as an integrated access and backhaul (IAB) node, a relay node, a sidelink node, an aggregated (monolithic) base station with a baseband unit (BBU) (including a CU and a DU) and a RU, or as a decomposed base station including one or more of a CU, a DU, and / or a RU. A set of base stations that may include decomposed base stations and / or aggregated base stations may be referred to as a next generation (NG) RAN (NG-RAN).

[0055] The core network 120 may include an access and mobility management function (AMF) 161, a session management function (SMF) 162, a user plane function (UPF) 163, a unified data management (UDM) 164, one or more location servers 168, and other functional entities. AMF 161 is a control node that handles signaling between UE 104 and core network 120. AMF 161 supports registration management, connection management, mobility management, and other functions. SMF 162 supports session management and other functions. UPF 163 supports packet routing, packet forwarding, and other functions. UDM 164 supports the generation of authentication and key agreement (AKA) credentials, user identity handling, access authorization, and subscription management. One or more location servers 168 are illustrated as including a gateway mobile location center (GMLC) 165 and a location management function (LMF) 166. However, in general, the one or more location servers 168 may include one or more location / positioning servers, which may include one or more of the GMLC 165, LMF 166, position determination entity (PDE), serving mobile location center (SMLC), mobile positioning center (MPC), etc. GMLC 165 and LMF 166 support UE location services. GMLC 165 provides an interface for clients / applications (e.g., emergency services) to access UE positioning information. LMF 166 receives measurement and assistance information from NG-RAN and UE 104 via AMF 161 to calculate the location of UE 104. NG-RAN may determine the location of UE 104 using one or more positioning methods. Positioning UE 104 may involve signal measurements, position estimation, and optional speed calculation based on these measurements. Signal measurements may be performed by UE 104 and / or serving base station 102. The measured signals may be based on a satellite positioning system (SPS) 170 (e.g., one or more of a global navigation satellite system (GNSS), a global positioning system (GPS), a non-terrestrial network (NTN), or other satellite positioning / positioning systems), LTE signals, wireless local area network (WLAN) signals, Bluetooth signals, a terrestrial beacon system (TBS), sensor-based information (e.g., an atmospheric pressure sensor, a motion sensor), an NR enhanced cell ID (NR E-CID) method, NR signals (e.g., multi-round trip time (multi-RTT), DL angle of departure (DL-AoD), DL time difference of arrival (DL-TDOA), UL time difference of arrival (UL-TDOA), and UL angle of arrival (UL-AoA) positioning), and / or one or more of other systems / signals / sensors.

[0056] Examples of UE 104 include cellular phones, smart phones, session initiation protocol (SIP) phones, laptops, personal digital assistants (PDAs), satellite radios, global positioning systems, multimedia devices, video devices, digital audio players (e.g., MP3 players), cameras, game consoles, tablet computers, smart devices, wearable devices, vehicles, electric meters, gas pumps, large or small kitchen appliances, healthcare equipment, implants, sensors / actuators, displays, or any other similarly functional devices. Some of the UEs 104 may be referred to as IoT devices (e.g., parking meters, gas pumps, toasters, vehicles, heart monitors, etc.). UE 104 may also be referred to as stations, mobile stations, subscriber stations, mobile units, subscriber units, wireless units, remote units, mobile devices, wireless devices, wireless communication devices, remote devices, mobile subscriber stations, access terminals, mobile terminals, wireless terminals, remote terminals, mobile phones, user agents, mobile clients, clients, or some other suitable terminology. In some scenarios, the term UE may also be applied to one or more supporting devices, such as in a device cluster arrangement. One or more of these devices may access the network collectively and / or individually.

[0057] Reference again Figure 1In some aspects, the UE 104 may include an AI / ML-based mobility prediction component 198, which is configured to: obtain at least one mobility-related prediction associated with the UE or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network; and handover from the source network node to a first target network node among the at least one target network node based on the at least one mobility-related prediction. In some aspects, the base station 102 may include an AI / ML-based mobility prediction component 199, which is configured to: obtain at least one mobility-related prediction associated with the UE or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network; and handover the UE from the source network node to the at least one target network node based on the at least one mobility-related prediction. In certain aspects, the base station 102 may include an AI / ML-based mobility prediction component 199, which is configured to: receive a handover request to handover a UE from a source network node; obtain at least one mobility-related prediction associated with the UE or the target network node, the at least one mobility-related prediction being derived by at least one neural network; and output a handover request ACK for transmission, the handover request ACK being based at least in part on the at least one mobility-related prediction. Although the following description may focus on 5G NR, the concepts described herein may be applicable to other similar fields, such as LTE, LTE-A, CDMA, GSM, and other wireless technologies.

[0058] Figure 2A FIG200 is a diagram illustrating an example of a first subframe within a 5G NR frame structure. Figure 2B FIG230 is a diagram illustrating an example of DL channels within a 5G NR subframe. Figure 2C FIG250 is a diagram illustrating an example of a second subframe within a 5G NR frame structure. Figure 2D FIG280 is a diagram illustrating an example of UL channels within a 5G NR subframe. The 5G NR frame structure may be frequency division duplex (FDD), where for a particular set of subcarriers (carrier system bandwidth), subframes within that subcarrier set are dedicated to either DL or UL, or may be time division duplex (TDD), where for a particular set of subcarriers (carrier system bandwidth), subframes within that subcarrier set are dedicated to both DL and UL. Figure 2A , Figure 2CIn the example provided, the 5G NR frame structure is assumed to be TDD, where subframe 4 is configured with slot format 28 (most of which are DL), where D is DL, U is UL, and F is flexible between DL / UL, and subframe 3 is configured with slot format 1 (all of which are UL). Although subframes 3 and 4 are shown as having slot formats 1 and 28, respectively, any particular subframe may be configured with any of the various available slot formats 0-61. Slot formats 0 and 1 are full DL and full UL, respectively. Other slot formats 2-61 include a mix of DL, UL and flexible symbols. The UE is configured with the slot format through the received slot format indicator (SFI) (dynamically configured through DL control information (DCI) or semi-statically / statically configured through radio resource control (RRC) signaling). Note that the following description also applies to the 5G NR frame structure as TDD.

[0059] FIG. 2A to FIG. 2D The frame structure is illustrated, and various aspects of the present disclosure may be applicable to other wireless communication technologies that may have different frame structures and / or different channels. A frame (10ms) may be divided into 10 subframes of equal size (1ms). Each subframe may include one or more time slots. A subframe may also include a microslot, which may include 7, 4 or 2 symbols. Each time slot may include 14 or 12 symbols, depending on whether the cyclic prefix (CP) is normal or extended. For a normal CP, each time slot may include 14 symbols, and for an extended CP, each time slot may include 12 symbols. The symbol on the DL may be a CP orthogonal frequency division multiplexing (OFDM) (CP-OFDM) symbol. The symbol on the UL may be a CP-OFDM symbol (for high throughput scenarios) or a discrete Fourier transform (DFT) extended OFDM (DFT-s-OFDM) symbol (also known as a single carrier frequency division multiple access (SC-FDMA) symbol) (for power-limited scenarios; limited to single-stream transmission). The number of slots within a subframe is based on the CP and the parameter set. The parameter set defines the subcarrier spacing (SCS) and effectively defines the symbol length / duration, which is equal to 1 / SCS.

[0060] μ <![CDATA[SCSΔf=2 μ ·15[kHz]]]> Cyclic prefix 0 15 normal 1 30 normal 2 60 Normal, Extended 3 120 normal 4 240 normal

[0061] For normal CP (14 symbols / slot), different parameter sets μ0 to 4 allow 1, 2, 4, 8, and 16 slots per subframe, respectively. For extended CP, parameter set 2 allows 4 slots per subframe. Thus, for normal CP and parameter set μ, there are 14 symbols / slot and 2 μ timeslots / subframe. The subcarrier spacing can be equal to 2 μ*15kHz, where μ is parameter set 0 to 4. Therefore, the subcarrier spacing for parameter set μ=0 is 15kHz, and the subcarrier spacing for parameter set μ=4 is 240kHz. The symbol length / duration is inversely related to the subcarrier spacing. FIG. 2A to FIG. 2D An example is provided for a normal CP with 14 symbols per slot and a parameter set μ=2 with 4 slots per subframe. The slot duration is 0.25 ms, the subcarrier spacing is 60 kHz, and the symbol duration is about 16.67 μs. Within a frame set, there may be one or more different bandwidth parts (BWPs) that are frequency-division multiplexed (see Figure 2B ). Each BWP may have a specific parameter set and CP (normal or extended).

[0062] A resource grid may be used to represent the frame structure. Each slot includes a resource block (RB) (also referred to as a physical RB (PRB)) extending over 12 consecutive subcarriers. The resource grid is divided into a plurality of resource elements (REs). The number of bits carried by each RE depends on the modulation scheme.

[0063] like Figure 2A As illustrated, some of the REs carry reference (pilot) signals (RS) for the UE. The RS may include a demodulation RS (DM-RS) (indicated as R for one particular configuration, but other DM-RS configurations are possible) and a channel state information reference signal (CSI-RS) for channel estimation at the UE. The RS may also include a beam measurement RS (BRS), a beam refinement RS (BRRS), and a phase tracking RS (PT-RS).

[0064] Figure 2BExamples of various DL channels within a subframe of a frame are illustrated. A physical downlink control channel (PDCCH) carries DCI within one or more control channel elements (CCEs) (e.g., 1, 2, 4, 8, or 16 CCEs), each CCE including six RE groups (REGs), each REG including 12 consecutive REs in an OFDM symbol of an RB. A PDCCH within a BWP may be referred to as a control resource set (CORESET). The UE is configured to monitor PDCCH candidates in a PDCCH search space (e.g., a common search space, a UE-specific search space) during a PDCCH monitoring opportunity on a CORESET, wherein the PDCCH candidates have different DCI formats and different aggregation levels. Additional BWPs may be located at higher and / or lower frequencies on the channel bandwidth. A primary synchronization signal (PSS) may be within symbol 2 of a particular subframe of a frame. The PSS is used by UE 104 to determine subframe / symbol timing and physical layer identification. A secondary synchronization signal (SSS) may be within symbol 4 of a particular subframe of a frame. The SSS is used by the UE to determine the physical layer cell identity group number and the radio frame timing. Based on the physical layer identity and the physical layer cell identity group number, the UE can determine the physical cell identifier (PCI). Based on the PCI, the UE can determine the location of the DM-RS. The physical broadcast channel (PBCH) carrying the master information block (MIB) can be logically grouped with the PSS and SSS to form a synchronization signal (SS) / PBCH block (also referred to as an SS block (SSB)). The MIB provides the number of RBs in the system bandwidth and the system frame number (SFN). The physical downlink shared channel (PDSCH) carries user data, broadcast system information not sent via the PBCH (such as a system information block (SIB)), and paging messages.

[0065] like Figure 2C As illustrated, some of the REs carry DM-RS (indicated as R for a particular configuration, but other DM-RS configurations are possible) for channel estimation at the base station. The UE may send a DM-RS for a physical uplink control channel (PUCCH) and a DM-RS for a physical uplink shared channel (PUSCH). The PUSCH DM-RS may be sent in the first or first two symbols of the PUSCH. Depending on whether a short PUCCH or a long PUCCH is sent and depending on the specific PUCCH format used, the PUCCH DM-RS may be sent in different configurations. The UE may send a sounding reference signal (SRS). The SRS may be sent in the last symbol of a subframe. The SRS may have a comb structure, and the UE may send the SRS on one of the teeth of the comb. The SRS may be used by the base station for channel quality estimation to achieve frequency-dependent scheduling of the UL.

[0066] Figure 2DExamples of various UL channels within a subframe of a frame are illustrated. The PUCCH may be located at a position as indicated in one configuration. The PUCCH carries uplink control information (UCI), such as scheduling requests, channel quality indicators (CQI), precoding matrix indicators (PMI), rank indicators (RI), and hybrid automatic repeat request (HARQ) acknowledgement (ACK) (HARQ-ACK) feedback (i.e., one or more HARQ ACK bits indicating one or more ACKs and / or negative ACKs (NACKs)). The PUSCH carries data and may be used to carry, among other things, a buffer status report (BSR), a power headroom report (PHR), and / or UCI.

[0067] Figure 3 370 is a block diagram of a base station 310 in an access network communicating with a UE 350. In the DL, Internet Protocol (IP) packets may be provided to a controller / processor 375. The controller / processor 375 implements layer 3 and layer 2 functionality. Layer 3 includes a radio resource control (RRC) layer, and layer 2 includes a service data adaptation protocol (SDAP) layer, a packet data convergence protocol (PDCP) layer, a radio link control (RLC) layer, and a medium access control (MAC) layer. The controller / processor 375 provides RRC layer functionality associated with broadcasting of system information (e.g., MIB, SIB), RRC connection control (e.g., RRC connection paging, RRC connection establishment, RRC connection modification, and RRC connection release), inter-radio access technology (RAT) mobility, and measurement configuration for UE measurement reporting; PDCP layer functionality associated with header compression / decompression, security (encryption, decryption, integrity protection, integrity verification), and handover support functions; RLC layer functionality associated with transfer of upper layer packet data units (PDUs), error correction through ARQ, concatenation, segmentation and reassembly of RLC service data units (SDUs), re-segmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functionality associated with mapping between logical channels and transport channels, multiplexing of MAC SDUs onto transport blocks (TBs), demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction through HARQ, priority handling, and logical channel prioritization.

[0068] The transmit (TX) processor 316 and receive (RX) processor 370 implement layer 1 functionality associated with various signal processing functions. Layer 1 (which includes the physical (PHY) layer) may include error detection on the transport channel, forward error correction (FEC) coding / decoding of the transport channel, interleaving, rate matching, mapping to the physical channel, modulation / demodulation of the physical channel, and MIMO antenna processing. The TX processor 316 handles the mapping to the signal constellation based on various modulation schemes (e.g., binary phase shift keying (BPSK), quadrature phase shift keying (QPSK), M-order phase shift keying (M-PSK), M-order quadrature amplitude modulation (M-QAM)). The coded and modulated symbols may then be separated into parallel streams. Each stream may then be mapped to an OFDM subcarrier, multiplexed with a reference signal (e.g., pilot) in the time and / or frequency domain, and then combined together using an inverse fast Fourier transform (IFFT) to produce a physical channel carrying a time domain OFDM symbol stream. The OFDM stream is spatially pre-coded to generate multiple spatial streams. Channel estimates from a channel estimator 374 may be used to determine the coding and modulation schemes, as well as for spatial processing. Channel estimates may be derived based on reference signals and / or channel condition feedback sent by the UE 350. Each spatial stream may then be provided to a different antenna 320 via a separate transmitter 318Tx. Each transmitter 318Tx may modulate a radio frequency (RF) carrier with a corresponding spatial stream for transmission.

[0069] At the UE 350, each receiver 354Rx receives a signal through its corresponding antenna 352. Each receiver 354Rx recovers the information modulated onto the RF carrier and provides the information to a receive (RX) processor 356. The TX processor 368 and the RX processor 356 implement layer 1 functionality associated with various signal processing functions. The RX processor 356 can perform spatial processing on the information to recover any spatial stream destined for the UE 350. If multiple spatial streams are destined for the UE 350, they can be combined into a single OFDM symbol stream by the RX processor 356. The RX processor 356 then converts the OFDM symbol stream from the time domain to the frequency domain using a fast Fourier transform (FFT). The frequency domain signal includes a separate OFDM symbol stream for each subcarrier of the OFDM signal. The symbols on each subcarrier and the reference signal are recovered and demodulated by determining the signal constellation point most likely to be sent by the base station 310. These soft decisions can be based on channel estimates calculated by the channel estimator 358. The soft decisions are then decoded and deinterleaved to recover the data and control signals originally sent on the physical channel by base station 310. The data and control signals are then provided to controller / processor 359, which implements layer 3 and layer 2 functionality.

[0070] The controller / processor 359 may be associated with a memory 360 that stores program codes and data. The memory 360 may be referred to as a computer readable medium. In the UL, the controller / processor 359 provides demultiplexing between transport channels and logical channels, packet reassembly, decryption, header decompression, and control signal processing to recover IP packets. The controller / processor 359 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operations.

[0071] Similar to the functionality described in conjunction with DL transmissions performed by the base station 310, the controller / processor 359 provides RRC layer functionality associated with system information (e.g., MIB, SIB) acquisition, RRC connection, and measurement reporting; PDCP layer functionality associated with header compression / decompression and security (encryption, decryption, integrity protection, integrity verification); RLC layer functionality associated with transfer of upper layer PDUs, error correction through ARQ, concatenation, segmentation and reassembly of RLC SDUs, resegmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functionality associated with mapping between logical channels and transport channels, multiplexing of MAC SDUs onto TBs, demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction through HARQ, priority handling, and logical channel prioritization.

[0072] Channel estimates derived by the channel estimator 358 based on a reference signal or feedback sent by the base station 310 may be used by the TX processor 368 to select the appropriate coding and modulation schemes and to facilitate spatial processing. The spatial streams generated by the TX processor 368 may be provided to different antennas 352 via separate transmitters 354Tx. Each transmitter 354Tx may modulate an RF carrier with a corresponding spatial stream for transmission.

[0073] UL transmissions are processed at the base station 310 in a manner similar to that described in conjunction with the receiver functionality at the UE 350. Each receiver 318Rx receives a signal through its respective antenna 320. Each receiver 318Rx recovers information modulated onto an RF carrier and provides the information to the RX processor 370.

[0074] The controller / processor 375 may be associated with a memory 376 that stores program codes and data. The memory 376 may be referred to as a computer readable medium. In the UL, the controller / processor 375 provides demultiplexing between transport channels and logical channels, packet reassembly, decryption, header decompression, control signal processing to recover IP packets. The controller / processor 375 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operations.

[0075] At least one of the TX processor 368, the RX processor 356, and the controller / processor 359 may be configured to perform operations related to Figure 1 The TX processor 316, the RX processor 370, and the controller / processor 375 may be configured to perform various aspects related to the AI / ML-based mobility-related prediction component 198. Figure 1 Various aspects related to the AI / ML based mobility prediction component 199.

[0076] A handover procedure may refer to a procedure for handing over (or transferring) a UE from being served by one cell to being served by another cell. In some aspects, a call of the UE may be in progress during a handover procedure from a serving cell to another cell (e.g., a target cell). The handover procedure may be triggered in response to a UE (e.g., a mobile device) moving from one place to another or a change in a wireless network connection. Here, a serving cell may be associated with a serving network node, and a target cell may be associated with a target network node.

[0077] In some aspects, the network (including the base station) may decide to hand over the UE from one cell to another cell based on the measurement report received from the UE. That is, based on the measurement report received from the UE, the base station may decide to hand over the UE from the first cell to the second cell. The measurement report may include multiple measurements of cell metrics, such as reference signal received power (RSRP), reference signal received quality (RSRQ), signal to interference plus noise ratio (SINR), and the signal quality of the serving cell and the neighboring cell may be measured using various methods (e.g., periodic measurement or event-triggered measurement). That is, in order to reduce unnecessary handover procedures, the base station and the UE may be configured with periodic measurement reports and / or event-triggered measurement reports, and the base station and the UE may perform handover based on the measurement report.

[0078] In some aspects, an event-triggered handover procedure may be performed based on an event, which may refer to at least one type of measurement report. The base station may configure the UE with at least one type of event via an RRC signaling message. That is, the UE may receive an RRC signaling message including the configuration of at least one type of event from the base station.

[0079] In one aspect, the event may correspond to the measurement of the serving cell becoming better than a threshold (e.g., event A1), and the ongoing handover procedure may be canceled based on event A1. On the other hand, the event may correspond to the measurement of the service becoming worse than a threshold, such as event A2, which may trigger a mobility procedure. On the other hand, the event may correspond to the measurement of the neighboring cell becoming better than the primary cell (PCell) by an offset value, such as event A3, which may trigger an intra-frequency or inter-frequency handover procedure. On the other hand, the event may correspond to the measurement of the neighboring cell becoming better than a threshold, such as event A4, which may trigger a handover procedure that may not depend on the coverage of the serving cell. On the other hand, the event may correspond to the measurement of the PCell becoming worse than a first threshold and the measurement of the neighboring cell becoming better than a second threshold, such as event A5, which may trigger an intra-frequency or inter-frequency handover procedure. On the other hand, the event may correspond to the measurement of the neighboring cell becoming better than an offset value of the SCell, such as event A6, which may be applicable to carrier aggregation. In another aspect, the event may correspond to measurements of inter-radio access technology (RAT) neighboring cells becoming better than a threshold, such as event B1, which may trigger an inter-RAT handover procedure that is independent of the coverage of the serving cell. In another aspect, the event may correspond to measurements of the PCell becoming worse than a first threshold and measurements of the inter-RAT neighboring cells becoming better than a second threshold, such as event B2, which may trigger an inter-RAT mobility procedure when the primary serving cell becomes weak.

[0080] Figure 4 400 is an example of an AI / ML algorithm 400 of a method for wireless communication. Here, the AI / ML algorithm 400 may be included in a UE or a network node (e.g., a source network node or a target network node of a handover procedure) to provide mobility-related predictions based on AI / ML. The AI / ML algorithm 400 may include various functions, including a data collection function 402, a model training function 404, a model inference function 406, and an actor 408.

[0081] The data collection function 402 may be a function that provides input data to the model training function 404 and the model inference function 406. The data collection function 402 may include any form of data preparation, and it may not be specific to the specific implementation of the AI / ML algorithm (e.g., data preprocessing and cleaning, formatting, and transformation). Examples of input data may include, but are not limited to, measurements from network entities including UEs or network nodes, feedback from the actor 408, and output from another AI / ML model. The data collection function 402 may include training data and inference data, wherein the training data refers to data to be transmitted as input to the model training function 404, and the inference data refers to data transmitted as input to the model inference function 406.

[0082] The model training function 404 may be a function that performs ML model training, validation, and testing, which may generate model performance metrics as part of the model testing procedure. The model training function 404 may also be responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on the training data delivered or received from the data collection function 402. The model training function 404 may deploy or update the trained, validated, and tested AI / ML models to the model inference function 406, and receive model performance feedback from the model inference function 406.

[0083] The model inference function 406 may be a function that provides a model inference output (e.g., a prediction or decision). The model inference function 406 may also perform data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on the inference data delivered from the data collection function 402. The output of the model inference function 406 may include the inference output of the AI / ML model generated by the model inference function 406. The details of the inference output may be use case specific.

[0084] Model performance feedback may refer to information derived from the model inference function 406 that may be suitable for improving the AI / ML model trained in the model training function 404. Feedback from actors 408 or other network entities (via the data collection function 402) may be implemented for the model inference function 406 to create model performance feedback.

[0085] The actor 408 may be a function that receives output from the model inference function 406 and triggers or performs a corresponding action. The actor 408 may trigger an action for a network entity including other network entities or itself. The actor 408 may also provide feedback information for the model training function 404 or the model inference function 406 to derive training or inference data or performance feedback. The feedback may be sent back to the data collection function 402.

[0086] UE and / or network entities (centralized and / or distributed units) may use machine learning algorithms, deep learning algorithms, neural networks, reinforcement learning, regression, boosting or advanced signal processing methods for various aspects of wireless communications, such as with a base station, a TRP, another UE, etc.

[0087] In some aspects described herein, a coding device (e.g., UE) may train one or more neural networks to learn the dependence of the measured quality on various parameters. In addition, examples of machine learning models or neural networks that may be included in the UE and / or network entities include artificial neural networks (ANNs); decision tree learning; convolutional neural networks (CNNs); deep learning architectures, in which the output of a first layer of neurons becomes the input of a second layer of neurons, etc.; support vector machines (SVMs), for example, which include a separating hyperplane (e.g., a decision boundary) for classifying data; regression analysis; Bayesian networks; genetic algorithms; deep convolutional networks (DCNs), which are configured with additional pooling and normalization layers; and deep belief networks (DBNs).

[0088] A machine learning model, such as an artificial neural network (ANN), may include a set of interconnected artificial neurons (e.g., a neuron model) and may be a computing device or may represent a method to be performed by a computing device. The connections of the neuron model may be modeled as weights. The machine learning model may provide predictive models, adaptive control, and other applications by training via a data set. The model may be adaptive based on external or internal information processed by the machine learning model. Machine learning may provide nonlinear statistical data models or decision making, and may model complex relationships between input data and output information.

[0089] The machine learning model may include multiple layers and / or operations, which may be formed by cascading one or more of the cited operations. Examples of operations that may be involved include: extraction of various features of data, convolution operations, fully connected operations that may be activated or deactivated, compression, decompression, quantization, flattening, etc. As used herein, the "layer" of the machine learning model may be used to represent operations on input data. For example, convolution layers, fully connected layers, etc. may be used to refer to associated operations on data input to the layer. Convolution AxB operations refer to operations that convert multiple input features A into multiple output features B. "Kernel size" may refer to the number of neighboring coefficients combined in a dimension. As used herein, "weights" may be used to represent one or more coefficients used in operations for combining individual rows and / or columns of input data in each layer. For example, a fully connected layer operation may have an output y, which is determined at least in part based on the product of the input matrix x and the weight A (which may be a matrix) and the sum of the bias value B (which may be a matrix). The term "weight" may be generally used herein to refer to both weights and bias values. Weights and biases are examples of parameters of a trained machine learning model. Different layers of a machine learning model can be trained independently.

[0090] Machine learning models may include various connectivity patterns, for example, including any of feedforward networks, hierarchies, recursive architectures, feedback connections, etc. The connections between layers of a neural network may be fully connected or locally connected. In a fully connected neural network, a neuron in a first layer may communicate its output to each neuron in a second layer, and each neuron in a second layer may receive input from each neuron in the first layer. In a locally connected network, a neuron in a first layer may be connected to a limited number of neurons in a second layer. In some aspects, a convolutional network may be locally connected and configured with a shared connection strength associated with the input of each neuron in the second layer. A locally connected layer of a network may be configured so that each neuron in the layer has the same or similar connectivity pattern, but with different connection strengths.

[0091] A machine learning model or neural network may be trained. For example, a machine learning model may be trained based on supervised learning. During training, the machine learning model may be presented with inputs that the model uses to calculate to produce an output. The actual output may be compared to the target output, and the difference may be used to adjust the parameters of the machine learning model (such as weights and biases) to provide an output closer to the target output. Before training, the output may be incorrect or less accurate, and the error or difference between the actual output and the target output may be calculated. The weights of the machine learning model may then be adjusted so that the output is more closely aligned with the target. In order to adjust the weights, the learning algorithm may calculate a gradient vector for the weights. The gradient may indicate the amount by which the error will increase or decrease if the weights are slightly adjusted. At the top layer, the gradient may directly correspond to the value of the weights connecting the activated neurons in the penultimate layer and the neurons in the output layer. In the lower layers, the gradient may depend on the value of the weights and the calculated error gradients of the higher layers. The weights may then be adjusted to reduce the error or move the output closer to the target. This way of adjusting the weights may be referred to as back propagation through a neural network. The process may continue until the achievable error rate stops decreasing, or until the error rate has reached a target level.

[0092] These machine learning models may include computational complexity and a large number of processors for training machine learning models. The output of one node is connected as an input to another node. The connection between nodes may be referred to as an edge, and weights may be applied to the connection / edge to adjust the output from one node, which is used as an input to another node. Nodes may apply thresholds to determine whether or when to provide output to a connected node. The output of each node may be calculated as a nonlinear function of the sum of the inputs to the node. A neural network may include any number of nodes and any type of connection between the nodes. A neural network may include one or more hidden nodes. Nodes may be aggregated into layers, and different layers of a neural network may perform different kinds of transformations on the input. A signal may travel from an input at the first layer through multiple layers of a neural network to an output at the last layer of the neural network, and may traverse these layers multiple times.

[0093] In some aspects, the handover procedure may have enhanced mobility performance using AI / ML based predictions. That is, the handover procedure may be based at least in part on mobility related predictions of at least one of the UE or the network to improve the performance of the handover procedure. The AI / ML based predictions may include, but are not limited to, UE trajectory predictions, UE traffic predictions, RRM measurement predictions, network resource status predictions, achievable QoS / QoE at the target network node, location and / or mobility status.

[0094] In one aspect, the UE may include an AI / ML model for deriving at least one mobility-related prediction associated with the UE, and the at least one mobility-related prediction associated with the UE may include a UE trajectory prediction, a UE traffic prediction, a radio resource management (RRM) measurement prediction, or at least one of a UE location and a mobility state. On the other hand, the source network node may include an AI / ML model for deriving at least one mobility-related prediction associated with the UE, and the at least one mobility-related prediction associated with the UE may include a UE trajectory prediction, a UE traffic prediction, an RRM measurement prediction, or at least one of a UE location and a mobility state. In one example, the AI / ML model of the UE or the source network node may predict that the trajectory of the UE is directed to enter a first target cell of a first target network node at a certain time, and the UE and the source network may determine to hand over the UE to the first target network node at a time corresponding to the UE trajectory prediction. In another example, the AI / ML model may predict that the UE traffic is heavy, and the source network node may hand over the UE to a target network node predicted by the AI / ML model to have a network throughput that can support heavy UE traffic.

[0095] In another aspect, the target network node may include an AI / ML model for deriving at least one mobility-related prediction associated with the target network node, and the at least one mobility-related prediction associated with the target network node may include a prediction of network resource capacity (including physical resource blocks (PRBs) or transport network layers (TNLs)) or at least one of a achievable quality of service (QoS) or quality of experience (QoE) (QoS / QoE) at at least one target network node after handover. In one example, the AI / ML model of the target network node may predict the QoS after handover of the UE from the source network node to the target network node, and the predicted QoS may be transmitted to the source network node so that the source network determines whether to proceed with the handover of the UE from the source network node to the target network node.

[0096] Based on some aspects of the present disclosure including AI / ML based mobility related predictions, handover procedures may have improved robustness, improved QoS / QoE during handover procedures, reduced UE power consumption, or reduced network resource costs.

[0097] Figure 5 The call flow diagram 500 is a handover procedure based on Xn or X2 (Xn / X2). Here, Xn / X2 may refer to an Xn interface in 5GNR or an X2 interface in LTE between a source network node and a target network node. That is, the source network node and the target network node may have an Xn / X2 interface configured between the source network node and the target network node, and signaling of the handover may be communicated between the source network node and the target network node over the Xn / X2 interface.

[0098] The Xn / X2 based handover procedure may include UE 502, source network node 504, and target network node 506. First, UE 502 may perform RRM measurements of source network node 504 and target network node 506, and at 510, UE 502 may send a measurement report based on the RRM measurements to source network node 504.

[0099] In some aspects, the source network node 504 may obtain at least one mobility-related prediction associated with the UE 502 or the target network node 506. Here, the at least one mobility-related prediction may be derived by at least one neural network. The at least one mobility-related prediction may be associated with the UE 502, and the at least one mobility-related prediction associated with the UE 502 may include at least one of a UE trajectory prediction, a UE 502 traffic prediction, an RRM measurement prediction, or a UE 502 location and a mobility state.

[0100] In one aspect, at 512, source network node 504 may derive at least one mobility-related prediction associated with UE 502 using at least one neural network of source network node 504. That is, source network node 504 may have at least one neural network, and based on the measurement report received from UE 502 at 510, source network node 504 may derive at least one mobility-related prediction associated with UE 502.

[0101] In another aspect, source network node 504 may obtain at least one mobility-related prediction associated with UE 502 by receiving at least one mobility-related prediction associated with UE 502 from UE 502. At 514, UE 502 may derive at least one mobility-related prediction associated with UE 502 using at least one neural network of UE 502. That is, UE 502 may have at least one neural network, and UE 502 may derive at least one mobility-related prediction associated with UE 502 using the at least one neural network. At 516, UE 502 may send at least one mobility-related prediction associated with UE 502 derived at 514, and source network node 504 may obtain at least one mobility-related prediction associated with UE 502.

[0102] In another aspect, source network node 504 may obtain at least one mobility-related prediction associated with target network node 506. The at least one mobility-related prediction may be associated with target network node 506, and the at least one mobility-related prediction associated with target network node 506 may include at least one of a prediction of network resource capacity (including PRB / TNL) or a achievable QoS / QoE at target network node 506 after handover. First, based on the RRM measurement report received at 510 and / or at least one mobility-related prediction associated with UE 502 (e.g., derived at 512 or received at 516), source network node 504 may determine to hand over UE 502 to target network node 506. Based on the determination to hand over UE 502 to target network node 506, at 520, source network node 504 may send a handover request to target network node 506 via an Xn / X2 interface between source network node 504 and target network node 506. Here, the handover request at 520 may indicate handover information associated with UE 502 and source network node 504, and may further include at least one mobility-related prediction associated with UE 502 (eg, derived at 512 or received at 516).

[0103] At 530, target network node 506 may derive at least one mobility-related prediction associated with target network node 506. That is, target network node 506 may have at least one neural network, and based on the handover request received from source network node 504 at 520, target network node 506 may derive at least one mobility-related prediction associated with target network node 506.

[0104] At 540, target network node 506 may send a handover request ACK in response to the handover request at 520. The handover request ACK may indicate to source network node 504 that the handover request was successfully sent to target network node 506, and that target network node 506 may accept the handover of UE 502 from source network node 504. In one aspect, target network node 506 may send at least one mobility-related prediction associated with target network node 506 derived at 530 in the handover request ACK sent at 540 to source network node 504. That is, target network node 506 may send at least one mobility-related prediction associated with target network node 506 derived at 530 to source network node 504 in the handover request ACK at 540.

[0105] Source network node 504 may consider at least one mobility-related prediction associated with target network node 506 obtained at 540 to perform a handover of UE 502 from source network node 504 to target network node 506. That is, based on at least one mobility-related prediction associated with target network node 506, such as at least one of a prediction of network resource capacity (including PRB / TNL) or a achievable QoS / QoE at target network node 506 after the handover, it is determined whether target network node 506 is not suitable for handing over UE 502 from source network node 504. For example, if the achievable QoS at target network node 506 may not support an active call of UE 502, source network node 504 may determine not to hand over UE 502 to target network node 506.

[0106] Source network node 504 may receive a handover request ACK from target network node 506 at 540 and send a handover command to UE 502 at 550. The handover command at 550 may instruct UE 502 to switch to target network node 506 to perform a handover of UE 502 from source network node 504 to target network node 506.

[0107] At 552, UE 502 may determine to handover to target network node 506 based on the handover command received from source network node 504. Here, determining to handover to target network node 506 may refer to selecting a target resource configuration associated with target network node 506. The target resource configuration associated with target network node 506 may include a first cell or a target beam associated with target network node 506.

[0108] At 554, UE 502 may send an RRC reconfiguration message to target network node 506 to establish a new RRC connection with target network node 506 to perform a handover of UE 502 from source network node 504 to target network node 506. The RRC message may include an indication of a target resource configuration associated with first target network node 506.

[0109] In one aspect, the handover command received at 550 may include at least one mobility-related prediction associated with the UE 502 derived at 512. That is, if the UE 502 does not derive at least one mobility-related prediction associated with the UE 502 at 514, the source network node 504 may transmit at least one mobility-related prediction associated with the UE 502 in the handover command 550, e.g., a UE trajectory prediction, a UE 502 traffic prediction, an RRM measurement prediction, or at least one of a UE 502 location and a mobility state, and the UE 502 may obtain the at least one mobility-related prediction associated with the UE 502. The UE 502 may determine to handover to the target network node 506 based at least in part on the at least one mobility-related prediction associated with the UE 502 received in the handover command at 550.

[0110] On the other hand, the handover command received at 550 may not include at least one mobility-related prediction associated with UE 502, and UE 502 may use at least one mobility-related prediction associated with UE 502 derived at 514 to determine whether to switch to target network node 506 based at least in part on at least one mobility-related prediction associated with UE 502 derived at 514.

[0111] In another aspect, the handover command received at 550 may further include a mobility-related prediction associated with the target network node 506 as derived at 530. That is, the source network node 504 may transmit at least one mobility-related prediction associated with the target network node 506, such as, for example, at least one of a prediction of network resource capacity (including PRBs / TNLs) or a achievable QoS / QoE at the target network node 506 after the handover, and the UE 502 may determine whether to handover to the target network node 506 based at least in part on the at least one mobility-related prediction associated with the target network node 506 received in the handover command at 550.

[0112] Figure 6 The call flow diagram 600 is a handover procedure based on NGAP or S1 (NG / S1). Here, NG / S1 may refer to the NGAP protocol in 5GNR or the S1 interface in LTE between the network node and the core network. That is, the source network node and the target network node may not have an Xn / X2 interface configured between the source network node and the target network node, and the signaling of the handover may be communicated between the source network node and the target network node through the core network over the NG / S1 interface.

[0113] The NG / S1 based handover procedure may include UE 602, source network node 604, target network node 606 and core network 608. First, the UE may perform RRM measurements of the source network node and the target network node, and at 610, the UE may send a measurement report based on the RRM measurements to the source network node.

[0114] In some aspects, the source network node 604 may obtain at least one mobility-related prediction associated with the UE 602 or the target network node 606. Here, the at least one mobility-related prediction may be derived by at least one neural network. The at least one mobility-related prediction may be associated with the UE 602, and the at least one mobility-related prediction associated with the UE 602 may include at least one of a UE trajectory prediction, a UE 602 traffic prediction, an RRM measurement prediction, or a UE 602 location and a mobility state.

[0115] In one aspect, at 612, source network node 604 may derive at least one mobility-related prediction associated with UE 602 using at least one neural network of source network node 604. That is, source network node 604 may have at least one neural network, and based on the measurement report received from UE 602 at 610, source network node 604 may derive at least one mobility-related prediction associated with UE 602.

[0116] In another aspect, the source network node 604 may obtain at least one mobility-related prediction associated with the UE 602 by receiving at least one mobility-related prediction associated with the UE 602 from the UE 602. At 614, the UE 602 may derive the at least one mobility-related prediction associated with the UE 602 using at least one neural network of the UE 602. That is, the UE 602 may have at least one neural network, and the UE 602 may derive the at least one mobility-related prediction associated with the UE 602 using the at least one neural network. At 616, the UE 602 may send the at least one mobility-related prediction associated with the UE 602 derived at 614, and the source network node 604 may obtain the at least one mobility-related prediction associated with the UE 602.

[0117] In another aspect, the source network node 604 may obtain at least one mobility-related prediction associated with the target network node 606. The at least one mobility-related prediction may be associated with the target network node 606, and the at least one mobility-related prediction associated with the target network node 606 may include at least one of a prediction of network resource capacity (including PRB / TNL) or a achievable QoS / QoE at the target network node 606 after the handover. First, based on the RRM measurement report received at 610 and / or at least one mobility-related prediction associated with the UE 602 (e.g., derived at 612 or received at 616), the source network node 604 may determine to hand over the UE 602 to the target network node 606. Based on the determination to hand over the UE 602 to the target network node 606, at 620, the source network node 604 may send a handover requirement message to the core network 608 via an NG / S1 interface between the source network node 604 and the core network 608. Here, the handover requirement message at 620 may indicate handover information associated with UE 602 and source network node 604, and may further include at least one mobility-related prediction (e.g., derived at 612 or received at 616) associated with UE 602. At 622, core network 608 may send a handover request to target network node 606 based on the handover requirement message received at 620 from source network node 604.

[0118] At least one mobility-related prediction associated with the UE 602 may be included in a source-to-target transparent container for NG / S1-based handover. Here, a source-to-target transparent container information element (IE) may refer to an IE for transparently transferring radio-related information from a handover source (e.g., source network node 604) to a handover target (e.g., target network node 606). At least one mobility-related prediction associated with the UE 602 in the source-to-target transparent container may be sent to the core network 608 in a handover requirement message at 620, and the core network may deliver the source-to-target transparent container including the at least one mobility-related prediction associated with the UE 602 to the target network node 606. The target network node 606 may receive the at least one mobility-related prediction associated with the UE 602 from the core network 608 in a handover request at 622, wherein the handover request includes the source-to-target transparent container with the at least one mobility-related prediction associated with the UE 602 from the source network node 604.

[0119] At 630, the target network node 606 may derive at least one mobility-related prediction associated with the target network node 606. That is, the target network node 606 may have at least one neural network, and based on the handover request received from the core network 608 at 620, the target network node 606 may derive at least one mobility-related prediction associated with the target network node 606.

[0120] At 632, the target network node 606 may send a handover request ACK to the target network node 606 based on the handover request received from the core network 608 at 622. The handover request ACK may indicate to the core network 608 that the handover request was successfully sent to the target network node 606 and that the target network node 606 may accept the handover of the UE 602 from the source network node 604. In one aspect, the target network node 606 may send at least one mobility-related prediction associated with the target network node 606 derived at 630 in the handover request ACK sent to the core network 608 at 640. That is, the target network node 606 may send to the core network 608 in the handover request ACK at 640 the at least one mobility-related prediction associated with the target network node 606 derived at 630. At 640, the core network 608 may send a handover command in response to the handover request ACK received at 632.

[0121] At least one mobility-related prediction associated with the target network node 606 may be included in a target-to-source transparent container. Here, the target-to-source transparent container IE may refer to an IE for transparently transferring radio-related information from a handover target (e.g., the target network node 606) to a handover source (e.g., the source network node 604). The at least one mobility-related prediction associated with the target network node 606 in the target-to-source transparent container may be sent to the core network 608 in a handover requirement message at 620, and the core network may deliver the target-to-source transparent container including the at least one mobility-related prediction associated with the target network node 606 to the source network node 604. The source network node 604 may receive the at least one mobility-related prediction associated with the target network node 606 from the core network 608 in a handover command at 640, wherein the handover command includes the target-to-source transparent container with the at least one mobility-related prediction associated with the target network node 606 from the target network node 606.

[0122] Source network node 604 may consider at least one mobility-related prediction associated with target network node 606 obtained at 640 to perform a handover of UE 602 from source network node 604 to target network node 606. That is, based on at least one mobility-related prediction associated with target network node 606, such as at least one of a prediction of network resource capacity (including PRB / TNL) or a achievable QoS / QoE at target network node 606 after the handover, it is determined whether target network node 606 is not suitable for handing over UE 602 from source network node 604. For example, if the achievable QoS at target network node 606 may not support an active call of UE 602, source network node 604 may determine not to hand over UE 602 to target network node 606.

[0123] Source network node 604 may receive a handover request ACK from target network node 606 via core network 608 at 640 and send a handover command to UE 602 at 650. The handover command at 650 may instruct UE 602 to switch to target network node 606 to perform a handover of UE 602 from source network node 604 to target network node 606.

[0124] At 652, UE 602 may determine to handover to target network node 606 based on the handover command received from source network node 604. Here, determining to handover to target network node 606 may refer to selecting a target resource configuration associated with target network node 606. The target resource configuration associated with target network node 606 may include a first cell or a target beam associated with target network node 606.

[0125] At 654, UE 602 may send an RRC reconfiguration message to target network node 606 to establish a new RRC connection with target network node 606 to perform a handover of UE 602 from source network node 604 to target network node 606. The RRC message may include an indication of a target resource configuration associated with first target network node 606.

[0126] In one aspect, the handover command received at 650 may include at least one mobility-related prediction associated with the UE 602 derived at 612. That is, if the UE 602 does not derive at least one mobility-related prediction associated with the UE 602 at 614, the source network node 604 may transmit at least one mobility-related prediction associated with the UE 602 in the handover command 650, e.g., a UE trajectory prediction, a UE 602 traffic prediction, an RRM measurement prediction, or at least one of a UE 602 location and a mobility state, and the UE 602 may obtain the at least one mobility-related prediction associated with the UE 602. The UE 602 may determine to handover to the target network node 606 based at least in part on the at least one mobility-related prediction associated with the UE 602 received in the handover command at 650.

[0127] On the other hand, the handover command received at 650 may not include at least one mobility-related prediction associated with UE 602, and UE 602 may use at least one mobility-related prediction associated with UE 602 derived at 614 to determine whether to switch to target network node 606 based at least in part on at least one mobility-related prediction associated with UE 602 derived at 614.

[0128] In another aspect, the handover command received at 650 may further include a mobility-related prediction associated with the target network node 606 as derived at 630. That is, the source network node 604 may transmit at least one mobility-related prediction associated with the target network node 606, such as, for example, at least one of a prediction of network resource capacity (including PRBs / TNLs) or a achievable QoS / QoE at the target network node 606 after the handover, and the UE 602 may determine whether to handover to the target network node 606 based at least in part on the at least one mobility-related prediction associated with the target network node 606 received in the handover command at 650.

[0129] Figure 7700 is a call flow diagram of a handover procedure. Here, the handover procedure may be a conditional handover (CHO), in which multiple target network nodes are triggered for the handover procedure. The handover procedure may include UE 702, source network node 704, first target network node 706, and second target network node 707. Here, first target network node 706 and second target network node 707 may be multiple target network nodes triggered for the handover procedure. That is, UE 702 may send measurement reports based on RRM measurements to source network node 704, and these measurement reports may trigger a handover of UE 702 to one of first target network node 706 and second target network node 707.

[0130] In some aspects, the source network node 704 may obtain at least one mobility-related prediction associated with the UE 702 or the target network node 706. Here, the at least one mobility-related prediction may be derived by at least one neural network. The at least one mobility-related prediction may be associated with the UE 702, and the at least one mobility-related prediction associated with the UE 702 may include at least one of a UE trajectory prediction, a UE 702 traffic prediction, an RRM measurement prediction, or a UE 702 location and a mobility state.

[0131] In one aspect, at 712, source network node 704 may derive at least one mobility-related prediction associated with UE 702 using at least one neural network of source network node 704. That is, source network node 704 may have at least one neural network, and based on the measurement report received from UE 702 at 710, source network node 704 may derive at least one mobility-related prediction associated with UE 702.

[0132] In another aspect, the source network node 704 may obtain at least one mobility-related prediction associated with the UE 702 by receiving at least one mobility-related prediction associated with the UE 702 from the UE 702. At 714, the UE 702 may derive the at least one mobility-related prediction associated with the UE 702 using at least one neural network of the UE 702. That is, the UE 702 may have at least one neural network, and the UE 702 may derive the at least one mobility-related prediction associated with the UE 702 using the at least one neural network. At 716, the UE 702 may send the at least one mobility-related prediction associated with the UE 702 derived at 714, and the source network node 704 may obtain the at least one mobility-related prediction associated with the UE 702.

[0133] In another aspect, the source network node 704 may obtain at least one mobility-related prediction associated with the target network node 706. The at least one mobility-related prediction may be associated with the target network node 706, and the at least one mobility-related prediction associated with the target network node 706 may include at least one of a prediction of network resource capacity (including PRB / TNL) or a achievable QoS / QoE at the target network node 706 after the handover. First, based on the RRM measurement report received at 710 and / or at least one mobility-related prediction associated with the UE 702 (e.g., derived at 712 or received at 716), the source network node 704 may determine to hand over the UE 702 to the target network node 706. Based on the determination to hand over the UE 702 to the target network node 706, at 720, the source network node 704 may send a first handover request to the first target network node 706 and a second handover request to the second target network node 707 via an Xn / X2 interface. Here, the first handover request and the second handover request at 720 may indicate handover information associated with UE 702 and source network node 704, and may further include at least one mobility-related prediction associated with UE 702 (eg, derived at 712 or received at 716).

[0134] At 730, the first target network node 706 may derive a first mobility-related prediction associated with the target network node 706. That is, the first target network node 706 may have at least one neural network, and based on the handover request received from the source network node 704 at 720, the first target network node 706 may derive a first mobility-related prediction associated with the target network node 706.

[0135] At 740, the first target network node 706 may send a handover request ACK in response to the handover request at 720. The handover request ACK may indicate to the source network node 704 that the handover request was successfully sent to the target network 7, and that the target network node 707 may accept the handover of UE 702 from the source network node 704. In one aspect, the first target network node 706 may send the first mobility-related prediction associated with the first target network node 706 derived at 730 in the handover request ACK sent to the source network node 704 at 740. That is, the first target network node 706 may send the first mobility-related prediction associated with the first target network node 706 derived at 730 to the source network node 704 in the handover request ACK at 740.

[0136] At 735, the second target network node 707 may derive a second mobility-related prediction associated with the target network node 707. That is, the second target network node 707 may have at least one neural network, and based on the handover request received from the source network node 704 at 720, the second target network node 707 may derive a second mobility-related prediction associated with the target network node 707.

[0137] At 742, the second target network node 707 may send a handover request ACK in response to the handover request at 720. The handover request ACK may indicate to the source network node 704 that the handover request was successfully sent to the target network 7, and that the target network node 707 may accept the handover of the UE 702 from the source network node 704. In one aspect, the second target network node 707 may send the second mobility-related prediction associated with the second target network node 707 derived at 735 in the handover request ACK sent to the source network node 704 at 742. That is, the second target network node 707 may send the second mobility-related prediction associated with the second target network node 707 derived at 735 to the source network node 704 in the handover request ACK at 742.

[0138] In one aspect, source network node 704 may perform handover of UE 702 from source network node 704 to first target network node 706 and second target network node 707 taking into account first mobility-related predictions and second mobility-related predictions associated with first target network node 706 and second target network node 707 obtained at 740 and 742. That is, first target network node 706 is determined to be more suitable for handing over UE 702 from source network node 704 based on first mobility-related predictions and second mobility-related predictions associated with first target network node 706 and second target network node 707, for example, at least one of predictions of network resource capacity (including PRB / TNL) or achievable QoS / QoE at first target network node 706 and second target network node 707 after handover. For example, if the achievable QoS at first target network node 706 can better support the active call of UE 702 than that at second target network node 707, source network node 704 can determine to hand over UE 702 to first target network node 706 instead of to second target network node 707. Therefore, source network node 704 can receive handover request ACKs from first target network node 706 and second target network node 707 at 740 and 742, and send a handover command to UE 702 at 750, thereby instructing UE 702 to switch to first target network node 706 and second target network node 707 to perform the handover of UE 702 from source network node 704 to first target network node 706 and second target network node 707.

[0139] In some aspects, the UE may evaluate the handover condition and determine the first target network node 706 for the handover procedure. At 752, the UE 702 may determine to hand over to the first target network node 706 among the first target network node 706 and the second target network node 707 based on the handover command received from the source network node 704. Here, determining to hand over to the first target network node 706 may refer to selecting a target resource configuration associated with the first target network node 706. The target resource configuration associated with the first target network node 706 may include a first cell or a first target beam associated with the first target network node 706.

[0140] At 754, UE 702 may send an RRC reconfiguration message to first target network node 706 to establish a new RRC connection with first target network node 706 to perform a handover of UE 702 from source network node 704 to first target network node 706. The RRC message may include an indication of a target resource configuration associated with first target network node 506.

[0141] In one aspect, the handover command received at 750 may include at least one mobility-related prediction associated with the UE 702 derived at 712. That is, if the UE 702 does not derive at least one mobility-related prediction associated with the UE 702 at 714, the source network node 704 may transmit at least one mobility-related prediction associated with the UE 702 in the handover command 750, e.g., a UE trajectory prediction, a UE 702 traffic prediction, an RRM measurement prediction, or at least one of a UE 702 location and a mobility state, and the UE 702 may obtain the at least one mobility-related prediction associated with the UE 702. The UE 702 may determine to hand over to the target network node 706 based at least in part on the at least one mobility-related prediction associated with the UE 702 received in the handover command at 750.

[0142] On the other hand, the handover command received at 750 may not include at least one mobility-related prediction associated with UE 702, and UE 702 may use at least one mobility-related prediction associated with UE 702 derived at 714 to determine whether to switch to target network node 706 based at least in part on at least one mobility-related prediction associated with UE 702 derived at 714.

[0143] In another aspect, the handover command received at 750 may further include mobility-related predictions associated with the first target network node 706 and the second target network node 707 as derived at 730 and 735. That is, the source network node 704 may transmit, in the handover command at 750, first and second mobility-related predictions associated with the first target network node 706 and the second target network node 707, e.g., a prediction of network resource capacity (including PRBs / TNLs) or at least one of a achievable QoS / QoE at the first and second target network nodes 706 and 707 after the handover, and the UE 702 may determine whether to handover to the first and second target network nodes 706 and 707 based at least in part on the first and second mobility-related predictions associated with the first and second target network nodes 706 and 707 received in the handover command at 750.

[0144] The UE may include a machine learning model for selecting a first target network node 706 from a plurality of target network nodes that are triggered for a handover procedure. That is, the handover condition at 752 may be evaluated by the machine learning model. In one example, the input of the machine learning may include at least one of radio measurements, assistance information from a source network node, and location / motion sensor measurements of the UE, and the output of the machine learning may include at least one of a target cell to trigger a handover, a target cell to perform a handover, or a target cell to measure.

[0145] The machine learning model may be configured by the source network node 704. That is, the source network node 704 may include in the handover command at 750 at least one parameter for the machine learning model of the UE to select a first target network node from among the at least one target network node.

[0146] Figure 8 8 is a call flow for RRM measurement relaxation 800. The call flow 800 may include a UE 802 and a source network node 804. The source network node 804 may configure RRM relaxation for the UE to relax RRM measurements based on at least one mobility-related prediction associated with the UE, and the UE may relax at least one configuration of RRM measurements based on the at least one mobility-related prediction.

[0147] At 860, the source network node may relax RRM configuration for the UE to different measurement objects based on at least one mobility-related prediction associated with the UE. Here, at least one configuration of the RRM measurement to be relaxed may include at least one of a sampling rate, a filter coefficient, a reporting configuration, etc.

[0148] At 862, the source network node may configure the UE to decide whether to perform RRM relaxation based on the UE's prediction of the trajectory. That is, the source network node may send to the UE a configuration for determining to relax at least one parameter of RRM measurement for each of at least one target network node at the UE, and the UE may receive from the source network node a configuration for determining to relax at least one parameter of RRM measurement for each of at least one target network node at the UE based on at least one mobility-related prediction associated with the UE. In one example, the source network node may configure the UE with a relaxation strategy, for example, different relaxation levels for different target arrivals. In another example, the source network node may also configure the RRM relaxation boundary based on its own prediction.

[0149] In one aspect, the source network node may allow the UE to use RRM prediction for a certain measurement object. That is, the source network node may instruct the UE to determine the RRM measurement relaxation based on at least one mobility-related prediction associated with the UE derived at 864. In one aspect, the permission may be configured separately for different scenarios. That is, the source network node may configure different configurations for the RRM measurement of the UE based on different scenarios. For example, the source network node may configure the UE with a first configuration based on conventional RRM measurements when the UE is in RRCCONNECTED mode, a second configuration for RRM measurements when the UE is in RRCIDLE mode or RRCINACTIVE mode, and a third configuration for triggering or performing RRM measurements for CHO. In addition, RRM measurements may be configured differently for inter-RAT or inter-frequency RRM measurements.

[0150] At 864, the UE 802 may utilize at least one neural network of the UE 802 to derive at least one mobility-related prediction associated with the UE 802. That is, the UE 802 may have at least one neural network, and the UE 802 may utilize the at least one neural network to derive at least one mobility-related prediction associated with the UE 802. The at least one mobility-related prediction associated with the UE may include at least one of a UE trajectory prediction, a UE traffic prediction, an RRM measurement prediction, or a UE location and a mobility state.

[0151] At 866, the source network node may configure a machine learning model for the UE to decide RRM prediction and relaxation. That is, the UE may include a machine learning model for predicting or relaxing RRM measurements, and the source network node may configure the UE's machine learning model for predicting or relaxing RRM measurements.

[0152] At 868, the UE may generate relaxed RRM measurements. In one aspect, the UE may generate relaxed RRM measurements based on a configuration to the UE for at least one parameter to determine to relax RRM measurements at the UE for each of the at least one target network node as received at 862. In another aspect, the UE may generate relaxed RRM measurements based on at least one mobility-related prediction associated with the UE derived at 864.

[0153] On the other hand, the output of the machine learning model for generating relaxed RRM measurements may include at least one of predicted RRM measurements or recommended target network nodes to be measured and an RRM relaxation level for each target network node. Here, at least one of the predicted RRM measurements or recommended target network nodes may be derived based on the configuration of the machine learning model for the UE received at 866.

[0154] At 870, the UE may send a relaxed RRM measurement. The relaxed RRM measurement may refer to an RRM measurement for which at least one configuration is relaxed. The at least one configuration of the RRM measurement to be relaxed may include at least one of a sampling rate, a filter coefficient, a reporting configuration, and the like.

[0155] In one aspect, the UE may generate the relaxed RRM measurement based on a configuration to the UE for determining at least one parameter to relax RRM measurements at the UE for each of the at least one target network node as received at 862. In another aspect, the UE may generate the relaxed RRM measurement based on at least one mobility-related prediction associated with the UE derived at 864.

[0156] On the other hand, the output of the machine learning model for generating relaxed RRM measurements may include at least one of the predicted RRM measurements or the recommended target network nodes to be measured and the RRM relaxation level for each target network node. Here, instead of the actual RRM measurement, the UE may include at least one flag indicating the prediction result and / or the confidence level in the measurement report so that the UE indicates that the reported measurement is based on the prediction. That is, the RRM measurement may be based on the prediction of mobility or the confidence level of the prediction.

[0157] Fig. 9 Flowchart 900 of a method of wireless communication. The method may be performed by a UE (e.g., UE 104 / 502 / 602 / 702 / 802; device 1504). The UE may be configured to: obtain at least one mobility-related prediction associated with the UE or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network; and handover from a source network node to a first target network node of at least one target network node based on the at least one mobility-related prediction.

[0158] At 960, the UE may receive an instruction to relax at least one parameter of RRM measurements for each of at least one target network node at the UE. For example, at 860, the UE 802 may receive an instruction to relax at least one parameter of RRM measurements for each of at least one target network node at the UE. In addition, 960 may be performed by the AI / ML-based mobility-related prediction component 198.

[0159] At 962, the UE may receive from the source network node at least one configuration for determining at least one parameter to relax RRM measurements for each of at least one target network node at the UE. Here, at least one configuration may be associated with at least one measurement object of the UE. For example, at 862, the UE 802 may receive from the source network node at least one configuration for determining at least one parameter to relax RRM measurements for each of at least one target network node at the UE. In addition, 962 may be performed by the mobility-related prediction component 198 based on AI / ML.

[0160] At 964, the UE may derive at least one mobility-related prediction associated with the UE. For example, at 864, the UE 802 may derive at least one mobility-related prediction associated with the UE. In addition, 964 may be performed by the AI / ML-based mobility-related prediction component 198.

[0161] At 966, the UE may receive at least one parameter for the machine learning model for the UE to determine the RRM prediction and at least one parameter for the RRM measurement. For example, at 866, the UE 802 may receive at least one parameter for the machine learning model for the UE to determine the RRM prediction and at least one parameter for the RRM measurement. In addition, 966 may be performed by the AI / ML-based mobility-related prediction component 198.

[0162] At 968, the UE may generate a relaxed RRM measurement. For example, at 868, the UE 802 may generate a relaxed RRM measurement. In addition, 968 may be performed by the AI / ML-based mobility-related prediction component 198.

[0163] At 970, the UE may send a relaxed RRM measurement report. Here, the relaxed RRM measurement report may include at least one flag indicating that the RRM measurement is based on a prediction of mobility or a confidence level of the prediction. For example, at 870, the UE 802 may send an RRM measurement report. In addition, 970 may be performed by the AI / ML-based mobility-related prediction component 198.

[0164] At 910, the UE may send RRM measurements to the source network node. For example, at 510 / 610 / 710, the UE 502 / 602 / 702 may send RRM measurements to the source network node. In addition, 910 may be performed by the AI / ML-based mobility-related prediction component 198.

[0165] At 913, the UE may obtain at least one mobility-related prediction associated with the UE or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network. In one example, the at least one mobility-related prediction associated with the UE may include at least one of a UE trajectory prediction, a UE traffic prediction, an RRM measurement prediction, or a UE location and a mobility state. In another example, the at least one mobility-related prediction associated with the at least one target network node may include at least one of a prediction of network resource capacity (including PRB / TNL) or a reachable QoS / QoE at the at least one target network node after handing over the UE from the source network node to the target network node. In one aspect, the at least one mobility-related prediction associated with the UE may be obtained by the UE using at least one neural network of the UE to derive the at least one mobility-related prediction associated with the UE. In another aspect, the at least one mobility-related prediction associated with the UE or at least one target network node may be received from the source network node. The at least one mobility-related prediction associated with the UE or at least one target network node may be received in a handover command from the source network node. 913 may include 914 and 950. For example, 953 may be performed by the AI / ML based mobility related prediction component 198 .

[0166] At 914, the UE may use at least one neural network of the UE to derive at least one mobility-related prediction associated with the UE. For example, at 514 / 614 / 714, the UE 502 / 602 / 702 may use at least one neural network of the UE to derive at least one mobility-related prediction associated with the UE. In addition, 914 may be performed by the AI / ML-based mobility-related prediction component 198.

[0167] At 950, the UE may receive a handover command from the source network node. Here, the handover command may include at least one mobility-related prediction, and the handover command may include at least one parameter for the UE's machine learning model to select a first target network node from at least one target network node. For example, at 550 / 650 / 750, the UE 502 / 602 / 702 may receive a handover command from the source network node. In addition, 950 may be performed by the AI / ML-based mobility-related prediction component 198.

[0168] At 916, the UE may send at least one mobility-related prediction to the source network node. For example, at 516 / 616 / 716, the UE 502 / 602 / 702 may send at least one mobility-related prediction to the source network node. In addition, 916 may be performed by the AI / ML-based mobility-related prediction component 198.

[0169] At 952, the UE may choose to switch from at least one target network node to a first target network node based on at least one mobility-related prediction. The UE may choose to switch to the target network node based on selecting a target resource configuration associated with the target network node. The target resource configuration associated with the target network node may include a first cell or a target beam associated with the target network node. Here, the UE may choose to switch from at least one target network node to the first target network node based on a machine learning model. The input of the machine learning includes at least one of radio measurements, auxiliary information from the source network node, and location / motion sensor measurements of the UE, and the output of the machine learning includes at least one of a target cell to trigger handover, a target cell to perform handover, or a target cell to be measured. For example, at 552 / 652 / 752, the UE 502 / 602 / 702 may choose to switch from at least one target network node to the first target network node based on at least one mobility-related prediction. In addition, 952 may be performed by a mobility-related prediction component 198 based on AI / ML.

[0170] At 954, the UE may switch from the source network node to a first target network node in at least one target network node based on at least one mobility-related prediction. 954 may include 956. At 954, the UE may send an RRC reconfiguration message to the target network node to establish a new RRC connection with the target network node to perform a handover of the UE from the source network node to the target network node. The RRC message may include an indication of a target resource configuration associated with the first target network node. For example, at 554 / 654 / 754, the UE 502 / 602 / 702 may switch from the source network node to a first target network node in at least one target network node based on at least one mobility-related prediction. In addition, 954 and 956 may be performed by an AI / ML-based mobility-related prediction component 198.

[0171] Fig.101000 is a flow chart of a method of wireless communication. The method may be performed by a UE (e.g., UE 104 / 502 / 602 / 702 / 802; apparatus 1504). The UE may be configured to: obtain at least one mobility-related prediction associated with the UE or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network; and perform handover from a source network node to a first target network node of at least one target network node based on the at least one mobility-related prediction.

[0172] At 1013, the UE may obtain at least one mobility-related prediction associated with the UE or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network. In one example, the at least one mobility-related prediction associated with the UE may include at least one of a UE trajectory prediction, a UE traffic prediction, an RRM measurement prediction, or a UE location and a mobility state. In another example, the at least one mobility-related prediction associated with at least one target network node may include at least one of a prediction of network resource capacity (including PRB / TNL) or a reachable QoS / QoE at at least one target network node after handing over the UE from the source network node to the target network node. In one aspect, the at least one mobility-related prediction associated with the UE may be obtained by the UE using at least one neural network of the UE to derive at least one mobility-related prediction associated with the UE. On the other hand, at least one mobility-related prediction associated with the UE or at least one target network node may be received from the source network node. At least one mobility-related prediction associated with the UE or at least one target network node may be received in a handover command from the source network node. For example, 1013 may be performed by an AI / ML-based mobility-related prediction component 198.

[0173] At 1054, the UE may switch from the source network node to a first target network node in at least one target network node based on at least one mobility-related prediction. Here, the first target network node may be associated with a target resource configuration selected based on at least one mobility-related prediction. The target resource configuration associated with the target network node may include a first cell or a target beam associated with the target network node. The UE may send an RRC reconfiguration message to the target network node to establish a new RRC connection with the target network node to perform a handover of the UE from the source network node to the target network node. The RRC message may include an indication of the target resource configuration associated with the first target network node. For example, at 554 / 654 / 754, the UE 502 / 602 / 702 may switch from the source network node to the first target network node in at least one target network node based on at least one mobility-related prediction. In addition, 1054 may be performed by an AI / ML-based mobility-related prediction component 198.

[0174] Fig.11 1100 is a flow chart of a method of wireless communication. The method may be performed by a source network node (e.g., base station 102; source network node 504 / 604 / 704 / 804; network entity 1602). The source network node may be configured to: obtain at least one mobility-related prediction associated with a UE or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network; and hand over the UE from the source network node to at least one target network node based on the at least one mobility-related prediction.

[0175] At 1160, the source network node may send an instruction to relax at least one parameter of RRM measurement for each of the at least one target network node at the UE. For example, at 860, the source network node 804 may send an instruction to relax at least one parameter of RRM measurement for each of the at least one target network node at the UE. In addition, 1160 may be performed by the AI / ML-based mobility prediction component 199.

[0176] At 1162, the source network node may send at least one configuration from the source network node for determining at least one parameter to relax RRM measurements for each of at least one target network node at the UE. Here, at least one configuration may be associated with at least one measurement object of the UE. For example, at 862, the source network node 804 may send at least one configuration from the source network node for determining at least one parameter to relax RRM measurements for each of at least one target network node at the UE. In addition, 1162 may be performed by the AI / ML-based mobility prediction component 199.

[0177] At 1166, the source network node may send at least one parameter for the machine learning model for the UE to determine the RRM prediction and at least one parameter for the RRM measurement. For example, at 866, the source network node 804 may send at least one parameter for the machine learning model for the UE to determine the RRM prediction and at least one parameter for the RRM measurement. In addition, 1166 may be performed by the AI / ML-based mobility prediction component 199.

[0178] At 1170, the source network node may receive a relaxed RRM measurement report. Here, the relaxed RRM measurement report may include at least one flag indicating that the RRM measurement is based on a prediction of mobility or a confidence level of the prediction. For example, at 870, the source network node 804 may receive a relaxed RRM measurement report. In addition, 1170 may be performed by the mobility prediction component 199 based on AI / ML.

[0179] At 1110, the source network node may receive RRM measurements of the source network node. For example, at 510 / 610 / 710, the source network node 504 / 604 / 704 may receive RRM measurements of the source network node. In addition, 1110 may be performed by the AI / ML-based mobility prediction component 199.

[0180] At 1111, the source network node may obtain at least one mobility-related prediction associated with the UE or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network. In one example, the at least one mobility-related prediction may be associated with the UE and include at least one of a UE trajectory prediction, a UE traffic prediction, an RRM measurement prediction, or a UE location and a mobility state. In another example, the at least one mobility-related prediction may be associated with at least one target network node and include at least one of a prediction of network resource capacity (including PRB / TNL) or a achievable QoS / QoE at at least one target network node after handing over the UE from the source network node to the target network node. In one aspect, the at least one mobility-related prediction associated with the UE may be obtained by the source network node using at least one neural network of the source network node to derive the at least one mobility-related prediction associated with the UE. On the other hand, at 1116, at least one mobility-related prediction associated with the UE may be received from the UE. On the other hand, at 1140, at least one mobility-related prediction associated with at least one target network node may be received from the target network node or from the core network. 1111 may include 1112 and 1116. For example, 1111 may be performed by the mobility prediction component 199 based on AI / ML.

[0181] At 1112, the source network node may use at least one neural network of the source network node to derive at least one mobility-related prediction associated with the UE. For example, at 512 / 612 / 712, the source network node 504 / 604 / 704 may use at least one neural network of the source network node to derive at least one mobility-related prediction associated with the UE. In addition, 1112 may be performed by the AI / ML-based mobility prediction component 199.

[0182] At 1116, the source network node may receive at least one mobility-related prediction associated with the UE from the UE, the at least one mobility-related prediction associated with the UE being derived by at least one neural network of the UE. For example, at 516 / 516 / 616 / 716, the source network node 504 / 604 / 704 may receive at least one mobility-related prediction associated with the UE from the UE. In addition, 1116 may be performed by the AI / ML-based mobility prediction component 199.

[0183] At 1120, the source network node may send a handover message including at least one mobility-related prediction associated with the UE. In one example, the handover message may be a handover request sent to the target network node. In another example, the handover message may be a handover requirement message sent to the core network. At least one mobility-related prediction associated with the UE may be included in a container (e.g., a source-to-target transparent container IE) to the target network node, and the handover requirement message sent to the core network may include a container with at least one mobility-related prediction associated with the UE. For example, at 520 / 520 / 620 / 720, the source network node 504 / 604 / 704 may send a handover message including at least one mobility-related prediction associated with the UE. In addition, 1120 may be performed by an AI / ML-based mobility prediction component 199.

[0184] At 1140, the source network node may receive a handover request ACK or a handover command. In one example, based on sending a handover request to the target network node, the source network node may receive a handover request ACK from the target network node. In another example, based on sending a handover requirement message to the core network, the source network node may receive a handover command from the core network. At least one mobility-related prediction associated with at least one target network node may be included in a container (e.g., a target-to-source transparent container IE) from the target network node, and the handover command received from the core network may include a container with at least one mobility-related prediction associated with at least one target network node. For example, at 540 / 540 / 640 / 740, the source network node 504 / 604 / 704 may receive a handover request ACK or a handover command. In addition, 1140 may be performed by an AI / ML-based mobility prediction component 199.

[0185] At 1150, the source network node may send a handover command to the UE. Here, the handover command may include at least one mobility-related prediction, and the handover command may include at least one parameter for the machine learning model of the UE to select a first target network node from at least one target network node. For example, at 550 / 550 / 650 / 750, the source network node 504 / 604 / 704 may send a handover command to the UE. In addition, 1150 may be performed by an AI / ML-based mobility prediction component 199.

[0186] Fig.121200 is a flow chart of a method of wireless communication. The method may be performed by a source network node (e.g., base station 102; source network node 504 / 604 / 704 / 804; network entity 1602). The source network node may be configured to: obtain at least one mobility-related prediction associated with a UE or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network; and hand over the UE from the source network node to at least one target network node based on the at least one mobility-related prediction.

[0187] At 1211, the source network node may obtain at least one mobility-related prediction associated with the UE or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network. In one example, the at least one mobility-related prediction may be associated with the UE and include at least one of a UE trajectory prediction, a UE traffic prediction, an RRM measurement prediction, or a UE location and a mobility state. In another example, the at least one mobility-related prediction may be associated with at least one target network node and include at least one of a prediction of network resource capacity (including PRB / TNL) or a achievable QoS / QoE at at least one target network node after handing over the UE from the source network node to the target network node. In one aspect, the at least one mobility-related prediction associated with the UE may be obtained by the source network node using at least one neural network of the source network node to derive the at least one mobility-related prediction associated with the UE. On the other hand, at 1216, at least one mobility-related prediction associated with the UE may be received from the UE. On the other hand, at 1240, at least one mobility-related prediction associated with at least one target network node may be received from the target network node or from the core network. 1211 may include 1212 and 1216. For example, 1211 may be performed by the AI / ML-based mobility prediction component 199.

[0188] At 1250, the source network node may send a handover command to the UE. Here, the handover command may include at least one mobility-related prediction, and the handover command may include at least one parameter for the machine learning model of the UE to select a first target network node from at least one target network node. For example, at 550 / 550 / 650 / 750, the source network node 504 / 604 / 704 may send a handover command to the UE. In addition, 1250 may be performed by the AI / ML-based mobility prediction component 199.

[0189] Fig.131300 is a flow chart of a method of wireless communication. The method may be performed by a target network node (e.g., base station 102; target network node 506 / 606 / 706 / 707; network entity 1602). The target network node may be configured to: receive a handover request to hand over a UE from a source network node; obtain at least one mobility-related prediction associated with the UE or the target network node, the at least one mobility-related prediction being derived by at least one neural network; and output a handover request ACK for transmission, the handover request ACK being based at least in part on the at least one mobility-related prediction.

[0190] At 1318, the target network node may obtain at least one mobility-related prediction associated with the UE or the target network node, the at least one mobility-related prediction being derived by at least one neural network. In one example, the at least one mobility-related prediction associated with the UE may include at least one of a UE trajectory prediction, a UE traffic prediction, an RRM measurement prediction, or a UE location and a mobility state. In another example, the at least one mobility-related prediction associated with at least one target network node may include at least one of a prediction of network resource capacity (including PRB / TNL) or a achievable QoS / QoE at at least one target network node after handing over the UE from the source network node to the target network node. In one aspect, the at least one mobility-related prediction associated with the UE may be obtained by the target network node receiving at least one mobility-related prediction associated with the UE from the source network node. In another aspect, the at least one mobility-related prediction associated with the target network node may be obtained by the target network using at least one neural network of the target network node to derive at least one mobility-related prediction associated with the target network node. 1318 may include 1320, 1322, and 1330. For example, 1318 may be performed by the AI / ML based mobility prediction component 199 .

[0191] At 1320, the target network node may receive a handover request from the source network node to hand over the UE from the source network node to the target network node. For example, at 520 / 720, the target network node 506 / 706 / 707 may receive a handover request from the source network node to hand over the UE from the source network node to the target network node. In addition, 1320 may be performed by the AI / ML-based mobility prediction component 199.

[0192] At 1322, the target network node may receive a handover request from the core network to hand over the UE from the source network node to the target network node. At least one mobility-related prediction associated with the UE may be included in a container (e.g., a source-to-target transparent container IE) from the source network node, and the handover request received from the core network may include a container with at least one mobility-related prediction associated with the UE. For example, at 622, the target network node 606 may receive a handover request from the core network to hand over the UE from the source network node to the target network node. In addition, 1322 may be performed by the AI / ML-based mobility prediction component 199.

[0193] At 1330, the target network node may use at least one neural network of the target network node to derive at least one mobility-related prediction associated with the target network node. For example, at 530 / 630 / 730, the target network node 506 / 606 / 706 / 707 may use at least one neural network of the target network node to derive at least one mobility-related prediction associated with the target network node. In addition, 1330 may be performed by the AI / ML-based mobility prediction component 199.

[0194] At 1332, the target network node may send a handover request ACK to the core network to hand over the UE from the source network node. At least one mobility-related prediction associated with at least one target network node may be included in a container (e.g., a target-to-source transparent container IE) to the source network node, and the handover request ACK sent to the core network may include a container with at least one mobility-related prediction associated with at least one target network node. For example, at 532 / 632 / 732, the target network node 506 / 606 / 706 / 707 may send a handover request ACK to the core network to hand over the UE from the source network node. In addition, 1332 may be performed by an AI / ML-based mobility prediction component 199.

[0195] At 1340, the target network node may send a handover request ACK to the source network node to hand over the UE from the source network node. For example, at 540 / 640 / 740, the target network node 506 / 606 / 706 / 707 may send a handover request ACK to the source network node to hand over the UE from the source network node. In addition, 1340 may be performed by the AI / ML-based mobility prediction component 199.

[0196] At 1354, the target network node may receive from the UE an RRC reconfiguration for handing over the UE from the source network node to the target network node. For example, at 554 / 654 / 754, the target network node 506 / 606 / 706 / 707 may receive from the UE an RRC reconfiguration for handing over the UE from the source network node to the target network node. In addition, 1354 may be performed by the AI / ML-based mobility prediction component 199.

[0197] Fig.14 1400 is a flow chart of a method of wireless communication. The method may be performed by a target network node (e.g., base station 102; target network node 506 / 606 / 706 / 707; network entity 1602). The target network node may be configured to: receive a handover request to hand over a UE from a source network node; obtain at least one mobility-related prediction associated with the UE or the target network node, the at least one mobility-related prediction being derived by at least one neural network; and output a handover request ACK for transmission, the handover request ACK being based at least in part on the at least one mobility-related prediction.

[0198] At 1418, the target network node may obtain at least one mobility-related prediction associated with the UE or the target network node, the at least one mobility-related prediction being derived by at least one neural network. In one example, the at least one mobility-related prediction associated with the UE may include at least one of a UE trajectory prediction, a UE traffic prediction, an RRM measurement prediction, or a UE location and a mobility state. In another example, the at least one mobility-related prediction associated with at least one target network node may include at least one of a prediction of network resource capacity (including PRB / TNL) or a achievable QoS / QoE at at least one target network node after handing over the UE from the source network node to the target network node. In one aspect, the at least one mobility-related prediction associated with the UE may be obtained by the target network node receiving at least one mobility-related prediction associated with the UE from the source network node. In another aspect, the at least one mobility-related prediction associated with the target network node may be obtained by the target network using at least one neural network of the target network node to derive at least one mobility-related prediction associated with the target network node. 1418 may include 1420, 1422, and 1430. For example, 1418 may be performed by the AI / ML based mobility prediction component 199 .

[0199] At 1440, the target network node may send a handover request ACK to the source network node to hand over the UE from the source network node. For example, at 540 / 640 / 740, the target network node 506 / 606 / 706 / 707 may send a handover request ACK to the source network node to hand over the UE from the source network node. In addition, 1440 may be performed by the AI / ML-based mobility prediction component 199.

[0200] Fig.151500 is a diagram illustrating an example of a hardware implementation for an apparatus 1504. The apparatus 1504 may be a UE, a component of a UE, or may implement UE functionality. In some aspects, the apparatus 1504 may include a cellular baseband processor 1524 (also referred to as a modem) coupled to one or more transceivers 1522 (e.g., a cellular RF transceiver). The cellular baseband processor 1524 may include on-chip memory 1524'. In some aspects, the apparatus 1504 may also include one or more subscriber identity module (SIM) cards 1520 and an application processor 1506 coupled to a secure digital (SD) card 1508 and a screen 1510. The application processor 1506 may include on-chip memory 1506'. In some aspects, the device 1504 may also include a Bluetooth module 1512, a WLAN module 1514, an SPS module 1516 (e.g., a GNSS module), one or more sensor modules 1518 (e.g., an atmospheric pressure sensor / altimeter; a motion sensor such as an inertial management unit (IMU), a gyroscope, and / or an accelerometer; light detection and ranging (LIDAR), radio-aided detection and ranging (RADAR), sound navigation and ranging (SONAR), a magnetometer, audio, and / or other technologies for positioning), an additional memory module 1526, a power source 1530, and / or a camera 1532. The Bluetooth module 1512, the WLAN module 1514, and the SPS module 1516 may include an on-chip transceiver (TRX) (or in some cases, only a receiver (RX)). The Bluetooth module 1512, the WLAN module 1514, and the SPS module 1516 may include their own dedicated antennas and / or communicate using antennas 1580. The cellular baseband processor 1524 communicates with the UE 104 and / or with the RU associated with the network entity 1502 through the transceiver 1522 via one or more antennas 1580. The cellular baseband processor 1524 and the application processor 1506 may each include a computer-readable medium / memory 1524', 1506', respectively. The additional memory module 1526 may also be considered as a computer-readable medium / memory. Each computer-readable medium / memory 1524', 1506', 1526 may be non-transitory. The cellular baseband processor 1524 and the application processor 1506 are each responsible for general processing, including executing software stored on a computer-readable medium / memory. The software enables the cellular baseband processor 1524 / application processor 1506 to perform the various functions described above when executed by the cellular baseband processor 1524 / application processor 1506. The computer-readable medium / memory can also be used to store data manipulated by the cellular baseband processor 1524 / application processor 1506 when executing the software.The cellular baseband processor 1524 / application processor 1506 may be a component of the UE 350 and may include the memory 360 and / or at least one of the TX processor 368, the RX processor 356, and the controller / processor 359. In one configuration, the device 1504 may be a processor chip (modem and / or application) and include only the cellular baseband processor 1524 and / or the application processor 1506, and in another configuration, the device 1504 may be the entire UE (e.g., see. Figure 3 350) and includes additional modules of device 1504.

[0201] As discussed above, the AI / ML-based mobility-related prediction component 198 is configured to: obtain at least one mobility-related prediction associated with the UE or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network; and switch from the source network node to a first target network node among the at least one target network node based on the at least one mobility-related prediction. The AI / ML-based mobility-related prediction component 198 may be within the cellular baseband processor 1524, the application processor 1506, or both the cellular baseband processor 1524 and the application processor 1506. The AI / ML-based mobility-related prediction component 198 may be one or more hardware components that are specifically configured to execute the process / algorithm, implemented by one or more processors configured to execute the process / algorithm, stored in a computer-readable medium for implementation by one or more processors, or some combination thereof. As shown, the device 1504 may include a variety of components configured for various functions. In one configuration, the apparatus 1504 and in particular the cellular baseband processor 1524 and / or the application processor 1506 include: means for obtaining at least one mobility-related prediction associated with the UE or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network; and means for handing over from the source network node to a first target network node of the at least one target network node, the first target network node being associated with a target resource configuration selected based on the at least one mobility-related prediction. In one configuration, the at least one mobility-related prediction is associated with the UE and includes at least one of a UE trajectory prediction, a UE traffic prediction, an RRM measurement prediction, or a UE location and mobility state, and wherein the means for obtaining the at least one mobility-related prediction is further configured to derive the at least one mobility-related prediction associated with the UE using at least one neural network of the UE. In one configuration, the apparatus 1504 and in particular the cellular baseband processor 1524 and / or the application processor 1506 also include means for sending the at least one mobility-related prediction to the source network node. In one configuration, the at least one mobility-related prediction is associated with at least one target network node and includes at least one of a prediction of network resource capacity (including PRB / TNL) or a achievable QoS / QoE at the at least one target network node after handing over the UE from the source network node to the target network node, and the means for obtaining the at least one mobility-related prediction also includes receiving at least one mobility-related prediction associated with the at least one target network node from the source network node. In one configuration, the apparatus 1504 and in particular the cellular baseband processor 1524 and / or the application processor 1506 also include means for receiving a handover command from the source network node, the handover command including the at least one mobility-related prediction.In one configuration, the apparatus 1504 and in particular the cellular baseband processor 1524 and / or the application processor 1506 further comprises means for selecting a handover from at least one target network node to a first target network node based on the at least one mobility-related prediction. In one configuration, the apparatus 1504 and in particular the cellular baseband processor 1524 and / or the application processor 1506 further comprises: means for receiving a handover command for the UE, the handover command comprising at least one parameter for a machine learning model of the UE to select a first target network node from at least one target network node; and means for selecting a target resource configuration associated with the first target network node from the at least one target network node based on the machine learning model, wherein the input of the machine learning comprises at least one of radio measurements, assistance information from the source network node, and location / motion sensor measurements of the UE, and the output of the machine learning comprises at least one of a target cell to trigger the handover, a target cell to perform the handover, and a target cell to measure. In one configuration, the apparatus 1504 and in particular the cellular baseband processor 1524 and / or the application processor 1506 further include means for sending an RRC message indicating a target resource configuration associated with the first target network node to the target network node. In one configuration, the apparatus 1504 and in particular the cellular baseband processor 1524 and / or the application processor 1506 further include means for receiving an instruction to relax at least one parameter of RRM measurement for each of at least one target network node at the UE. In one configuration, the apparatus 1504 and in particular the cellular baseband processor 1524 and / or the application processor 1506 further include means for receiving from the source network node at least one configuration for determining at least one parameter of RRM measurement for each of at least one target network node at the UE to be relaxed. In one configuration, the at least one configuration is associated with at least one measurement object of the UE. In one configuration, the device 1504 and in particular the cellular baseband processor 1524 and / or the application processor 1506 further include means for sending an RRM measurement report including at least one flag indicating that the RRM measurement is based on a prediction of mobility or a confidence level of the prediction. In one configuration, the device 1504 and in particular the cellular baseband processor 1524 and / or the application processor 1506 further include means for receiving at least one parameter for a machine learning model for the UE to determine the RRM prediction and at least one parameter of the RRM measurement. The means may be an AI / ML-based mobility-related prediction component 198 of the device 1504 configured to perform the functions recorded by the means. As described above, the device 1504 may include a TX processor 368, an RX processor 356, and a controller / processor 359.Thus, in one configuration, the means may be the TX processor 368, the RX processor 356, and / or the controller / processor 359 configured to perform the functions recited by the means.

[0202] Fig.16 1600 is a diagram illustrating an example of a hardware implementation for a network entity 1602. The network entity 1602 may be a BS, a component of a BS, or may implement BS functionality. The network entity 1602 may include at least one of a CU 1610, a DU 1630, or a RU 1640. For example, depending on the layer functionality handled by the AI / ML-based mobility prediction component 199, the network entity 1602 may include a CU 1610; both a CU 1610 and a DU 1630; each of the CU 1610, the DU 1630, and the RU 1640; the DU 1630; both a DU 1630 and a RU 1640; or a RU 1640. The CU 1610 may include a CU processor 1612. The CU processor 1612 may include an on-chip memory 1612'. In some aspects, the CU 1610 may also include an additional memory module 1614 and a communication interface 1618. CU 1610 communicates with DU 1630 via a midhaul link, such as an F1 interface. DU 1630 may include a DU processor 1632. DU processor 1632 may include on-chip memory 1632'. In some aspects, DU 1630 may also include additional memory modules 1634 and a communication interface 1638. DU 1630 communicates with RU 1640 via a fronthaul link. RU 1640 may include a RU processor 1642. RU processor 1642 may include on-chip memory 1642'. In some aspects, RU 1640 may also include additional memory modules 1644, one or more transceivers 1646, antenna 1680, and communication interface 1648. RU 1640 communicates with UE 104. On-chip memory 1612', 1632', 1642' and additional memory modules 1614, 1634, 1644 may each be considered a computer-readable medium / memory. Each computer readable medium / memory may be non-transitory. Each of processors 1612, 1632, 1642 is responsible for general processing, including executing software stored on the computer readable medium / memory. The software, when executed by the corresponding processor, causes the processor to perform the various functions described above. The computer readable medium / memory may also be used to store data manipulated by the processor when executing the software.

[0203] As discussed above, the AI / ML-based mobility prediction component 199 of the source network node is configured to: obtain at least one mobility-related prediction associated with the UE or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network; and hand over the UE from the source network node to the at least one target network node based on the at least one mobility-related prediction. The AI / ML-based mobility prediction component 199 of the target network node is configured to: receive a handover request to hand over the UE from the source network node; obtain at least one mobility-related prediction associated with the UE or the target network node, the at least one mobility-related prediction being derived by at least one neural network; and output a handover request ACK for transmission, the handover request ACK being based at least in part on the at least one mobility-related prediction. The AI / ML-based mobility prediction component 199 may be within one or more processors of one or more of the CU 1610, the DU 1630, and the RU 1640. The AL / ML-based mobility prediction component 199 may be one or more hardware components specifically configured to execute the process / algorithm, implemented by one or more processors configured to execute the process / algorithm, stored in a computer-readable medium for implementation by one or more processors, or some combination thereof. The network entity 1602 may include a variety of components configured for various functions. In one configuration, the network entity 1602 may be a source network entity, and the network entity 1602 includes: a component for obtaining at least one mobility-related prediction associated with a UE or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network; and a component for handing over the UE from the source network node to at least one target network node based on the at least one mobility-related prediction. In one configuration, the at least one mobility-related prediction is associated with the UE and includes at least one of a UE trajectory prediction, a UE traffic prediction, an RRM measurement prediction, or a UE location and a mobility state, and the method also includes a component for sending a handover message including at least one mobility-related prediction associated with the UE. In one configuration, the means for obtaining at least one mobility-related prediction may be configured to derive at least one mobility-related prediction associated with the UE using at least one neural network of the source network node. In one configuration, the means for obtaining at least one mobility-related prediction may be configured to receive at least one mobility-related prediction associated with the UE from the UE, the at least one mobility-related prediction associated with the UE being derived by at least one neural network of the UE. In one configuration, the handover message is a handover request to at least one target network node, and the network entity 1602 further comprises means for receiving a handover request ACK from the at least one target network node.In one configuration, the handover message is a handover requirement message to a core network, and at least one mobility-related prediction associated with the UE is included in a container for at least one target network node. In one configuration, the at least one mobility-related prediction is associated with at least one target network node and includes at least one of a prediction of network resource capacity (including PRB / TNL) or a achievable QoS / QoE at the at least one target network node after the handover, wherein the means for obtaining the at least one mobility-related prediction may be configured to receive at least one mobility-related prediction associated with the at least one target network node from the at least one target network node. In one configuration, the network entity 1602 further comprises means for sending a handover request to the at least one target network node, wherein the at least one mobility-related prediction associated with the at least one target network node is received in a handover request ACK from the at least one target network node. In one configuration, the network entity 1602 further includes a component for sending a handover requirement message to the core network, and at least one mobility-related prediction associated with at least one target network node is received in a handover command from the core network, and the at least one mobility-related prediction associated with at least one target network node is included in a container from at least one target network node. In one configuration, the network entity 1602 further includes a component for sending a handover command for the UE, the handover command including at least one mobility-related prediction. In one configuration, the method further includes a component for sending a handover command for the UE, the handover command including at least one parameter for a machine learning model for the UE to select a target resource configuration associated with a first target network node from at least one target network node. In one configuration, the network entity 1602 further includes a component for instructing the UE to relax at least one parameter of RRM measurements for each of the at least one target network node at the UE. In one configuration, the network entity 1602 further includes a component for sending at least one configuration for the UE to determine at least one parameter to relax RRM measurements for each of the at least one target network node at the UE. In one configuration, at least one configuration is associated with at least one measurement object of the UE. In one configuration, the network entity 1602 further comprises means for receiving an RRM measurement report comprising at least one flag indicating that the RRM measurement is based on a prediction or a confidence level of the prediction of the mobility. In one configuration, the network entity 1602 further comprises means for sending at least one parameter for a machine learning model for the UE to determine the RRM prediction and at least one parameter of the RRM measurement.In another configuration, the network entity 1602 may be a target network entity, and the network entity 1602 includes: a component for receiving a handover request from a source network node to handover a UE; a component for obtaining at least one mobility-related prediction associated with the UE or the target network node, the at least one mobility-related prediction being derived by at least one neural network; and a component for sending a handover request ACK, the handover request ACK being based at least in part on the at least one mobility-related prediction. In one configuration, the at least one mobility-related prediction is associated with the UE and includes at least one of a UE trajectory prediction, a UE traffic prediction, an RRM measurement prediction, or a UE location and a mobility state, and the at least one mobility-related prediction is extracted from the handover request. In one configuration, the handover request is received from a source network node. In one configuration, the handover request is received from a core network, and the at least one mobility-related prediction associated with the UE is included in a container from the source network node. In one configuration, the at least one mobility-related prediction is associated with a target network node and includes at least one of a prediction of network resource capacity (including PRB / TNL) or a achievable QoS / QoE at at least one target network node after handover, wherein the means for obtaining the at least one mobility-related prediction is configured to derive at least one mobility-related prediction associated with the target network node using at least one neural network of the target network node. In one configuration, the network entity 1602 further includes a means for sending a handover request ACK to at least one target network node. In one configuration, the network entity 1602 further includes a means for sending a handover request ACK to the core network, and at least one mobility-related prediction associated with at least one target network node is included in a container to the source network node. In one configuration, the network entity 1602 further includes a means for receiving from the UE an RRC reconfiguration for handing over the UE from the source network node to the target network node. The means may be an AI / ML-based mobility prediction component 199 of the network entity 1602 configured to perform the functions recorded by the means. As described above, the network entity 1602 may include the TX processor 316, the RX processor 370, and the controller / processor 375. Thus, in one configuration, the means may be the TX processor 316, the RX processor 370, and / or the controller / processor 375 configured to perform the functions recited by the means.

[0204] According to some aspects of the present disclosure, a UE may be configured to: obtain at least one mobility-related prediction associated with the UE or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network; and switch from a source network node to a first target network node among the at least one target network node based on the at least one mobility-related prediction. A source network node is configured to: obtain at least one mobility-related prediction associated with the UE or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network; and hand over the UE from the source network node to the at least one target network node based on the at least one mobility-related prediction. A target network node is configured to: receive a handover request to hand over the UE from the source network node; obtain at least one mobility-related prediction associated with the UE or the target network node, the at least one mobility-related prediction being derived by at least one neural network; and output a handover request ACK for transmission, the handover request ACK being based at least in part on the at least one mobility-related prediction.

[0205] It should be understood that the specific order or hierarchy of the blocks in the disclosed process / flowchart is merely an illustration of the exemplary method. It should be understood that the specific order or hierarchy of the blocks in the process / flowchart may be rearranged based on design preferences. Further, some blocks may be combined or omitted. The attached method claims provide the elements of the various blocks in a sample order, but are not limited to the specific order or hierarchy provided.

[0206] The foregoing description is provided to enable any person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects. Therefore, the claims are not limited to the various aspects described herein, but should be given the full scope consistent with the language claims. Unless otherwise specified, reference to an element in the singular form does not mean "one and only one", but "one or more". Terms such as "if", "when" and "while" do not mean a direct temporal relationship or reaction. That is, these phrases, such as "when ...", do not mean an immediate action in response to the occurrence of an action or during the occurrence of an action, but simply imply that if the conditions are met, then the action will occur, but no specific or immediate time limit is required for the occurrence of the action. The word "exemplary" is used herein to mean "used as an example, instance or illustration". Any aspect described as "exemplary" herein is not necessarily interpreted as being preferred or having advantages over other aspects. Unless otherwise specified, the term "some" refers to one or more. Combinations such as "at least one of A, B, or C", "one or more of A, B, or C", "at least one of A, B and C", "one or more of A, B, and C", and "A, B, C, or any combination thereof" include any combination of A, B, and / or C, which may include multiple A, multiple B, or multiple C. Specifically, combinations such as "at least one of A, B, or C", "one or more of A, B, or C", "at least one of A, B, and C", "one or more of A, B, and C", and "A, B, C, or any combination thereof" may be only A, only B, only C, A and B, A and C, B and C, or A and B and C, where any such combination may contain one or more members of A, B, or C. A set should be interpreted as a set of elements, where the number of elements is one or more. Thus, for a set of X, X will include one or more elements. If the first device receives data from the second device or sends data to the second device, data may be directly received / sent between the first device and the second device, or indirectly received / sent between the first device and the second device through a collection of devices. All structural and functional equivalents of the elements of the various aspects described throughout the present disclosure that are known or will be known later to a person of ordinary skill in the art are expressly incorporated herein by reference and are covered by the claims. In addition, nothing disclosed herein is intended to be dedicated to the public, regardless of whether such disclosure is explicitly stated in the claims. Words such as "module", "mechanism", "element", "device" cannot replace the word "component". Therefore, no claim element will be understood as a component plus function unless the element is explicitly stated using the phrase "component for..."

[0207] As used herein, the phrase "based on" should not be interpreted as referring to a closed set of information, one or more conditions, one or more factors, etc. In other words, the phrase "based on A" (where "A" can be information, a condition, a factor, etc.) should be interpreted as "based at least on A" unless specifically stated differently.

[0208] The following aspects are merely illustrative and may be combined with other aspects or teachings described herein without limitation.

[0209] Aspect 1 is a method for wireless communication at a source network node, the method comprising: obtaining at least one mobility-related prediction associated with a UE or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network; and handing over the UE from the source network node to the at least one target network node based on the at least one mobility-related prediction.

[0210] Aspect 2 is a method according to Aspect 1, wherein the at least one mobility-related prediction is associated with the UE and includes a UE trajectory prediction, a UE traffic prediction, an RRM measurement prediction, or at least one of a UE location and a mobility state, and the method also includes sending a handover message including the at least one mobility-related prediction associated with the UE.

[0211] Aspect 3 is a method according to aspect 2, wherein obtaining the at least one mobility-related prediction further comprises using the at least one neural network of the source network node to derive the at least one mobility-related prediction associated with the UE.

[0212] Aspect 4 is a method according to any one of Aspect 2 and Aspect 3, wherein obtaining the at least one mobility-related prediction also includes receiving the at least one mobility-related prediction associated with the UE from the UE, and the at least one mobility-related prediction associated with the UE is derived by the at least one neural network of the UE.

[0213] Aspect 5 is a method according to any one of aspects 2 to 4, wherein the handover message is a handover request to the at least one target network node, and the method further comprises receiving a handover request ACK from the at least one target network node.

[0214] Aspect 6 is a method according to any one of aspects 2 to 5, wherein the handover message is a handover requirement message to a core network, and the at least one mobility-related prediction associated with the UE is included in a container for the at least one target network node.

[0215] Aspect 7 is a method according to any one of Aspects 1 to 6, wherein the at least one mobility-related prediction is associated with the at least one target network node and includes a prediction of network resource capacity (including PRB / TNL) or at least one of the achievable QoS / QoE at the at least one target network node after the handover, wherein obtaining the at least one mobility-related prediction also includes receiving the at least one mobility-related prediction associated with the at least one target network node from the at least one target network node.

[0216] Aspect 8 is a method according to aspect 7, wherein the method further comprises sending a handover request to the at least one target network node, wherein the at least one mobility-related prediction associated with the at least one target network node is received in a handover request ACK from the at least one target network node.

[0217] Aspect 9 is a method according to any one of Aspect 7 and Aspect 8, wherein the method also includes sending a handover requirement message to a core network, and the at least one mobility-related prediction associated with the at least one target network node is received in a handover command from the core network, and the at least one mobility-related prediction associated with the at least one target network node is included in a container from the at least one target network node.

[0218] Aspect 10 is a method according to any one of aspects 1 to 9, wherein the method further comprises sending a handover command for the UE, the handover command comprising the at least one mobility-related prediction.

[0219] Aspect 11 is a method according to any one of Aspects 1 to 3, wherein the method also includes sending a handover command for the UE, the handover command including at least one parameter for a machine learning model for the UE to select a target resource configuration associated with a first target network node from the at least one target network node.

[0220] Aspect 12 is a method according to any one of aspects 1 to 3, wherein the method further comprises instructing the UE to relax at least one parameter of RRM measurement at the UE for each of the at least one target network node.

[0221] Aspect 13 is a method according to aspect 12, wherein the method further comprises sending at least one configuration for the UE to determine at least one parameter for relaxing the RRM measurement for each of the at least one target network node at the UE.

[0222] Aspect 14 is a method according to aspect 13, wherein the at least one configuration is associated with at least one measurement object of the UE.

[0223] Aspect 15 is a method according to any one of aspects 13 and 14, wherein the method further comprises receiving an RRM measurement report, the RRM measurement report comprising at least one flag indicating that the RRM measurement is based on a prediction of mobility or a confidence level of the prediction.

[0224] Aspect 16 is a method according to any one of Aspects 12 to 15, wherein the method further comprises sending at least one parameter for a machine learning model for the UE to determine RRM prediction and the at least one parameter of the RRM measurement.

[0225] Aspect 17 is an apparatus for wireless communication, the apparatus comprising: at least one processor, the at least one processor being coupled to a memory and configured to implement any one of aspects 1 to 16, the apparatus further comprising a transceiver coupled to the at least one processor.

[0226] Aspect 18 is an apparatus for wireless communication, the apparatus comprising means for implementing any one of aspects 1 to 16.

[0227] Aspect 19 is a non-transitory computer readable medium storing computer executable code, wherein the code, when executed by a processor, causes the processor to implement any one of aspects 1 to 16.

[0228] Aspect 20 is a method for performing wireless communications at a target network node, the method comprising: receiving a handover request from a source network node to hand over a UE; obtaining at least one mobility-related prediction associated with the UE or the target network node, the at least one mobility-related prediction being derived by at least one neural network; and sending a handover request ACK, the handover request ACK being based at least in part on the at least one mobility-related prediction.

[0229] Aspect 21 is a method according to aspect 20, wherein the at least one mobility-related prediction is associated with the UE and includes at least one of a UE trajectory prediction, a UE traffic prediction, an RRM measurement prediction, or a UE location and mobility state, and the at least one mobility-related prediction is extracted from the handover request.

[0230] Aspect 22 is a method according to aspect 21, wherein the handover request is received from the source network node.

[0231] Aspect 23 is a method according to any one of Aspect 21 and Aspect 22, wherein the handover request is received from a core network and the at least one mobility-related prediction associated with the UE is included in a container from the source network node.

[0232] Aspect 24 is a method according to any one of Aspects 20 to 23, wherein the at least one mobility-related prediction is associated with the target network node and includes a prediction of network resource capacity (including PRB / TNL) or at least one of the achievable QoS / QoE at the at least one target network node after the handover, and obtaining the at least one mobility-related prediction also includes using the at least one neural network of the target network node to derive the at least one mobility-related prediction associated with the target network node.

[0233] Aspect 25 is a method according to aspect 24, wherein the method further comprises sending a handover request ACK to the at least one target network node.

[0234] Aspect 26 is a method according to any one of aspects 24 and 25, wherein the method further comprises sending a handover request ACK to a core network, the at least one mobility-related prediction associated with the at least one target network node being included in a container to the source network node.

[0235] Aspect 27 is a method according to any one of aspects 20 to 26, wherein the method further comprises receiving, from the UE, an RRC reconfiguration for handing over the UE from the source network node to the target network node.

[0236] Aspect 28 is an apparatus for wireless communication, the apparatus comprising: at least one processor, the at least one processor coupled to a memory and configured to implement any one of aspects 20 to 27, the apparatus further comprising a transceiver coupled to the at least one processor.

[0237] Aspect 29 is an apparatus for wireless communication, the apparatus comprising means for implementing any one of aspects 20 to 27.

[0238] Aspect 30 is a non-transitory computer readable medium storing computer executable code, wherein the code, when executed by a processor, causes the processor to implement any one of aspects 20 to 27.

[0239] Aspect 31 is a method for performing wireless communication at a UE, the method comprising: obtaining at least one mobility-related prediction associated with the UE or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network; and switching from a source network node to a first target network node among the at least one target network node, the first target network node being associated with a target resource configuration selected based on the at least one mobility-related prediction.

[0240] Aspect 32 is a method according to aspect 31, wherein the at least one mobility-related prediction is associated with the UE and includes a UE trajectory prediction, a UE traffic prediction, an RRM measurement prediction, or at least one of a UE location and mobility state, and obtaining the at least one mobility-related prediction also includes using the at least one neural network of the UE to derive the at least one mobility-related prediction associated with the UE.

[0241] Aspect 33 is a method according to any one of aspects 31 and 32, wherein the method further comprises sending the at least one mobility-related prediction to the source network node.

[0242] Aspect 34 is a method according to any one of aspects 31 to 33, wherein the at least one mobility-related prediction is associated with the at least one target network node and includes a prediction of network resource capacity (including PRB / TNL) or at least one of the achievable QoS / QoE at the at least one target network node after handing over the UE from the source network node to the target network node, and obtaining the at least one mobility-related prediction also includes receiving the at least one mobility-related prediction associated with the at least one target network node from the source network node.

[0243] Aspect 35 is a method according to any one of aspects 31 to 34, wherein the method further comprises receiving a handover command from the source network node, the handover command comprising the at least one mobility-related prediction.

[0244] Aspect 36 is a method according to aspect 35, wherein the method further comprises selecting to handover from the at least one target network node to the first target network node based on the at least one mobility-related prediction.

[0245] Aspect 37 is a method according to any one of Aspects 31 to 36, wherein the method also includes receiving a handover command for the UE, the handover command including at least one parameter for a machine learning model of the UE to select a first target network node from the at least one target network node; and selecting the target resource configuration associated with the first target network node from the at least one target network node based on the machine learning model, wherein the input of the machine learning includes at least one of radio measurements, auxiliary information from the source network node, and location / motion sensor measurements of the UE, and the output of the machine learning includes at least one of a target cell to trigger the handover, a target cell to perform the handover, or a target cell to be measured.

[0246] Aspect 38 is a method according to any one of aspects 31 to 37, wherein the method further comprises sending an RRC message to the target network node indicating the target resource configuration associated with the first target network node.

[0247] Aspect 39 is a method according to any one of aspects 31 to 38, wherein the method further comprises receiving an instruction to relax at least one parameter of RRM measurements for each of the at least one target network node at the UE.

[0248] Aspect 40 is a method according to aspect 39, wherein the method further comprises receiving from the source network node at least one configuration for determining at least one parameter for relaxing the RRM measurement at the UE for each of the at least one target network node.

[0249] Aspect 41 is a method according to aspect 40, wherein the at least one configuration is associated with at least one measurement object of the UE.

[0250] Aspect 42 is a method according to any one of aspects 31 to 33, wherein the method further comprises sending an RRM measurement report, the RRM measurement report comprising at least one flag indicating that the RRM measurement is based on a prediction of mobility or a confidence level of the prediction.

[0251] Aspect 43 is a method according to any one of aspects 39 to 42, wherein the method also includes receiving at least one parameter for a machine learning model for the UE to determine RRM prediction and the at least one parameter of the RRM measurement.

[0252] Aspect 44 is an apparatus for wireless communication, the apparatus comprising: at least one processor, the at least one processor coupled to a memory and configured to implement any one of aspects 31 to 43, the apparatus further comprising a transceiver coupled to the at least one processor.

[0253] Aspect 45 is an apparatus for wireless communication, the apparatus comprising means for implementing any one of aspects 31 to 43.

[0254] Aspect 46 is a non-transitory computer readable medium storing computer executable code, wherein the code, when executed by a processor, causes the processor to implement any one of aspects 31 to 43.

Claims

1. An apparatus for wireless communication at a source network node, the apparatus comprising: Memory; and at least one processor coupled to the memory and based at least in part on the information stored in the memory, the at least one processor configured to: obtaining at least one mobility-related prediction associated with a user equipment (UE) or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network; and The UE is handed over from the source network node to the at least one target network node based on the at least one mobility-related prediction.

2. The apparatus of claim 1 , wherein the at least one mobility-related prediction is associated with the UE and comprises at least one of: UE trajectory prediction, UE business forecast, Radio Resource Management (RRM) measurement prediction, or UE location and mobility status, The at least one processor is further configured to output a handover message for transmission, the handover message comprising the at least one mobility-related prediction associated with the UE.

3. The device according to claim 2, wherein: To obtain the at least one mobility-related prediction, the at least one processor is further configured to: The at least one mobility-related prediction associated with the UE is derived using the at least one neural network of the source network node.

4. The device according to claim 2, wherein: To obtain the at least one mobility-related prediction, the at least one processor is further configured to: The at least one mobility-related prediction associated with the UE is received from the UE, the at least one mobility-related prediction associated with the UE being derived by the at least one neural network of the UE.

5. The apparatus of claim 2, wherein the handover message is a handover request to the at least one target network node, Wherein the at least one processor is further configured to receive a handover request acknowledgement (ACK) from the at least one target network node.

6. The apparatus of claim 2, wherein the handover message is a handover requirement message to a core network, and the at least one mobility-related prediction associated with the UE is included in a container for the at least one target network node.

7. The apparatus of claim 1 , wherein the at least one mobility-related prediction is associated with the at least one target network node and comprises at least one of: A prediction of the capacity of network resources including physical resource blocks (PRBs) or transport network layers (TNLs); or a achievable quality of service (QoS) or quality of experience (QoE) (QoS / QoE) at said at least one target network node after said handover, in, To obtain the at least one mobility-related prediction, the at least one processor is further configured to receive, from the at least one target network node, the at least one mobility-related prediction associated with the at least one target network node.

8. The apparatus of claim 7, wherein the at least one processor is further configured to output a handover request to the at least one target network node for transmission, Wherein the at least one mobility-related prediction associated with the at least one target network node is received in a handover request acknowledgement (ACK) from the at least one target network node.

9. The apparatus of claim 7, wherein the at least one processor is further configured to output a handover requirement message to a core network for transmission, Wherein the at least one mobility-related prediction associated with the at least one target network node is received in a handover command from the core network, the at least one mobility-related prediction associated with the at least one target network node being included in a container from the at least one target network node.

10. The apparatus of claim 1, wherein the at least one processor is further configured to output a handover command for the UE for transmission, the handover command comprising the at least one mobility-related prediction.

11. The apparatus of claim 1 , wherein the at least one processor is further configured to: A handover command for the UE is output for sending, the handover command comprising at least one parameter for a machine learning model for the UE to select a target resource configuration associated with a first target network node from the at least one target network node.

12. The apparatus of claim 1, wherein the at least one processor is further configured to instruct the UE to relax at least one parameter of a radio resource management (RRM) measurement at the UE for each of the at least one target network node.

13. The apparatus of claim 12, wherein the at least one processor is further configured to output for transmission at least one configuration for the UE to determine to relax the at least one parameter of the RRM measurement for each of the at least one target network node at the UE.

14. The apparatus of claim 13, wherein the at least one configuration is associated with at least one measurement object of the UE.

15. The apparatus of claim 13, wherein the at least one processor is further configured to receive an RRM measurement report comprising at least one flag indicating that the RRM measurement is based on a prediction of mobility or a confidence level of the prediction.

16. The apparatus of claim 12, wherein the at least one processor is further configured to output for transmission at least one parameter for a machine learning model for the UE to determine RRM prediction and the at least one parameter for the RRM measurement.

17. An apparatus for wireless communication at a target network node, the apparatus comprising: Memory; and at least one processor coupled to the memory and based at least in part on the information stored in the memory, the at least one processor configured to: receiving a handover request to handover a user equipment (UE) from a source network node; obtaining at least one mobility-related prediction associated with the UE or the target network node, the at least one mobility-related prediction being derived by at least one neural network; and A handover request acknowledgement (ACK) is output for transmission, the handover request ACK being based at least in part on the at least one mobility-related prediction.

18. The apparatus of claim 17, wherein the at least one mobility-related prediction is associated with the target network node and comprises at least one of: A prediction of the capacity of network resources including physical resource blocks (PRBs) or transport network layers (TNLs); or a achievable quality of service (QoS) or quality of experience (QoE) (QoS / QoE) at said at least one target network node after said handover, in, To obtain the at least one mobility-related prediction, the at least one processor is further configured to derive the at least one mobility-related prediction associated with the target network node using the at least one neural network of the target network node.

19. The apparatus of claim 18, wherein the at least one processor is further configured to output a handover request ACK to the at least one target network node for transmission.

20. The apparatus of claim 18, wherein the at least one processor is further configured to output a handover request ACK to a core network for transmission, the at least one mobility-related prediction associated with the at least one target network node being included in a container to the source network node.

21. An apparatus for wireless communication at a user equipment (UE), the apparatus comprising: Memory; and at least one processor coupled to the memory and based at least in part on the information stored in the memory, the at least one processor configured to: obtaining at least one mobility-related prediction associated with the UE or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network; as well as A handover is performed from the source network node to a first target network node of the at least one target network node, the first target network node being associated with a target resource configuration based on the at least one mobility-related prediction.

22. The apparatus of claim 21 , wherein the at least one mobility-related prediction is associated with the at least one target network node and comprises at least one of: A prediction of the capacity of network resources including physical resource blocks (PRBs) or transport network layers (TNLs); or a achievable quality of service (QoS) or quality of experience (QoE) (QoS / QoE) at the at least one target network node after handing over the UE from the source network node to the target network node, in, To obtain the at least one mobility-related prediction, the at least one processor is further configured to receive, from the source network node, the at least one mobility-related prediction associated with the at least one target network node.

23. The apparatus of claim 21, wherein the at least one processor is further configured to receive a handover command from the source network node, the handover command comprising the at least one mobility-related prediction.

24. The apparatus of claim 23, wherein the at least one processor is further configured to select to handover from the at least one target network node to the first target network node based on the at least one mobility-related prediction.

25. The apparatus of claim 21, wherein the at least one processor is further configured to: receiving a handover command for the UE, the handover command comprising at least one parameter for a machine learning model of the UE to select a first target network node from the at least one target network node; and selecting the target resource configuration associated with the first target network node from the at least one target network node based on the machine learning model, The input of the machine learning includes at least one of radio measurements, auxiliary information from the source network node, and location / motion sensor measurements of the UE, and the output of the machine learning includes at least one of a target cell to trigger the handover, a target cell to perform the handover, or a target cell to be measured.

26. The device according to claim 21, wherein To switch from the source network node to the first target network node, the at least one processor is further configured to: A radio resource control (RRC) message is sent to the target network node indicating the target resource configuration associated with the first target network node.

27. The apparatus of claim 21, wherein the at least one processor is further configured to receive instructions for relaxing at least one parameter of radio resource management (RRM) measurements at the UE for each of the at least one target network node.

28. The apparatus of claim 27, wherein the at least one processor is further configured to receive from the source network node at least one configuration for determining the at least one parameter to relax the RRM measurement at the UE for each of the at least one target network node.

29. The apparatus of claim 27, wherein the at least one processor is further configured to receive at least one parameter for determining RRM prediction by a machine learning model for the UE and the at least one parameter of the RRM measurement.

30. A method at a source network node, the method comprising: obtaining at least one mobility-related prediction associated with a user equipment (UE) or at least one target network node, the at least one mobility-related prediction being derived by at least one neural network; and The UE is handed over from the source network node to the at least one target network node based on the at least one mobility-related prediction.

Images