Reporting of L1-RSRP margins for predictive beam management

Abstract

A method and related apparatus for wireless communication at a user equipment (UE) are provided. In the method, the UE predicts one or more predicted beams from a first group of beams; and performing a first beam measurement for a first set of beams comprising the one or more predicted beams, respectively. The UE further sends performance information to the network node, the performance information indicating a difference between a first signal measurement based on the first beam measurement and a second signal measurement, the first signal measurement being associated with the one or more predicted beams, the second signal measurement being associated with one or more beams in the first set of beams.

Description

Technical Field

[0001] This disclosure relates in general to communication systems, and more specifically to wireless communications including predictive beam management. Background Technology

[0002] Wireless communication systems are widely deployed to provide a variety of telecommunications services, such as telephone, video, data, messaging, and broadcasting. 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.

[0003] These multiple access technologies have been adopted in various telecommunications standards to provide a common protocol that enables different wireless devices to communicate at the city, national, regional, and even global levels. An example telecommunications standard is 5G New Radio (NR). 5G NR is part of the Continuous Evolution of Mobile Broadband (CEM) program issued by the 3rd 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. 5G NR includes services associated with enhanced mobile broadband (eMBB), massive machine-type communications (mMTC), and ultra-reliable low-latency communications (URLLC). Some aspects of 5G NR can be based on the 4G Long Term Evolution (LTE) standard. Further improvements to 5G NR technology are needed. Furthermore, these improvements can also be applied to other multiple access technologies and telecommunications standards that adopt these technologies. Summary of the Invention

[0004] The following is a simplified summary of one or more aspects to provide a basic understanding of these aspects. This summary is not a comprehensive overview of all conceived aspects. It neither identifies key or essential 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 the more detailed descriptions that follow.

[0005] In one aspect of this disclosure, a method, computer-readable medium, and apparatus for wireless communication at a user equipment (UE) are provided. The apparatus may include at least one memory and at least one processor coupled to the at least one memory. Based at least in part on information stored in the at least one memory, the at least one processor may be configured individually or in any combination to: predict one or more predicted beams from a first set of beams; perform first beam measurements for the first set of beams, including the one or more predicted beams; and transmit performance information to a network node, the performance information indicating a difference between a first signal measurement and a second signal measurement based on the first beam measurement, the first signal measurement being associated with the one or more predicted beams, and the second signal measurement being associated with one or more beams in the first set of beams.

[0006] In one aspect of this disclosure, methods, computer-readable media, and apparatus for wireless communication at a network entity are provided. The apparatus may include at least one memory and at least one processor coupled to the at least one memory. Based at least in part on information stored in the at least one memory, the at least one processor may be configured individually or in any combination to: transmit a first set of reference signals (RS) to a UE via a first set of beams to initiate the UE to predict one or more predicted beams from the first set of beams; and receive performance information from the UE indicating a difference between a first signal measurement and a second signal measurement based on a first beam measurement of the first set of beams, the first signal measurement being associated with the one or more predicted beams from the first set of beams, and the second signal measurement being associated with one or more beams in the first set of beams.

[0007] To achieve the foregoing and related objectives, one or more aspects may include the features fully described below and specifically pointed out in the claims. The following description and drawings set forth some exemplary features of one or more aspects in detail. However, these features indicate only a few of the various ways in which the principles of the various aspects may be employed. Attached Figure Description

[0008] Figure 1 This is a diagram illustrating an example of a wireless communication system and an access network.

[0009] Figure 2A This is an illustration of an example of the first frame according to various aspects of this disclosure.

[0010] Figure 2B This is a diagram illustrating examples of downlink (DL) channels within a subframe according to various aspects of this disclosure.

[0011] Figure 2C This is an illustration of an example of a second frame according to various aspects of this disclosure.

[0012] Figure 2D This is a diagram illustrating examples of uplink (UL) channels within a subframe according to various aspects of this disclosure.

[0013] Figure 3 This is a diagram illustrating examples of base stations and user equipment (UEs) in an access network.

[0014] Figure 4 This is an example of an artificial intelligence / machine learning (AI / ML) algorithm for wireless communication methods.

[0015] Figure 5A This is a diagram illustrating an example of spatial beam prediction using an AI / ML model.

[0016] Figure 5B This is a diagram illustrating an example of spatial beam prediction using an AI / ML model.

[0017] Figure 5C This is a diagram illustrating an example of temporal beam prediction using an AI / ML model.

[0018] Figure 6A This is a diagram illustrating examples of UE-side performance monitoring of AI / ML models according to various aspects of this disclosure.

[0019] Figure 6B This is a diagram illustrating examples of NW-side performance monitoring for AI / ML models according to various aspects of this disclosure.

[0020] Figure 7 This is a diagram illustrating examples of hybrid performance monitoring for AI / ML models according to various aspects of this disclosure.

[0021] Figure 8 This is a diagram illustrating examples of dedicated RS for performance monitoring according to various aspects of this disclosure.

[0022] Figure 9A These are illustrations illustrating examples of performance monitoring according to various aspects of this disclosure.

[0023] Figure 9B These are illustrations illustrating examples of performance monitoring according to various aspects of this disclosure.

[0024] Figure 10 This is a call flowchart illustrating various aspects of wireless communication methods according to this disclosure.

[0025] Figure 11 This is a flowchart illustrating various methods of wireless communication at a UE according to various aspects of this disclosure.

[0026] Figure 12 This is a flowchart illustrating various methods of wireless communication at a UE according to various aspects of this disclosure.

[0027] Figure 13 This is a flowchart illustrating various methods of wireless communication at a network entity according to various aspects of this disclosure.

[0028] Figure 14 This is a flowchart illustrating various methods of wireless communication at a network entity according to various aspects of this disclosure.

[0029] Figure 15 These are illustrations illustrating specific hardware implementations used for example devices and / or network entities.

[0030] Figure 16 This is a diagram illustrating an example of a hardware implementation used for an example network entity. Detailed Implementation

[0031] Artificial intelligence (AI) / machine learning (ML) models can be used for beam management in wireless communications, such as for wireless communication between user equipment (UE) and base stations. For example, AI / ML models can predict and select beams in the spatial and / or temporal domains for wireless communication between the UE and the base station. However, monitoring the performance of predictions made by AI / ML models remains a challenging task. Some confidence reports may be based on the probability of correct predictions, but these reports may be made without a testing process to verify the reported probabilities to the network. Therefore, network operators and vendors may have very limited information about the accuracy of such probability reports. The example aspect presented in this paper addresses these issues by introducing a reliability metric that assists UEs and / or networks in measuring the accuracy of AI / ML model predictions in real-world scenarios.

[0032] Various aspects are generally related to wireless communication. Some aspects are more specifically related to the reporting of Layer 1 (L1) Reference Signal Received Power (RSRP) margins for predictive beam management in wireless communication. In some examples, the UE may use an AI / ML model to predict one or more predicted beams, for example, from a first set of beams; and perform a first beam measurement, respectively, for the first set of beams including the one or more predicted beams. The UE may further send performance information to the network node indicating a difference (e.g., margin) between a first signal measurement (e.g., L1-RSRP) and a second signal measurement (e.g., L1-RSRP) based on the first beam measurement, the first signal measurement associated with the one or more predicted beams, and the second signal measurement associated with one or more beams in the first set of beams. In some aspects, the UE may perform preliminary beam measurements on a preliminary set of beams, respectively, before predicting the one or more predicted beams, and the first set of beams may be based on the preliminary beam measurements. In addition, depending on whether specific conditions related to the difference between signal measurements are met, the UE may perform lifecycle management (LCM) operations on the AI / ML model. These lifecycle management (LCM) operations may involve activating the AI / ML model, deactivating the AI / ML model, switching to another AI / ML model, or performing a rollback operation on the AI / ML model.

[0033] Specific aspects of the subject matter described in this disclosure can be implemented to achieve one or more of the following potential advantages. In some examples, by calculating the difference between the predicted optimal beam and the actual optimal beam (such as L1-RSRP), the described techniques provide a concrete metric for measuring prediction accuracy, and thus improve beam prediction accuracy, thereby enhancing the efficiency and reliability of wireless communication. In some aspects, the reporting of metrics (such as L1-RSRP) can be event-triggered (e.g., when the L1-RSRP margin exceeds a predetermined threshold). This helps ensure that significant deviations that could affect communication quality are reported, while reducing unnecessary overhead. In some aspects, by enabling the UE to disable or switch AI / ML functionality or revert to legacy procedures based on the L1-RSRP margin, the described techniques ensure optimal performance of the AI / ML model under varying conditions.

[0034] The detailed descriptions following, illustrated with reference to the accompanying drawings, describe various configurations and do not represent the only configurations in which the concepts described herein can be practiced. To provide a thorough understanding of the various concepts, the detailed descriptions include specific details. However, these concepts can be practiced without these specific details. In some instances, well-known structures and components are shown in block diagram form to avoid obscuring these concepts.

[0035] Various apparatuses and methods are presented with reference to several aspects of a telecommunications system. These apparatuses and methods are described in detail below and illustrated in the accompanying drawings by various blocks, components, circuits, processes, algorithms, etc. (collectively, “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 system as a whole.

[0036] As an example, an element, any part of an element, or any combination of elements may be implemented as a "processing system" including one or more processors. When multiple processors are implemented, the multiple processors may perform functions individually or in combination. 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, system-on-a-chip (SoCs), baseband processors, field-programmable gate arrays (FPGAs), programmable logic devices (PLDs), state machines, gate logic, discrete hardware circuits, and other suitable hardware configured to perform the various functionalities described throughout this disclosure. One or more processors in the 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 instructions, instruction sets, code, code segments, program code, programs, subroutines, software components, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, or any combination thereof.

[0037] Therefore, 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 code on a computer-readable medium. Computer-readable media include computer storage media. Storage media may be any available medium accessible to a computer. By way of example, such computer-readable media may include random access memory (RAM), read-only memory (ROM), electrically erasable programmable ROM (EEPROM), optical disc storage devices, magnetic disk storage devices, 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 accessible to a computer.

[0038] While aspects, implementations, and / or use cases are described herein by way of example, additional or different aspects, implementations, and / or use cases may arise in many different arrangements and scenarios. The aspects, implementations, and / or use cases described herein can be implemented across many different platform types, devices, systems, shapes, sizes, and package arrangements. For example, aspects, implementations, and / or use cases may arise via integrated chip implementations and other devices based on non-modular components (e.g., end-user devices, vehicles, communication devices, computing devices, industrial equipment, retail / purchasing devices, medical devices, AI-enabled devices, etc.). While some examples may or may not be specific to a use case or application, the described examples may exhibit broad applicability. Aspects, implementations, and / or use cases can range from chip-level or modular components to non-modular, non-chip-level implementations, and further to aggregated, distributed, or original equipment manufacturer (OEM) devices or systems incorporating one or more of the technologies described herein. In some practical settings, devices incorporating the described aspects and features 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 involve 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 techniques described herein can be practiced in a wide variety of devices, chip-level components, systems, distributed arrangements, aggregated or decomposed components, end-user equipment, etc., of various sizes, shapes, and configurations.

[0039] Communication systems, such as 5G NR systems, can be deployed in various ways with a variety of components or parts. In a 5G NR system or network, network nodes, network entities, network mobility elements, radio access network (RAN) nodes, core network nodes, network elements or network equipment (such as base stations (BS)), or one or more units (or components) performing base station functions can be implemented in aggregated or decomposed architectures. For example, BSs (such as Node B (NB), evolved NB (eNB), NR BS, 5G NB, access point (AP), transmit / receive point (TRP), or cell, etc.) can be implemented as aggregated base stations (also known as standalone BS or monolithic BS) or decomposed base stations.

[0040] Aggregated base stations can be configured to utilize a radio protocol stack that is physically or logically integrated within a single RAN node. Decentralized base stations can be configured to utilize a protocol stack that is physically or logically distributed across 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, the CU may be implemented within a RAN node, and one or more DUs may co-located with the CU, or alternatively, may be geographically or virtually distributed across one or more other RAN nodes. DUs may be implemented to communicate with one or more RUs. Each of the CU, DU, and RU may be implemented as a virtual unit, namely a virtual central unit (VCU), a virtual distributed unit (VDU), or a virtual radio unit (VRU).

[0041] Base station operation or network design can take into account the aggregation characteristics of base station functionality. For example, decomposed base stations can be utilized in Integrated Access Backhaul (IAB) networks, Open Radio Access Networks (O-RAN (such as network configurations initiated by the O-RAN Alliance)), or Virtualized Radio Access Networks (vRAN, also known as Cloud Radio Access Networks (C-RAN)). Decomposition can include distributing functionality across two or more units in various physical locations, as well as virtually distributing the functionality of at least one unit, which enables flexibility in network design. The various units of a decomposed base station or decomposed RAN architecture can be configured to communicate wirelessly with at least one other unit.

[0042] Figure 1 Figure 100 illustrates an example of a wireless communication system and access network. The illustrated wireless communication system includes a decomposed base station architecture. The decomposed base station architecture may include one or more CUs 110, which may communicate directly with the core network 120 via a backhaul link, or indirectly with the core network 120 via one or more decomposed 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. CUs 110 may communicate with one or more DUs 130 via a corresponding midhaul link (such as an F1 interface). DUs 130 may communicate with one or more RUs 140 via a corresponding fronthaul link. RUs 140 may communicate with a corresponding UE 104 via one or more radio frequency (RF) access links. In some implementations, a UE 104 may be served simultaneously by multiple RUs 140.

[0043] Each of the units (i.e., CU 110, DU 130, RU 140, and near-RT RIC 125, non-RT RIC 115, and SMO frame 105) may include or be coupled to one or more interfaces configured to receive or transmit signals, data, or information (collectively, signals) via wired or wireless transmission media. Each of the units, or an associated processor or controller providing instructions to the communication interfaces of these units, may be configured to communicate with one or more other units via transmission media. For example, these units may include wired interfaces configured to receive signals or transmit signals to one or more other units via wired transmission media. Additionally, these units may include wireless interfaces that may include receivers, transmitters, or transceivers (such as RF transceivers) configured to receive signals via wireless transmission media and / or transmit signals to one or more other units.

[0044] In some aspects, the CU 110 can host one or more higher-level control functions. Such control functions may include Radio Resource Control (RRC), Packet Data Convergence Protocol (PDCP), Serving Data Adaptation Protocol (SDAP), etc. Each control function can be implemented using an interface configured to signal to other control functions hosted by the CU 110. The CU 110 can 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 implementations, the CU 110 can be logically divided into one or more CU-UP units and one or more CU-CP units. When implemented in an O-RAN configuration, the CU-UP units can communicate bidirectionally with the CU-CP units via an interface such as an E1 interface. The CU 110 can be implemented to communicate with the DU 130 for network control and signaling, as needed.

[0045] DU 130 may correspond to a logical unit that includes one or more base station functions for controlling the operation of one or more RU 140s. In some aspects, DU 130 may at least partially host one or more of the Radio Link Control (RLC) layer, Media 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, demodulation, etc.) according to functional splits (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 configured to communicate signals with other layers (and modules) hosted by DU 130 or with control functions hosted by CU 110.

[0046] Lower-layer functionality can be implemented by one or more RU 140s. In some deployments, an RU140 controlled by a DU 130 may correspond to a logical node that at least partially 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.) based on functional decomposition such as lower-layer functional decomposition, or both. In this architecture, the RU 140 can be implemented to handle over-the-air (OTA) communications with one or more UEs 104. In some specific implementations, the 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 allows the DU 130 and CU 110 to be implemented in cloud-based RAN architectures such as vRAN architectures.

[0047] SMO framework 105 can be configured to support RAN deployment and provisioning of both non-virtualized and virtualized network elements. For non-virtualized network elements, SMO framework 105 can be configured to support the deployment of dedicated physical resources for RAN coverage requirements, which can be managed via operation and maintenance interfaces such as the O1 interface. For virtualized network elements, SMO framework 105 can be configured to interact with a cloud computing platform such as 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 the 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 implementations, SMO framework 105 can communicate with hardware aspects of the 4G RAN, such as Open eNB (O-eNB) 111, via the O1 interface. Additionally, in some implementations, SMO framework 105 can communicate directly with one or more RU 140s via the O1 interface. SMO framework 105 may also include a non-RT RIC 115 configured to support the functionality of SMO framework 105.

[0048] The non-RT RIC 115 can be configured to include logical functions enabling non-real-time control and optimization of RAN elements and resources, including artificial intelligence (AI) / machine learning (ML) workflows for model training and updates, or policy-based guidance for applications / features in the near-RT RIC 125. The non-RT RIC 115 can be coupled to or communicate with the near-RT RIC 125, such as via an A1 interface. The near-RT RIC 125 can be configured to include logical functions enabling near real-time control and optimization of RAN elements and resources via data collection and actions through an interface such as an E2 interface, connecting one or more CU 110s, one or more DU 130s, or both, and O-eNBs to the near-RT RIC 125.

[0049] In some implementations, to generate AI / ML models 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. This information can be utilized by the near-RT RIC 125 and can be received from non-network data sources or network functions 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 in performance and employ AI / ML models to perform corrective actions via the SMO framework 105 (such as reconfiguration via O1) or by creating RAN management policies (such as A1 policies).

[0050] At least one of CU 110, DU 130, and RU 140 may be referred to as base station 102. Therefore, base station 102 may include one or more of CU 110, DU 130, and RU 140 (each component is indicated by a dashed line to indicate that each component may or may not be included in base station 102). Base station 102 provides UE 104 with an access point to core network 120. Base station 102 may include macro cells (high-power cellular base stations) and / or small cells (low-power cellular base stations). Small cells include femtocells, picocells, and microcells. A network that includes both small cells and macro cells may be referred to as a heterogeneous network. A heterogeneous network may also include an evolved home node B (eNB) (HeNB), which can provide service 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) transmission (also known as reverse link) from UE 104 to RU 140 and / or downlink (DL) transmission (also known as forward link) transmission from RU 140 to UE 104. The communication link may utilize multiple-input multiple-output (MIMO) antenna techniques, including spatial multiplexing, beamforming, and / or transmit diversity. The communication link may use one or more carriers. For each direction, the total number of carriers used for transmission can be up to [number missing]. Yx MHz ( x For each carrier allocated in carrier aggregation (of component carriers), base station 102 / UE 104 can use up to [number] carriers. Y A spectrum with a bandwidth of MHz (e.g., 5MHz, 10MHz, 15MHz, 20MHz, 100MHz, 400MHz, etc.). Carriers may be adjacent to each other or may not be adjacent to each other. Carrier allocation may be asymmetric with respect to DL and UL (e.g., more or fewer carriers may be allocated to DL compared to UL). Component carriers may include primary component carriers and one or more secondary component carriers. The primary component carrier may be referred to as the primary cell (PCell) and the secondary component carrier may be referred to as the secondary cell (SCell).

[0051] Some UEs 104 can communicate with each other using device-to-device (D2D) communication link 158. D2D communication link 158 can use DL / UL wireless wide area network (WWAN) spectrum. D2D communication link 158 can use one or more sidelink channels, such as Physical Sidelink Broadcast Channel (PSBCH), Physical Sidelink Discovery Channel (PSDCH), Physical Sidelink Shared Channel (PSSCH), and Physical Sidelink Control Channel (PSCCH). D2D communication can be performed through various wireless D2D communication systems, such as Bluetooth. ™ (Bluetooth is a trademark of the Bluetooth Special Interest Group (SIG), and is based on the IEEE 802.11 standard for Wi-Fi.)™ (Wi-Fi is a trademark of the Wi-Fi Alliance), LTE, or NR.

[0052] The wireless communication system may also include a Wi-Fi AP 150, which communicates with the UE 104 (also referred to as a Wi-Fi station (STA)) via a communication link 154, for example, in an unlicensed spectrum such as 5 GHz. When communicating in unlicensed spectrum, the UE 104 / AP 150 may perform a free channel assessment (CCA) to determine whether the channel is available before communication.

[0053] 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 designated as frequency ranges FR1 (410MHz to 7.125GHz) and FR2 (24.25GHz to 52.6GHz). Although a portion of FR1 is greater than 6GHz, in various documents and articles, FR1 is often (interchangeably) referred to as the "sub-6GHz" band. Similar naming issues sometimes occur with FR2, which is often (interchangeably) referred to as the "millimeter wave" band in documents and articles, although this is distinct from the Extremely High Frequency (EHF) band (30GHz to 300GHz) designated as "millimeter wave" by the International Telecommunication Union (ITU).

[0054] The frequencies between FR1 and FR2 are generally referred to as mid-band frequencies. Recent 5G NR studies have identified the operating bands used for these mid-band frequencies as the frequency range designation FR3 (7.125 GHz to 24.25 GHz). Bands falling within FR3 can inherit FR1 and / or FR2 characteristics, and thus can effectively extend the features of FR1 and / or FR2 to mid-band frequencies. Furthermore, higher frequency bands are currently being explored to extend 5G NR operation beyond 52.6 GHz. For example, three higher operating bands have been identified as the frequency range designations FR2-2 (52.6 GHz to 71 GHz), FR4 (71 GHz to 114.25 GHz), and FR5 (114.25 GHz to 300 GHz). Each of these higher frequency bands falls within the EHF band.

[0055] In view of the above, unless otherwise specifically stated, the term "below 6 GHz" as used herein can broadly refer to frequencies less than 6 GHz, within FR1, or including intermediate frequency band frequencies. Furthermore, unless otherwise specifically stated, the term "millimeter wave" as used herein can broadly refer to frequencies that can include intermediate frequency band frequencies, within FR2, FR4, FR2-2 and / or FR5, or within the EHF band.

[0056] Base station 102 and UE 104 may each include multiple antennas (such as antenna elements, antenna panels, and / or antenna arrays) to facilitate beamforming. Base station 102 may transmit beamformed signals 182 to UE 104 in one or more transmit directions. UE 104 may receive beamformed signals from base station 102 in one or more receive directions. UE 104 may also transmit beamformed signals 184 to base station 102 in one or more transmit directions. Base station 102 may receive beamformed signals from UE 104 in one or more receive directions. Base station 102 / UE 104 may perform beamforming training to determine the optimal receive and transmit directions for each of base station 102 / UE 104. The transmit and receive directions of base station 102 may be the same or different. The transmit and receive directions of UE 104 may be the same or different.

[0057] Base station 102 may include and / or be referred to as gNB, Node B, eNB, access point, transceiver base station, radio base station, radio transceiver, transceiver function, basic service set (BSS), extended service set (ESS), TRP, network node, network entity, network equipment, or some other suitable terminology. Base station 102 may be implemented as an integrated access and backhaul (IAB) node, relay node, sidelink node, aggregated (monolithic) base station with baseband units (BBU) (including CU and DU) and RU, or may be implemented as a decomposed base station including one or more of CU, DU, and / or RU. A collection of base stations that may include decomposed base stations and / or aggregated base stations may be referred to as Next Generation (NG) RAN (NG-RAN).

[0058] The core network 120 may include Access and Mobility Management Function (AMF) 161, Session Management Function (SMF) 162, User Plane Function (UPF) 163, Unified Data Management (UDM) 164, one or more location servers 168, and other functional entities. AMF 161 is the control node that handles signaling between UE 104 and the 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 authentication and key agreement (AKA) credential generation, user identity processing, access authorization, and subscription management. One or more location servers 168 are exemplified as including a Gateway Mobile Location Center (GMLC) 165 and a Location Management Function (LMF) 166. However, generally, one or more location servers 168 may include one or more location / positioning servers, which may include one or more of GMLC 165, LMF 166, Position Determination Entity (PDE), Serving Mobile Location Center (SMLC), Mobile Location 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 location information. LMF 166 receives measurement and auxiliary information from NG-RAN and UE 104 via AMF 161 to calculate the location of UE 104. NG-RAN may use one or more positioning methods to determine the location of UE 104. Positioning UE 104 may involve signal measurement, location estimation, and optional speed calculation based on these measurements. Signal measurement may be performed by UE 104 and / or base station 102 serving UE 104. The measured signals may be based on one or more of the following systems / signals / sensors: Satellite Positioning System (SPS) 170 (e.g., one or more of Global Navigation Satellite System (GNSS), Global Positioning System (GPS), Non-Terrestrial Network (NTN) or other position / location systems), LTE signals, Wireless Local Area Network (WLAN) signals, Bluetooth signals, Terrestrial Beacon System (TBS), sensor-based information (e.g., barometric pressure sensor, motion sensor), NR Enhanced Cell ID (NR E-CID) method, NR signals (e.g., multiple round-trip time (multiple RTT), DL departure angle (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 other systems / signals / sensors.

[0059] Examples of UE 104 include cellular phones, smartphones, Session Initiation Protocol (SIP) phones, laptops, personal digital assistants (PDAs), satellite radios, GPS devices, multimedia devices, video devices, digital audio players (e.g., MP3 players), cameras, game consoles, tablet devices, smart devices, wearable devices, vehicles, electricity meters, air pumps, large or small kitchen appliances, healthcare devices, implants, sensors / actuators, displays, or any other similarly functional device. Some UEs in UE 104 may be referred to as IoT devices (e.g., parking meters, air pumps, toasters, vehicles, heart monitors, etc.). UE 104 may also be referred to as a station, mobile station, subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, mobile phone, user agent, mobile client, client, or some other suitable terminology. In some scenarios, the term UE may also be applied to one or more companion devices, such as in a device constellation arrangement. One or more of these devices may access the network together and / or individually.

[0060] Refer again Figure 1 In some aspects, UE 104 may include a measurement reporting component 198. Measurement reporting component 198 may be configured to: predict one or more predicted beams from a first set of beams; perform a first beam measurement for each of the first set of beams including the one or more predicted beams; and send performance information to a network node indicating a difference between a first signal measurement and a second signal measurement based on the first beam measurement, the first signal measurement being associated with the one or more predicted beams, and the second signal measurement being associated with one or more beams in the first set of beams. In some aspects, base station 102 may include a measurement reporting component 199. Measurement reporting component 199 may be configured to: send a first set of reference signals (RS) to the UE via the first set of beams to initiate the UE's prediction of one or more predicted beams from the first set of beams; and receive performance information from the UE indicating a difference between a first signal measurement and a second signal measurement based on the first beam measurement of the first set of beams, the first signal measurement being associated with the one or more predicted beams from the first set of beams, and the second signal measurement being associated with one or more beams in the first set of beams. While the following description may focus on 5G NR, the concepts described herein may be applicable to other similar areas, such as LTE, LTE-A, CDMA, GSM, and other wireless technologies.

[0061] Figure 2A Figure 200 illustrates an example of the first subframe within a 5G NR frame structure. Figure 2BFigure 230 illustrates an example of a DL channel within a 5G NR subframe. Figure 2C Figure 250 is an example of a second subframe within a 5G NR frame structure. Figure 2D Figure 280 illustrates an example of a UL channel within a 5G NR subframe. The 5G NR frame structure can be Frequency Division Duplex (FDD) (where subframes within a specific set of subcarriers (carrier system bandwidth) are dedicated to either DL or UL) or Time Division Duplex (TDD) (where subframes within a specific set of subcarriers (carrier system bandwidth) are dedicated to both DL and UL). Figure 2A , Figure 2C In the provided example, the 5G NR frame structure is assumed to be TDD, where subframe 4 is configured using slot format 28 (most of which are DL), where D is DL, U is UL, and F is flexible and can be used between DL / UL, and subframe 3 is configured using 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 can be configured using any of the various available slot formats 0-61. Slot formats 0 and 1 are both DL and UL, respectively. Other slot formats 2-61 include a mixture of DL, UL, and flexible symbols. The slot format is configured for the UE via the received Slot Format Indicator (SFI) (dynamically configured via DL Control Information (DCI) or semi-statically / statically configured via Radio Resource Control (RRC) signaling). Note that the following description also applies to the 5G NR frame structure as TDD.

[0062] Figures 2A to 2D The frame structure is illustrated, and aspects of this disclosure are applicable to other wireless communication technologies that may have different frame structures and / or different channels. A frame (10 ms) can be divided into 10 equal-sized subframes (1 ms). Each subframe may include one or more time slots. Subframes may also include micro-time slots, 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 normal CP, each time slot may include 14 symbols, and for extended CP, each time slot may include 12 symbols. Symbols on the DL may be CP Orthogonal Frequency Division Multiplexing (OFDM) (CP-OFDM) symbols. Symbols on the UL may be CP-OFDM symbols (for high-throughput scenarios) or Discrete Fourier Transform (DFT) Extended OFDM (DFT-s-OFDM) symbols (for power-constrained scenarios; limited to single-stream transmission). The number of time slots within a subframe is based on the CP and a parameter set. The parameter set defines the subcarrier spacing (SCS) (see Table 1). Symbol length / duration can be scaled using 1 / SCS.

[0063] Table 1: Parameter Set, SCS, and CP For a normal CP (14 symbols / slot), different parameter sets µ 0 through 4 allow 1, 2, 4, 8, and 16 slots per subframe, respectively. For an extended CP, parameter set 2 allows 4 slots per subframe. Therefore, for a normal CP and parameter set µ, there are 14 symbols / slot and 2... µ One time slot / subframe. Subcarrier spacing can be equal to ,in The parameter sets are 0 to 4. Therefore, the subcarrier spacing is 15 kHz for parameter set µ=0 and 240 kHz for parameter set µ=4. The symbol length / duration is negatively correlated with the subcarrier spacing. Figures 2A to 2D Examples of a normal frequency division multiplexing (CP) with 14 symbols per time slot and a parameter set of µ=2 with 4 time slots per subframe are provided. The time slot duration is 0.25 ms, the subcarrier spacing is 60 kHz, and the symbol duration is approximately 16.67 μs. Within the frame set, there may be one or more distinct bandwidth portions (BWPs) of frequency division multiplexing (see [link to relevant documentation]). Figure 2B Each BWP can have a specific set of parameters and CP (normal or extended).

[0064] A resource grid can be used to represent the frame structure. Each time slot consists of a resource block (RB) extending for 12 consecutive subcarriers (also known as a physical RB (PRB)). The resource grid is divided into multiple resource elements (REs). The number of bits carried by each RE depends on the modulation scheme.

[0065] like Figure 2A As illustrated, some of the REs carry reference (pilot) signals (RS) for the UE. RS may include demodulation RS (DM-RS) (indicated as R for a particular configuration, but other DM-RS configurations are possible) and channel state information reference signals (CSI-RS) for channel estimation at the UE. RS may also include beam measurement RS (BRS), beam refinement RS (BRRS), and phase tracking RS (PT-RS).

[0066] Figure 2BExamples of various DL channels within a subframe of a frame are illustrated. The Physical Downlink Control Channel (PDCCH) carries the DCI within one or more Control Channel Elements (CCEs) (e.g., 1, 2, 4, 8, or 16 CCEs), each CCE comprising six RE Groups (REGs), each REG comprising 12 consecutive REs in the OFDM symbol of the RB. A PDCCH within a BWP can be referred to as a Control Resource Set (CORESET). The UE is configured to monitor PDCCH candidates in the PDCCH search space (e.g., the common search space, the UE-specific search space) during PDCCH monitoring timing on the CORESET, where 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. The Primary Synchronization Signal (PSS) may be located within symbol 2 of a specific subframe of the frame. The PSS is used by the UE 104 to determine subframe / symbol timing and physical layer identification. The Secondary Synchronization Signal (SSS) may be located within symbol 4 of a specific subframe of the frame. The SSS is used by the UE to determine the Physical Layer Cell Identifier Group Number and radio frame timing. Based on the Physical Layer Identifier and the Physical Layer Cell Identifier 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 known as an SS block (SSB)). The MIB provides the System Frame Number (SFN) and the number of Restricted Blocks (RBs) in the system bandwidth. The Physical Downlink Shared Channel (PDSCH) carries user data, broadcast system information not transmitted via the PBCH (such as System Information Blocks (SIBs)), and paging messages.

[0067] like Figure 2C As illustrated, some REs in the REs carry DM-RS (indicated as R for one particular configuration, but other DM-RS configurations are possible) for channel estimation at the base station. The UE can transmit DM-RS for the Physical Uplink Control Channel (PUCCH) and DM-RS for the Physical Uplink Shared Channel (PUSCH). The PUSCH DM-RS can be transmitted in the first or first two symbols of the PUSCH. Depending on whether a short or long PUCCH is transmitted and depending on the specific PUCCH format used, the PUCCH DM-RS can be transmitted in different configurations. The UE can transmit a Sounding Reference Signal (SRS). The SRS can be transmitted in the last symbol of a subframe. The SRS can have a comb structure, and the UE can transmit the SRS on one of the comb teeth. The SRS can be used by the base station for channel quality estimation to enable frequency-dependent scheduling of the UL.

[0068] Figure 2DExamples of various UL channels within a subframe of a frame are illustrated. The PUCCH may be located as indicated in one configuration. The PUCCH carries uplink control information (UCI), such as scheduling requests, channel quality indicators (CQI), pre-decoding matrix indicators (PMI), rank indicators (RI), and hybrid automatic repeat request (HARQ) acknowledgment (ACK) (HARQ-ACK) feedback (i.e., one or more HARQ ACK bits indicating one or more ACKs and / or negative ACKs (NACKs)). The PUCCH carries data and may additionally be used to carry buffer status reports (BSR), power clearance reports (PHR), and / or UCIs.

[0069] Figure 3 This is a block diagram illustrating communication between base station 310 and UE 350 in the access network. In the DL, Internet Protocol (IP) packets can be provided to controller / processor 375. Controller / processor 375 implements Layer 3 and Layer 2 functionality. Layer 3 includes the Radio Resource Control (RRC) layer, and Layer 2 includes the Service Data Adaptation Protocol (SDAP) layer, Packet Data Convergence Protocol (PDCP) layer, Radio Link Control (RLC) layer, and Media Access Control (MAC) layer. The controller / processor 375 provides RRC layer functionality associated with broadcasting 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 the delivery of upper-layer packet data units (PDUs), error correction via ARQ, concatenation, segmentation, and reassembly of RLC service data units (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 transport blocks (TBs), demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction via HARQ, priority handling, and logical channel priority ordering.

[0070] 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) decoding / decoding of the transport channel, interleaving, rate matching, mapping to the physical channel, modulation / demodulation of the physical channel, and MIMO antenna processing. TX processor 316 processes 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 decoded and modulated symbols can then be split into parallel streams. Each stream can then be mapped to OFDM subcarriers, multiplexed with a reference signal (e.g., a pilot) in the time and / or frequency domains, and subsequently combined using inverse fast Fourier transform (IFFT) to produce a physical channel carrying a stream of time-domain OFDM symbols. The OFDM stream is spatially pre-decoded to generate multiple spatial streams. Channel estimates from channel estimator 374 can be used to determine the decoding and modulation scheme, as well as for spatial processing. Channel estimates can be derived from reference signals transmitted by UE 350 and / or channel condition feedback. Each spatial stream can then be provided to different antennas 320 via a separate transmitter 318Tx. Each transmitter 318Tx can use the corresponding spatial stream to modulate a radio frequency (RF) carrier for transmission.

[0071] At UE 350, each receiver 354Rx receives signals via its corresponding antenna 352. Each receiver 354Rx recovers the information modulated onto the RF carrier and provides that information to the receive (RX) processor 356. The TX processor 368 and 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 UE 350. If multiple spatial streams are destined for UE 350, the RX processor 356 can combine them into a single OFDM symbol stream. The RX processor 356 then uses a Fast Fourier Transform (FFT) to transform the OFDM symbol stream from the time domain to the frequency domain. The frequency domain signal consists of a separate OFDM symbol stream for each subcarrier of the OFDM signal. The symbols on each subcarrier, along with the reference signal, are recovered and demodulated by determining the most probable signal constellation point transmitted by base station 310. These soft decisions can be based on a channel estimate calculated by channel estimator 358. Subsequently, the soft decision is decoded and deinterleaved to recover the data and control signals originally transmitted by base station 310 on the physical channel. The data and control signals are then provided to controller / processor 359, which implements layer 3 and layer 2 functionality.

[0072] The controller / processor 359 may be associated with at least one memory 360 storing program code and data. The at least one memory 360 may be referred to as a computer-readable medium. In the UL, the controller / processor 359 provides demultiplexing, packet reassembly, decryption, header decompression, and control signal processing between transport and logical channels to recover IP packets. The controller / processor 359 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operation.

[0073] Similar to the functionality described in conjunction with DL transmission performed by base station 310, controller / processor 359 provides RRC layer functionality associated with system information (e.g., MIB, SIB) acquisition, RRC connectivity, and measurement reporting; PDCP layer functionality associated with header compression / decompression and security (encryption, decryption, integrity protection, integrity verification); RLC layer functionality associated with upper-layer PDU delivery, error correction via 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 via HARQ, priority handling, and logical channel priority ordering.

[0074] The TX processor 368 can use the channel estimate derived from the reference signal or feedback transmitted by the channel estimator 358 from the base station 310 to select an appropriate decoding and modulation scheme and facilitate spatial processing. The spatial stream generated by the TX processor 368 can be provided to different antennas 352 via individual transmitters 354Tx. Each transmitter 354Tx can use the corresponding spatial stream to modulate an RF carrier for transmission.

[0075] UL transmission is processed at base station 310 in a manner similar to that described in conjunction with the receiver function at UE 350. Each receiver 318Rx receives signals via its corresponding antenna 320. Each receiver 318Rx recovers the information modulated onto the RF carrier and provides that information to RX processor 370.

[0076] The controller / processor 375 may be associated with at least one memory 376 storing program code and data. The at least one memory 376 may be referred to as a computer-readable medium. In the UL, the controller / processor 375 provides demultiplexing, packet reassembly, decryption, header decompression, and control signal processing to recover IP packets between transport and logical channels. The controller / processor 375 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operation.

[0077] At least one of the TX processor 368, RX processor 356, and controller / processor 359 can be configured to combine Figure 1 The measurement report component 198 is used to perform various aspects.

[0078] At least one of the TX processor 316, RX processor 370, and controller / processor 375 can be configured to combine Figure 1 The measurement report component 199 is used to perform various aspects.

[0079] Figure 4 This is an example of an AI / ML algorithm 400 using wireless communication methods. The AI / ML algorithm 400 may include various functions, including data collection 402, model training function 404, model inference function 406, and participants 408.

[0080] Data collection 402 can be a function that provides input data to model training function 404 and model inference function 406. The data collection 402 function can include any form of data preparation, and it may not be specific to any particular 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 (such as RSRP measurements or other TCI candidate information), feedback from participant 408, and output from another AI / ML model. Data collection 402 can include training data and inference data, where training data refers to the data to be transmitted as input to AI / ML model training function 404, and inference data refers to the data transmitted as input to AI / ML model inference function 406.

[0081] Model training function 404 can be a function that performs ML model training, validation, and testing, and can generate model performance metrics as part of the model testing process. Model training function 404 can also be responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on training data delivered or received from data collection function 402. Model training function 404 can deploy or update trained, validated, and tested AI / ML models to model inference function 406, and receive model performance feedback from model inference function 406.

[0082] Model inference function 406 may be a function that provides AI / ML model inference output (e.g., prediction or decision). Model inference function 406 may also perform data preparation (e.g., data preprocessing and cleaning, formatting and transformation) based on inference data delivered from data collection function 402. The output of model inference function 406 may include the inference output of the AI / ML model generated by model inference function 406. The details of the inference output may be use-use specific. As an example, the output may include predictions for one or more receiver beam candidates used as receiver beams at the UE, such as, in combination with... Figures 5A to 10 As described in any of the above. In some aspects, the output may include a beam pair comprising a receive beam for the UE. The input may include one or more measurements for a set of beams, and these measurements may be used to predict the quality of the receive beam when no measurements are performed, or the quality of the receive beam from a set of beams different from the measurement set. In some aspects, the participant may be the UE predicting the receive beam.

[0083] Model performance feedback can refer to information derived from the model inference function 406, which can be adapted to improve the AI / ML model trained in the model training function 404. Feedback from participants 408 or other network entities (via the data collection function 402) can be implemented in the model inference function 406 to create model performance feedback. For example, as combined with Figure 6A , Figure 6B , Figure 7 and / or Figure 10 As described, the UE and / or network node can evaluate the performance of beam prediction. This performance can be provided as feedback to improve the model.

[0084] Participant 408 can be a function that receives output from model inference function 406 and triggers or executes corresponding actions. Participant 408 can trigger actions against network entities, including other network entities or itself. Participant 408 can also provide feedback information from model training function 404 or model inference function 406, exporting training or inference data or performance feedback. Feedback can be sent back to data collection 402.

[0085] As described in this application, the UE may use machine learning algorithms, deep learning algorithms, neural networks, reinforcement learning, regression, boosting, or advanced signal processing methods for various aspects of wireless communication, including prediction of the received beam at the UE.

[0086] In some aspects described herein, one or more neural networks can be trained to learn the dependence of measurement quality on individual parameters. Furthermore, examples of machine learning models or neural networks that can be included in network entities include artificial neural networks (ANNs); decision tree learning; convolutional neural networks (CNNs); deep learning architectures where the output of a first layer of neurons becomes the input of a second layer of neurons, and so on; 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) configured using additional pooling and normalization layers; and deep belief networks (DBNs).

[0087] Machine learning models (such as artificial neural networks (ANNs)) may comprise a set of interconnected artificial neurons (e.g., neuron models) and may be computing devices or represent methods to be performed by computing devices. The connections in a neuron model can be modeled as weights. Machine learning models can be trained via datasets to provide predictive models, adaptive control, and other applications. The model can adapt based on external or internal information processed by the machine learning model. Machine learning can provide nonlinear statistical data models or decision-making and can model complex relationships between input data and output information.

[0088] Machine learning models can include multiple layers and / or operations, which can be formed by cascading one or more of the cited operations. Examples of operations that may be involved include: extraction of various features of the data, convolution operations, fully connected operations that can be activated or deactivated, compression, decompression, quantization, flattening, etc. As used in this paper, the term "layer" in a machine learning model can be used to represent an operation on the input data. For example, convolutional layers, fully connected layers, etc., can be used to refer to the associated operations on the data input into the layer. Convolution A × B Operation refers to combining multiple input features A Converted into multiple output features B The operation involves combining neighboring coefficients in a dimension. "Kernel size" can refer to the number of neighboring coefficients combined in the dimension. As used in this paper, "weight" can be used to represent one or more coefficients used in various rows and / or columns of input data in each layer. For example, a fully connected layer operation may have an output... y The output is at least partially based on the input matrix. x and weight A The product of (which can be matrices) and the bias value B The weights are determined by the sum of (which can be matrices). The term "weight" in this text is generally used to refer to both weights and biases. Weights and biases are examples of parameters trained on a machine learning model. Different layers of a machine learning model can be trained individually.

[0089] Machine learning models can include various connectivity patterns, such as any of feedforward networks, hierarchical structures, recursive architectures, feedback connections, etc. Connections between layers of a neural network can be fully connected or locally connected. In a fully connected neural network, neurons in the first layer can pass their outputs to every neuron in the second layer, and every neuron in the second layer can receive inputs from every neuron in the first layer. In a locally connected network, neurons in the first layer can connect to a limited number of neurons in the second layer. In some aspects, convolutional networks can be locally connected and configured using shared connection strengths associated with the inputs of each neuron in the second layer. Locally connected layers of a network can be configured such that each neuron in the layer has the same or similar connectivity pattern but different connection strengths.

[0090] Machine learning models, or neural networks, can be trained. For example, a machine learning model can be trained based on supervised learning. During training, the machine learning model is presented with the inputs it uses to compute to produce the output. The actual output can be compared to the target output, and the difference can be used to adjust the parameters of the machine learning model, such as weights and biases, to provide an output that is 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 can be calculated. The weights of the machine learning model can then be adjusted so that the output is more closely aligned with the target. To adjust the weights, the learning algorithm can compute gradient vectors over the weights. The gradient indicates the amount by which the error will increase or decrease with slight adjustments to the weights. At the top layers, the gradient corresponds directly to the values ​​of the weights connecting the activated neurons in the penultimate layer to the neurons in the output layer. In lower layers, the gradient may depend on the values ​​of the weights and the error gradient computed in the higher layers. The weights can then be adjusted to reduce the error or move the output closer to the target. This method of adjusting the weights can be called backpropagation through the neural network. The process can continue until the achievable error rate stops decreasing, or until the error rate has reached the target level.

[0091] These machine learning models can include computational complexity and a large number of processors used to train them. The output of one node is connected as input to another node. Connections between nodes can be called edges, and weights can be applied to the connections / edges to adjust the output from one node used as input to another. Nodes can be thresholded to determine whether or when to provide output to connected nodes. The output of each node can be computed as a non-linear function of the sum of the inputs to that node. Neural networks can include any number of nodes and any type of connection between them. Neural networks can include one or more hidden nodes. Nodes can be aggregated into layers, and different layers of the neural network can perform different kinds of transformations on the input. A signal can travel from the input at the first layer through multiple layers of the neural network to the output at the last layer, and can traverse these layers multiple times.

[0092] The management of AI / ML models may include model training (e.g., as described in conjunction with 404), model deployment, model inference (e.g., as described in conjunction with 406), model monitoring (e.g., performance monitoring), and model updates.

[0093] In some areas, AI / ML models can be used for air interface and beam prediction purposes. Using AI / ML models for beam prediction can help reduce overhead and latency, and can also help improve beam selection accuracy. Figure 5A Figure 500 illustrates an example of spatial beam prediction using an AI / ML model. In one example, such as Figure 5A As shown, AI / ML model 502 can be used for wide-to-narrow beam prediction. In this example, the UE can measure the signal (e.g., a reference signal) received on a set of wider beams 510, and based on the measurement results for that set of wider beams 510, AI / ML model 502 can predict measurements for a set of narrower beams 512. The predicted measurements enable the UE to select one of the narrower beams to receive wireless communication without actually performing measurements on the signal received on that narrower set of beams. Figure 5B Figure 520 is another example illustrating spatial beam prediction using an AI / ML model. Figure 5B In this process, the UE can measure the signal received on a subgroup of beam 530 (e.g., a reference signal), and based on the measurement results of the subgroup of beam 530, the AI / ML model 522 can predict the optimal beam in a larger set of beams 532. As an example, the output of the AI / ML model 522 can be the beam index or its identifier (ID) (e.g., beam ID) or the prediction layer 1 (L1) reference signal received power (RSRP) associated with the predicted optimal beam, depending on how the AI / ML model 522 has been trained.

[0094] In the context of beam prediction using an AI / ML model, a set of beams whose measurements are used as input to the AI / ML model (e.g., a subgroup of wider beams 510 or beams 530) may be referred to as "Group B" beams, and a set of beams for which the AI / ML model performs predictions (e.g., a narrower set of beams 512 or a set of beams 532) may be referred to as "Group A" beams. Figure 5A As shown, in an example of wide-to-narrow beam prediction, group B beams may consist of wider beams (e.g., beam 510), while group A beams may consist of narrower beams (e.g., beam 512). Figure 5B In the example, group B beam (e.g., beam 530) can be a subgroup of group A beam (e.g., beam 532).

[0095] Figure 5C Figure 540 illustrates an example of temporal beam prediction using an AI / ML model. Figure 5C In the example, beam measurements can be performed on a set of historical beam measurements (such as measurements of signals received on the beam at times 552 and 554) to predict beam measurements at a time when no measurements are performed (e.g., at 564). The measurements performed on this set of historical beam measurements can be used as input to AI / ML model 542, which predicts the optimal beam from the set of beams at the time when the UE does not perform beam measurements (as shown at 564). The output of AI / ML model 542 can be in the form of a beam index or its ID, or in the form of a predicted L1-RSRP associated with the predicted optimal beam. In time-based beam prediction, in some examples, group B beams can be a subgroup of group A beams; in some examples, group B beams may not be a subgroup of group A beams. And in some other examples, group B beams and group A beams can be the same set of beams, and the beam quality prediction is for a time period different from the time of the beam measurements.

[0096] When using AI / ML models for beam prediction, the performance of the AI / ML models can be monitored to ensure that they consistently meet performance expectations in real-world operating environments. In some examples, to evaluate the performance of the AI / ML model in beam prediction, the network (e.g., a base station) may transmit signals (e.g., reference signals) to the UE on actual Group A beams after the AI / ML model has made its predictions. The UE may then perform measurements on the signals received on these Group A beams. The UE can then evaluate the performance of the AI / ML model by comparing these measurements with the predictions of the AI / ML model (e.g., by checking whether the optimal beam determined based on the actual measurements matches the predicted optimal beam).

[0097] Performance monitoring of AI / ML models can be implemented on the UE side, network (NW) side, or a hybrid model, depending on which entity (e.g., network or UE) calculates the key performance indicators (KPIs) associated with the prediction and makes subsequent decisions related to monitoring, such as model selection, activation, deactivation, switching, and rollback mechanisms.

[0098] Figure 6A Figure 600 illustrates examples of UE-side performance monitoring of AI / ML models according to various aspects of this disclosure. Figure 6A In this example, some sends can be skipped.

[0099] exist Figure 6A In some aspects, the UE may transmit a UE AI / ML capability indication to base station 604 at 606 to notify the network that the UE supports AI / ML capabilities. This capability indication may relate to the UE's ability to handle various Group A and Group B beam configurations. As an example, via the capability indication, UE 602 may notify base station 604 that it has the capability to process spatial domain beam prediction measurements. In some aspects, the UE may provide additional information, such as the number of beams used by the UE to support spatial domain beam prediction. Although in Figure 6A Not illustrated, however, the UE can perform measurements on a group of beams (Group B) and can predict measurements for a group of beams (Group A), for example, as in combination Figures 5A to 5C Described by any of them.

[0100] As an example, the UE may instruct support for spatial domain beam prediction measurements for four wide beams to predict measurements for up to sixteen narrow beams. At 608, in some aspects, the UE 602 may transmit to the base station 604 a request for a dedicated RS to be transmitted (e.g., via group A beams) to enable performance monitoring of the UE's beam prediction. In response to the UE's request (at 608), the base station 604 may transmit via group A beams (e.g., via beams A1, ..., A...). i A NThe UE transmits a dedicated RS. In some examples, the transmission of the dedicated RS can be periodic or semi-persistent. At 612, the UE can calculate a monitoring KPI based on measurements of the dedicated RS and AI / ML inference results. In some examples, the KPI can be the L1-RSRP margin. The L1-RSRP margin can be the difference between the L1-RSRP measured on the dedicated RS received on one or more predicted beams and the maximum L1-RSRP (i.e., the L1-RSRP measured on the actual best beam). For example, the UE can predict that the first beam (beam 1) has the highest L1-RSRP measurement. The UE can measure a set of beams 1 to 4 and can measure the highest L1-RSRP measurement for the second beam (beam 2). The UE can then compare the L1-RSRP measured for beam 1 with the L1-RSRP measured for beam 2 to monitor the performance of beam prediction.

[0101] In some examples, at 614, UE 602 may transmit information about monitored KPIs (which may be referred to as performance information) to base station 604. In some examples, at 616, base station 604 may transmit information about LCM operations for the UE-side AI / ML model to UE 602. At 618, UE 602 may perform LCM operations. LCM operations may include, for example, activating, deactivating, or switching AI / ML models. For example, LCM operations may include activating a specific AI / ML model for beam prediction or beam management based on KPIs. LCM operations may include deactivating an AI / ML model for beam prediction based on KPIs. LCM operations may include switching to a different AI / ML model for beam prediction based on KPIs. LCM operations may also include a fallback operation in which the UE performs beam management or beam selection without an AI / ML model. A fallback operation for an AI / ML model may refer to the process of switching to an alternative communication standard or mechanism when the performance of the AI / ML model is considered inefficient.

[0102] For example, based on the information about the monitored KPIs at 614, base station 604 can determine that the predictive performance of the AI / ML model is not meeting expectations. Therefore, for example, base station 604 can instruct UE 602 at 616 to disable the AI / ML model (e.g., using an existing method that does not involve the AI / ML model) or switch to another AI / ML model. In some examples, at 620, UE 602 can report information about the LCM operations performed to base station 604.

[0103] Figure 6B Figure 650 is an example illustrating NW-side performance monitoring of AI / ML models according to various aspects of this disclosure. Although in Figure 6BNot illustrated, however, the UE can perform measurements on a group of beams (Group B) and can predict measurements for a group of beams (Group A), for example, as in combination Figures 5A to 5C Described by any of them. Figure 6B At positions 656, 658, and 660 respectively, and... Figure 6A Similar to 606, 608, and 610. The difference from UE-side performance monitoring is that... Figure 6B In the NW-side performance monitoring shown, AI / ML performance is evaluated by base station 654, not by UE 602. For example, UE 652 may send a measurement report to base station 654 at 662. The measurement report may include measurements performed by UE 652 on a dedicated RS (transmitted by base station 654 at 660). Based on the measurement report, base station 654 may evaluate AI / ML performance at 664. Then, in conjunction with... Figure 6A In a similar process, UE652 can receive information about LCM operation at 666, perform LCM operation at 668, and report information about the performed LCM operation to base station 654 at 670.

[0104] Figure 7 Figure 700 illustrates examples of hybrid performance monitoring for AI / ML models according to various aspects of this disclosure. Figure 7 At positions 706, 708, and 710 respectively, and Figure 6A Similar to 606, 608, and 610. (And...) Figure 6A and Figure 6B Similarly, although not illustrated, the UE can perform measurements on a group of beams (group B) and can predict measurements for a group of beams (group A), for example, as in combination Figures 5A to 5C As described in either of the above. In hybrid performance monitoring, UE 702 may calculate a monitoring KPI or determine whether an event has occurred at 712. For example, a monitoring KPI may be the L1-RSRP margin, which is the difference between the L1-RSRP measured on a dedicated RS transmitted via one or more predicted beams and the maximum L1-RSRP (i.e., the L1-RSRP measured on the actual optimal beam). The event to be determined by UE 702 may be related to beam integrity. For example, an event may be the detection of a beam failure. The specific event to be determined by UE 702 may be configured by the network (e.g., base station 704).

[0105] Then, at 714, UE 702 reports information to the base station regarding the occurrence of monitoring KPIs or events. For comparison, in Figure 6A UE-side performance monitoring and Figure 6BSuch reports may not be present in the NW-side performance monitoring. Based on the information provided by UE 702 at 714, base station 704 can evaluate AI / ML mode performance at 716. Then, in conjunction with... Figure 6A In a similar process, UE 702 can receive information about LCM operation at 718, perform LCM operation at 720, and report information about the performed LCM operation to base station 704 at 722.

[0106] Figure 8 Figure 800 illustrates examples of beam prediction and beam prediction performance monitoring using a dedicated RS for performance monitoring, according to various aspects of this disclosure. In some examples, the dedicated RS for performance monitoring may be referred to as a beam prediction monitoring reference signal (BPM-RS), or may be referred to by other names. Figure 8 As shown, during the beam prediction phase 801, for time beam prediction 810, base station 804 can transmit RS at intervals that are multiples (e.g., twice) the length of the transmission interval without beam prediction. For example, base station 804 can transmit RS at intervals of 2 x ms (e.g., 40 ms) instead of every x ms (e.g., 20 ms). Within the 2 x ms (e.g., 40 ms) interval, the UE can use the predicted beam (e.g., beam 806) based on previously measured values.

[0107] For spatial beam prediction 840, the UE can measure some beams in the beam (e.g., beams 841 and 843) and apply the beam prediction to other beams (e.g., beams 842 and 844), instead of measuring all beams (e.g., beams 841, 842, 843, 844, etc.). For wide-to-narrow spatial beam prediction 860, the UE can perform measurements on several wider beams (e.g., beam 861) instead of measuring narrow beams (e.g., beam 871), and predict the optimal narrow beam based on the measurements of the wider beams, for example, using an AI / ML model 880.

[0108] Compared to the beam prediction phase (during which the base station transmits different beams or subgroups or times of beams), during the performance monitoring phase 802, the base station may actually transmit reference signals on beams not transmitted during the beam prediction inference phase, and the UE may perform measurements on these beams (e.g., measuring the RSRP of RS received on the beams) to evaluate the accuracy of the UE's beam prediction during the beam prediction phase. For example, base station 804 may transmit BPM-RS on group A beams (e.g., including beam 816), which corresponds to beam 806 not transmitted during beam prediction. Similarly, base station 824 may transmit BPM-RS on beam 852, which corresponds to beam 842 not transmitted during beam prediction. Base station 854 may transmit BPM-RS on narrow beam 881, which corresponds to narrow beam 871 not transmitted during beam prediction.

[0109] The UE can compare the measurements obtained during the performance monitoring phase 802 with the predictions determined during the beam prediction phase 801, and can then perform one or more LCM operations based on the evaluation of the beam predictions.

[0110] Figure 9A Figure 900 is an illustration of examples of performance monitoring according to various aspects of this disclosure. Figure 9A In the example, the UE (or more specifically, AI / ML model 902) performs the top-ranked wide-to-narrow beam prediction, meaning that AI / ML model 902 predicts the optimal narrow beam based on wide beam measurements (e.g., group B). Figure 9A As shown, once the UE (or AI / ML model 902) predicts the optimal narrow beam (e.g., assuming the predicted optimal beam is beam 910), the network can transmit RS on the narrow beams (e.g., group A) for the UE to perform measurements on the RS received on these narrow beams. Based on the measurements, the UE can determine the actual optimal beam, which may differ from the predicted optimal beam. For example, the actual optimal beam could be beam 920. To evaluate the prediction performance of AI / ML model 902, the UE can calculate the L1-RSRP margin. The L1-RSRP margin can be defined as the difference between the L1-RSRP on the predicted optimal beam 910 and the L1-RSRP on the actual optimal beam 920.

[0111] Figure 9B Figure 950 is an illustration of examples of performance monitoring according to various aspects of this disclosure. Figure 9BIn the example, the UE (or more specifically, the AI / ML model 952) can perform top K wide-to-narrow beam prediction, meaning that the AI / ML model 952 predicts the best K (K>1) narrow beams based on wide beam measurements (e.g., group B). To explain, assume the AI / ML model 952 performs top 3 beam prediction, although this concept can be similarly applied to more or fewer than 3 identified beam numbers. Figure 9B As shown, once the UE (or AI / ML model 952) predicts the three optimal narrow beams (assuming these beams are beams 962, 964, and 966), the network can transmit RS on the narrow beams (e.g., group A) for the UE to perform measurements on the RS received on these narrow beams. Based on the measurements, the UE can determine the actual optimal beam, which may differ from the predicted optimal beam. For example, the actual optimal beam could be beam 970. To evaluate the prediction performance of AI / ML model 952, the UE can calculate the L1-RSRP margin. The L1-RSRP margin can be defined as the difference between the maximum L1-RSRP on the predicted beams (e.g., beams 962, 964, and 966) and the L1-RSRP on the actual optimal beam 970.

[0112] Despite the combination Figure 9A and Figure 9B The examples described are for wider and narrower beams, but the concept can be applied to any Group A beam predicted based on Group B beam measurements, including, for example, spatial and / or temporal predictions.

[0113] The L1-RSRP margin reporting mechanism can be implemented in various ways. In one configuration, UE reporting of L1-RSRP margin can be event-triggered. In some examples, the UE can be configured to report the margin if the L1-RSRP margin exceeds a specified threshold (e.g., a deviation threshold). The value of this threshold can be configured, for example, by the base station. In some examples, the UE can be configured to initiate an L1-RSRP margin report if the L1-RSRP margin exceeds a threshold (e.g., a deviation threshold) a specified number of times within a given time frame (e.g., a counter threshold). In some examples, the UE can be configured to report statistics related to the L1-RSRP margin to the base station (e.g., the number of times the L1-RSRP margin exceeds the threshold, the average or standard deviation of these L1-RSRP margins).

[0114] In some examples, L1-RSRP margin reporting can be performed periodically or semi-persistently. As an example, if the UE is configured by the base station using periodic BPM-RS or semi-persistent BPM-RS, there may be accompanying reporting configurations where the UE can be configured to report L1-RSRP margin.

[0115] In some examples, events may be defined in the radio standard or configured by the network (e.g., sent to the UE in a configuration from the base station). For example, if the L1-RSRP margin is consistently greater than a threshold number of times within a set duration, the base station may configure the UE to perform certain LCM operations, which may include disabling AI / ML functionality, switching to other AI / ML functionality, or reverting to a legacy procedure (without involving any AI / ML functionality).

[0116] Figure 10 This is a call flowchart 1000 illustrating a method of wireless communication according to various aspects of this disclosure. Various aspects are described in conjunction with UE 1002 and base station 1004. Each aspect may be performed by UE 1002 or base station 1004 in the aggregation and / or by one or more components of base station 1004 (e.g., such as CU 110, DU 130, and / or RU 140). In some examples, UE 1002 may include or be associated with an AI / ML model 1006. The AI / ML model 1006 may include... Figure 4 Various functionalities are illustrated in the text, such as data collection 402, model training function 404, model inference function 406, and participants 408. Figure 10 This illustrates various aspects of AI / ML performance monitoring that can be performed on beam prediction for a UE. The UE can perform beam prediction for a set of beams (e.g., group A) based on measurements performed on group B, for example, by combining... Figures 5A to 5C , Figure 8 , Figure 9A or Figure 9B Described by any of them.

[0117] like Figure 10 As shown, at 1008, in some respects, UE 1002 may send a request for a set of RSs to base station 1004. For example, refer to Figure 7 UE 702 can send a request for a dedicated RS for performance monitoring to base station 704 at 708.

[0118] At 1010, base station 1004 can transmit an initial set of RS to UE 1002 using an initial set of beams (e.g., beam 1040) (e.g., group B). The initial set of beams (e.g., beam 1040) can be group B beams used for beam prediction purposes. For example, refer to... Figure 8 The base station 854 may use an initial set of beams (e.g., beam 861) to send an initial set of RS (e.g., BPM-RS) to the UE.

[0119] At position 1012, UE 1002 can perform preliminary beam measurements on a preliminary set of RSs. For example, refer to Figure 8The UE (AI / ML model 880) can perform preliminary beam measurements on a preliminary set of RSs (e.g., BPM-RS).

[0120] At position 1014, UE 1002 can predict one or more predicted beams from a first group of beams (e.g., group A). ​​The first group of beams can be based on preliminary beam measurements of group B. For example, referencing Figure 8 The UE (AI / ML model 880) can predict one or more predicted beams (e.g., beam 871) from the first set of beams. The first set of beams can be based on preliminary beam measurements (e.g., measurements of beam 861). Reference Figure 9A The UE can predict a prediction beam 910 from the first group of beams. (Reference) Figure 9B The UE can predict three beams (beams 962, 964 and 966) from the first group of beams.

[0121] At 1016, base station 1004 can use a first set of beams (e.g., beam 1050) (e.g., group A) to send a first set of RS to UE 1002, allowing the UE to monitor the predicted performance of the UE based on measurements of group B. In some examples, the first set of RS at 1016 and the initial set of RS at 1010 can be the same set of RS. In some other examples, the first set of RS at 1016 can be different from the initial set of RS at 1010. For example, refer to... Figure 8 During the performance monitoring phase 802, the base station 824 may use the first set of beams (e.g., beam 852) to send the first set of RS (e.g., BPM-RS) to the UE.

[0122] At 1018, UE 1002 can perform a first beam measurement for a first group of beams that includes one or more predicted beams. For example, refer to Figure 8 During the performance monitoring phase 802, the UE may perform a first beam measurement for a first group of beams that includes one or more predicted beams (e.g., perform measurements for beams 816, 852, and 881).

[0123] At point 1020, base station 1004 can send a threshold configuration indicating a deviation threshold. The deviation threshold can be used to determine whether UE 1002 will send information related to the first beam measurement to base station 1004.

[0124] At 1022, base station 1004 can send a report configuration to UE 1002. The report configuration can indicate one or more of a periodic mode or a semi-persistent mode for sending information related to the first beam measurement.

[0125] At 1024, UE 1002 may send performance information to base station 1004, indicating a difference between a first signal measurement and a second signal measurement based on a first beam measurement associated with one or more predicted beams, and the second signal measurement associated with one or more beams in a first group of beams. For example, refer to... Figure 7 UE 702 can send information about monitoring KPIs to base station 704. In some examples, the monitoring KPIs may include the difference between a first signal measurement and a second signal measurement based on a first beam measurement associated with one or more predicted beams, and the second signal measurement associated with one or more beams in a first set of beams. (Reference) Figure 9A The monitoring KPI can be the L1-RSRP margin, which is the difference between the predicted L1-RSRP on the optimal beam 910 and the actual L1-RSRP on the optimal beam 920. (Reference) Figure 9B L1-RSRP margin can also be the difference between the maximum L1-RSRP on the predicted beams (e.g., beams 962, 964, and 966) and the L1-RSRP on the actual best beam 970.

[0126] At 1026, UE 1002 may perform an LCM operation on the AI / ML model in response to a triggering condition being met. The LCM operation may include one or more of the following: activating the AI / ML model, deactivating the AI / ML model, switching to another AI / ML model different from the AI / ML model, or performing a rollback operation on the AI / ML model. For example, refer to... Figure 7 UE 702 can perform LCM operations on AI / ML models at 720.

[0127] Figure 11 This is a flowchart 1100 illustrating a method for wireless communication at a UE according to various aspects of this disclosure. The method can be performed by the UE. The UE can be UE 104, 350, 702, 1002, or... Figure 15 The hardware implementation of device 1504 improves the reliability and verifiability of beam selection predictions made by AI / ML models. By calculating the difference between the predicted optimal beam and the actual optimal beam (such as L1-RSRP), these methods provide a concrete metric for measuring prediction accuracy. Therefore, these methods improve the accuracy of beam prediction, thereby enhancing the efficiency and reliability of wireless communication.

[0128] like Figure 11 As shown, at 1102, the UE can predict one or more prediction beams from the first set of beams. Figure 7 , Figure 8 , Figure 9A, Figure 9B and Figure 10 Various aspects of combining flowchart 1100 are illustrated. For example, refer to... Figure 10 At position 1014, UE 1002 can predict one or more predicted beams from the first set of beams. (Reference) Figure 8 The UE (AI / ML model 880) can predict one or more predicted beams (e.g., beam 871) from the first set of beams. (See reference) Figure 9A The UE can predict a prediction beam 910 from the first group of beams. (Reference) Figure 9B The UE can predict three beams (beams 962, 964, and 966) from the first set of beams. In some respects, 1102 can be performed by the measurement reporting component 198.

[0129] At 1104, the UE can perform a first beam measurement for a first group of beams that includes one or more predicted beams. For example, refer to Figure 10 UE 1002 can perform a first beam measurement at 1018 for a first group of beams including one or more predicted beams. (Reference) Figure 8 During the performance monitoring phase 802, the UE may perform a first beam measurement for a first group of beams that includes one or more predicted beams (e.g., performing measurements for beams 816, 852, and 881). In some aspects, 1104 may be performed by the measurement reporting component 198.

[0130] At point 1106, the UE may send performance information to the network node, indicating the difference between a first signal measurement and a second signal measurement based on a first beam measurement associated with one or more predicted beams, and the second signal measurement associated with one or more beams in a first set of beams. The network node may be a network entity, which may be... Figure 1 The base station or base station component in the access network, or core network component (e.g., base stations 102, 310, 704, 804, 824, 854, 1004; or Figure 15 (Network entity 1502 in the specific hardware implementation). For example, refer to Figure 10 UE 1002 may send performance information to the network node (base station 1004) at 1024. This performance information indicates the difference between a first signal measurement and a second signal measurement based on a first beam measurement associated with one or more predicted beams, and the second signal measurement associated with one or more beams in a first group of beams. (Reference) Figure 7UE702 can send information about monitoring KPIs to base station 704 at 714. In some examples, the monitoring KPIs may include the difference between a first signal measurement and a second signal measurement based on a first beam measurement associated with one or more predicted beams, and the second signal measurement associated with one or more beams in a first set of beams. (Reference) Figure 9A The monitoring KPI can be the L1-RSRP margin, which is the difference between the predicted L1-RSRP on the optimal beam 910 and the actual L1-RSRP on the optimal beam 920. (Reference) Figure 9B The L1-RSRP margin can also be the difference between the maximum L1-RSRP on the predicted beams (e.g., beams 962, 964, and 966) and the L1-RSRP on the actual optimal beam 970. In some respects, 1106 can be performed by the measurement reporting component 198.

[0131] Figure 12 This is a flowchart 1200 illustrating a method for wireless communication at a UE according to various aspects of this disclosure. The method can be performed by the UE. The UE can be UE 104, 350, 702, 1002, or... Figure 15 The hardware implementation of device 1504 improves the reliability and verifiability of beam selection predictions made by AI / ML models. By calculating the difference between the predicted optimal beam and the actual optimal beam (such as L1-RSRP), these methods provide a concrete metric for measuring prediction accuracy. Therefore, these methods improve the accuracy of beam prediction, thereby enhancing the efficiency and reliability of wireless communication.

[0132] like Figure 12 As shown, at 1206, the UE can predict one or more prediction beams from the first group of beams. Figure 7 , Figure 8 , Figure 9A , Figure 9B and Figure 10 Examples of various aspects of the steps combined with flowchart 1200 are shown. For example, refer to... Figure 10 At position 1014, UE 1002 can predict one or more predicted beams from the first set of beams. (Reference) Figure 8 The UE (AI / ML model 880) can predict one or more predicted beams (e.g., beam 871) from the first set of beams. (See reference) Figure 9A The UE can predict a prediction beam 910 from the first group of beams. (Reference) Figure 9B The UE can predict three beams (beams 962, 964, and 966) from the first set of beams. In some respects, 1206 can be performed by the measurement reporting component 198.

[0133] At 1210, the UE can perform a first beam measurement for a first group of beams that includes one or more predicted beams. For example, refer to Figure 10 UE 1002 can perform a first beam measurement at 1018 for a first group of beams including one or more predicted beams. (Reference) Figure 8 During the performance monitoring phase 802, the UE may perform a first beam measurement for a first group of beams that includes one or more predicted beams (e.g., performing measurements for beams 816, 852, and 881). In some aspects, 1210 may be performed by the measurement reporting component 198.

[0134] At point 1216, the UE may send performance information to the network node, indicating the difference between a first signal measurement and a second signal measurement based on a first beam measurement associated with one or more predicted beams, and the second signal measurement associated with one or more beams in a first set of beams. The network node may be a network entity. Figure 1 The base station or base station component in the access network, or core network component (e.g., base stations 102, 310, 704, 804, 824, 854, 1004; or Figure 15 (Network entity 1502 in the specific hardware implementation). For example, refer to Figure 10 UE 1002 may send performance information to the network node (base station 1004) at 1024. This performance information indicates the difference between a first signal measurement and a second signal measurement based on a first beam measurement associated with one or more predicted beams, and the second signal measurement associated with one or more beams in a first group of beams. (Reference) Figure 7 UE702 can send information about monitoring KPIs to base station 704 at 714. In some examples, the monitoring KPIs may include the difference between a first signal measurement and a second signal measurement based on a first beam measurement associated with one or more predicted beams, and the second signal measurement associated with one or more beams in a first set of beams. (Reference) Figure 9A The monitoring KPI can be the L1-RSRP margin, which is the difference between the predicted L1-RSRP on the optimal beam 910 and the actual L1-RSRP on the optimal beam 920. (Reference) Figure 9B The L1-RSRP margin can also be the difference between the maximum L1-RSRP on the predicted beams (e.g., beams 962, 964, and 966) and the L1-RSRP on the actual optimal beam 970. In some respects, 1216 can be performed by the measurement reporting component 198.

[0135] In some aspects, the first signal measurement may be a first maximum L1-RSRP on the one or more predicted beams, and the second signal measurement may be a second maximum L1-RSRP on the one or more beams in the first set of beams. For example, refer to Figure 9B The first signal measurement may be the first maximum L1-RSRP on the one or more predicted beams (e.g., beams 962, 964, and 966), and the second signal measurement may be the second maximum L1-RSRP on the one or more beams in the first set of beams (e.g., beam 970).

[0136] In some respects, at 1204, the UE can perform preliminary beam measurements on a preliminary set of beams respectively. The first set of beams can be based on the preliminary beam measurements. For example, refer to Figure 10 UE 1002 can perform preliminary beam measurements on a preliminary set of beams at 1012. The first set of beams can be based on the preliminary beam measurements. In some respects, 1204 can be performed by the measurement reporting component 198.

[0137] In some aspects, in order to predict one or more predicted beams (at 1206) from the first set of beams, the UE can predict one or more predicted beams from the first set of beams based on an AI / ML model and preliminary beam measurements. For example, refer to Figure 8 The UE can predict one or more predicted beams from the first set of beams based on AI / ML model 880 and preliminary beam measurements (e.g., measurements of beam 861).

[0138] In some respects, at 1202, the UE may request a set of RSs, and at 1208, receive the first set of RSs via the first set of beams. To perform a first beam measurement for the first set of beams separately (at 1210), the UE may perform the first beam measurement for the first set of beams based on the first set of RSs. For example, refer to... Figure 10 UE 1002 may request a set of RSs at 1008 and receive the first set of RSs via the first set of beams at 1016. In some respects, 1202 and 1208 may be performed by the measurement reporting component 198.

[0139] In some aspects, the one or more predicted beams may include a single predicted beam, and performance information may indicate the difference between a first maximum L1-RSRP on the single predicted beam and a second maximum L1-RSRP on the one or more beams in the first set of beams. For example, refer to Figure 9AThe one or more predicted beams may include a predicted beam (e.g., beam 910), and performance information may indicate the difference between a first maximum L1-RSRP on the one predicted beam (e.g., beam 910) and a second maximum L1-RSRP on the one or more beams in the first set of beams (e.g., beam 920).

[0140] In some aspects, the one or more predicted beams may include multiple predicted beams, and performance information may indicate the difference between a first maximum L1-RSRP on the multiple predicted beams and a second maximum L1-RSRP on the one or more beams in the first set of beams. For example, refer to Figure 9B The one or more predicted beams may include multiple predicted beams (e.g., beams 962, 964, and 966), and the performance information may indicate the difference between a first maximum L1-RSRP on the multiple predicted beams (e.g., beams 962, 964, and 966) and a second maximum L1-RSRP on the one or more beams in the first set of beams (e.g., beam 970).

[0141] In some respects, in order to send performance information indicating this difference (at 1216), the UE may send performance information indicating this difference to the network node in response to the fulfillment of a triggering condition. For example, refer to Figure 10 UE 1002 may send a transmission to the network node (base station 1004) at 1024 in response to the fulfillment of the trigger condition. In some respects, 1216 may be performed by the measurement reporting component 198.

[0142] In some respects, the triggering condition can be that the difference exceeds a deviation threshold. For example, refer to... Figure 10 The trigger condition (used to send information at 1024) can be that the difference is greater than the deviation threshold.

[0143] In some respects, at 1212, the UE can receive a threshold configuration indicating a deviation threshold from the network node. For example, refer to Figure 10 UE 1002 can receive a threshold configuration indicating a deviation threshold from the network node (base station 1004) at 1020. In some respects, 1212 can be performed by the measurement reporting component 198.

[0144] In some respects, the triggering condition could be that the difference exceeds a deviation threshold for a first time within the first duration, and this first time may exceed a counter threshold. For example, refer to... Figure 10 The trigger condition (used to send information at 1024) can be that the difference is greater than the deviation threshold for the first time within the first duration, and the first time can be greater than the counter threshold.

[0145] In some respects, this information may also include statistical data related to differences within the first duration. For example, referencing Figure 10 The information (sent at 1024) may also include statistics related to the differences within the first duration.

[0146] In some respects, at 1218, the UE can perform LCM operations on the AI / ML model in response to the fulfillment of a triggering condition. For example, refer to Figure 10 At 1026, UE 1002 can perform LCM operations on the AI / ML model in response to the fulfillment of a triggering condition. In some respects, 1218 can be performed by the measurement reporting component 198.

[0147] In some respects, the AI / ML model can be a first AI / ML model, and LCM operations can include one or more of the following: activating the first AI / ML model, deactivating the first AI / ML model, switching to a second AI / ML model different from the first AI / ML model, or performing a rollback operation on the first AI / ML model. For example, see [reference]. Figure 10 AI / ML model 1006 can be a first AI / ML model, and the LCM operation (at 1026) can include one or more of the following: activating the first AI / ML model 1006, deactivating the first AI / ML model 1006, switching to a second AI / ML model different from the first AI / ML model 1006, or performing a rollback operation on the first AI / ML model 1006.

[0148] In some respects, in order to send performance information indicating this difference (at 1216), the UE may send the performance information indicating the difference in either a periodic mode or a semi-persistent mode. For example, refer to Figure 10 UE 1002 may send performance information indicating the difference at 1024 in either periodic or semi-persistent mode.

[0149] In some respects, at 1214, the UE can receive a report configuration from the network node indicating one or more of the periodic or semi-persistent modes. For example, refer to Figure 10 UE 1002 can receive a report configuration indicating one or more of the periodic or semi-persistent modes from the network node (base station 1004) at 1022. In some aspects, 1214 can be performed by the measurement reporting component 198.

[0150] Figure 13 This is a flowchart 1300 illustrating a method for wireless communication at a network node according to various aspects of this disclosure. The method can be performed by a network node. The network node can be a network entity, which can be... Figure 1The base station or base station component in the access network, or core network component (e.g., base stations 102, 310, 704, 804, 824, 854, 1004; or Figure 15 (Network entity 1502 in the hardware implementation). This method improves the reliability and verifiability of beam selection predictions made by AI / ML models. By calculating the difference between the predicted optimal beam and the actual optimal beam (such as L1-RSRP), these methods provide a concrete metric for measuring prediction accuracy. Therefore, these methods improve the accuracy of beam prediction, thereby improving the efficiency and reliability of wireless communication.

[0151] like Figure 13 As shown, at 1302, the network node can send a first set of RS to the UE via the first set of beams to initiate the UE to predict one or more prediction beams from the first set of beams. The UE can be UE 104, 350, 702, 1002, or... Figure 15 The hardware implementation of the device 1504. Figure 7 , Figure 8 , Figure 9A , Figure 9B and Figure 10 Examples of various aspects of the steps combined with flowchart 1300 are shown. For example, refer to... Figure 10 The network node (base station 1004) can send a first set of RS to UE 1002 at 1016 via a first set of beams (e.g., beam 1050) to initiate UE 1002 to predict one or more prediction beams from the first set of beams (e.g., 1050). For example, refer to Figure 8 During the performance monitoring phase 802, the base station 824 may use a first set of beams (e.g., beam 852) to send a first set of RS (e.g., BPM-RS) to the UE. In some aspects, 1302 may be performed by the measurement reporting component 199.

[0152] At 1304, the network node can receive performance information from the UE indicating a difference between a first signal measurement and a second signal measurement based on a first beam measurement of a first group of beams, the first signal measurement being associated with one or more predicted beams from the first group of beams, and the second signal measurement being associated with one or more beams in the first group of beams. For example, refer to... Figure 10 The network node (base station 1004) can receive performance information from UE 1002 at 1024. This performance information indicates the difference between a first signal measurement and a second signal measurement based on a first beam measurement of a first group of beams, the first signal measurement being associated with one or more predicted beams from the first group of beams, and the second signal measurement being associated with one or more beams in the first group of beams. (Reference) Figure 9AThis difference can be the L1-RSRP margin, which is the difference between the predicted L1-RSRP on the optimal beam 910 and the actual L1-RSRP on the optimal beam 920. (Reference) Figure 9B This difference can be an L1-RSRP margin, which can be the difference between the maximum L1-RSRP on the predicted beams (e.g., beams 962, 964, and 966) and the actual optimal L1-RSRP on the optimal beam 970. In some respects, 1304 can be performed by the measurement reporting component 199.

[0153] Figure 14 This is a flowchart 1400 illustrating a method for wireless communication at a network node according to various aspects of this disclosure. The method can be performed by a network node. The network node can be a network entity, which can be... Figure 1 The base station or base station component in the access network, or core network component (e.g., base stations 102, 310, 704, 804, 824, 854, 1004; or Figure 15 (Network entity 1502 in the hardware implementation). This method improves the reliability and verifiability of beam selection predictions made by AI / ML models. By calculating the difference between the predicted optimal beam and the actual optimal beam (such as L1-RSRP), these methods provide a concrete metric for measuring prediction accuracy. Therefore, these methods improve the accuracy of beam prediction, thereby improving the efficiency and reliability of wireless communication.

[0154] like Figure 14 As shown, at position 1406, the network node can send a first set of RS to the UE via the first set of beams to initiate the UE to predict one or more prediction beams from the first set of beams. The UE can be UE 104, 350, 702, 1002, or... Figure 15 The hardware implementation of the device 1504. Figure 7 , Figure 8 , Figure 9A , Figure 9B and Figure 10 Examples of various aspects of the steps combined with flowchart 1400 are shown. For example, refer to... Figure 10 The network node (base station 1004) can send a first set of RS to UE 1002 at 1016 via a first set of beams (e.g., beam 1050) to initiate UE 1002 to predict one or more prediction beams from the first set of beams (e.g., 1050). For example, refer to Figure 8 During the performance monitoring phase 802, the base station 824 may use a first set of beams (e.g., beam 852) to send a first set of RS (e.g., BPM-RS) to the UE. In some aspects, 1406 may be performed by the measurement reporting component 199.

[0155] At 1412, the network node can receive performance information from the UE indicating a difference between a first signal measurement and a second signal measurement based on a first beam measurement of a first group of beams, the first signal measurement being associated with one or more predicted beams from the first group of beams, and the second signal measurement being associated with one or more beams in the first group of beams. For example, refer to... Figure 10 The network node (base station 1004) can receive performance information from UE 1002 at 1024. This performance information indicates the difference between a first signal measurement and a second signal measurement based on a first beam measurement of a first group of beams, the first signal measurement being associated with one or more predicted beams from the first group of beams, and the second signal measurement being associated with one or more beams in the first group of beams. (Reference) Figure 9A This difference can be the L1-RSRP margin, which is the difference between the predicted L1-RSRP on the optimal beam 910 and the actual L1-RSRP on the optimal beam 920. (Reference) Figure 9B This difference can be an L1-RSRP margin, which can be the difference between the maximum L1-RSRP on the predicted beams (e.g., beams 962, 964, and 966) and the L1-RSRP on the actual optimal beam 970. In some respects, 1412 can be performed by the measurement reporting component 199.

[0156] In some aspects, the first signal measurement may be a first maximum L1-RSRP on the one or more predicted beams, and the second signal measurement may be a second maximum L1-RSRP on the one or more beams in the first set of beams. For example, refer to Figure 9B The first signal measurement may be the first maximum L1-RSRP on the one or more predicted beams (e.g., beams 962, 964, and 966), and the second signal measurement may be the second maximum L1-RSRP on the one or more beams in the first set of beams (e.g., beam 970).

[0157] In some respects, at 1404, the network node can send an initial set of RS to the UE via an initial set of beams to initiate the UE to perform initial beam measurements on the initial set of beams, and the first set of beams is based on the initial beam measurements. For example, refer to Figure 10 The network node (base station 1004) may send a preliminary set of RS to the UE at 1010 via a preliminary set of beams (e.g., beam 1040) to initiate preliminary beam measurements by the UE 1002 at 1012 on the preliminary set of beams (e.g., beam 1040), and the first set of beams may be based on the preliminary beam measurements. In some aspects, 1404 may be performed by the measurement reporting component 199.

[0158] In some respects, at 1402, the network node may receive a request from the UE for a set of RS. In order to transmit the first set of RS via the first set of beams (at 1406), the network node may respond to this request by transmitting the first set of RS via the first set of beams. For example, refer to... Figure 10 The network node (base station 1004) may receive a request for a set of RS from UE 1002 at 1008. In order to transmit the first set of RS via the first set of beams (at 1016), the network node may respond to the request by transmitting the first set of RS via the first set of beams (e.g., beam 1050). In some aspects, 1402 may be performed by the measurement reporting component 199.

[0159] In some aspects, the one or more predicted beams may include a single predicted beam, and performance information may indicate the difference between a first maximum L1-RSRP on the single predicted beam and a second maximum L1-RSRP on the one or more beams in the first set of beams. For example, refer to Figure 9A The one or more predicted beams may include a predicted beam (e.g., beam 910), and performance information may indicate the difference between a first maximum L1-RSRP on the one predicted beam (e.g., beam 910) and a second maximum L1-RSRP on the one or more beams in the first set of beams (e.g., beam 920).

[0160] In some aspects, the one or more predicted beams may include multiple predicted beams, and performance information may indicate the difference between a first maximum L1-RSRP on the multiple predicted beams and a second maximum L1-RSRP on the one or more beams in the first set of beams. For example, refer to Figure 9B The one or more predicted beams may include multiple predicted beams (e.g., beams 962, 964, and 966), and the performance information may indicate the difference between a first maximum L1-RSRP on the multiple predicted beams (e.g., beams 962, 964, and 966) and a second maximum L1-RSRP on the one or more beams in the first set of beams (e.g., beam 970).

[0161] In some respects, in order to receive performance information indicating this difference (at 1412), a network node may receive performance information indicating this difference in response to a triggering condition being met. For example, refer to Figure 10 In order to receive performance information indicating the difference (at 1024), the network node (base station 1004) may receive performance information indicating the difference in response to the fulfillment of a trigger condition.

[0162] In some respects, the triggering condition can be a difference greater than a deviation threshold. For example, reference... Figure 10The trigger condition (used to receive information at 1024) can be that the difference is greater than the deviation threshold.

[0163] In some respects, at point 1408, the network node can send a threshold configuration indicating the deviation threshold to the UE. For example, refer to... Figure 10 The network node (base station 1004) can send a threshold configuration indicating a deviation threshold to the UE 1002 at 1020. In some respects, 1408 can be performed by the measurement reporting component 199.

[0164] In some respects, the triggering condition could be that the difference exceeds a deviation threshold for a first time within the first duration, and this first time may exceed a counter threshold. For example, refer to... Figure 10 The trigger condition (for receiving information at 1024) can be that the difference is greater than the deviation threshold for the first time within the first duration, and the first time can be greater than the counter threshold.

[0165] In some respects, this information may also include statistical data related to differences within the first duration. For example, referencing Figure 10 The information received at 1024 may also include statistical data related to the differences within the first duration.

[0166] In some respects, in order to receive performance information indicating this difference (at 1412), a network node may receive the performance information indicating the difference in either a periodic or semi-persistent mode. For example, refer to... Figure 10 In order to receive performance information indicating the difference (at 1024), the network node (base station 1004) may receive the performance information indicating the difference in either a periodic mode or a semi-persistent mode.

[0167] In some respects, at 1410, the network node can send a report configuration to the UE indicating one or more of the periodic or semi-persistent modes. For example, refer to Figure 10 The network node (base station 1004) can send a report configuration indicating one or more of the periodic or semi-persistent modes to the UE 1002 at 1022. In some aspects, 1410 can be performed by the measurement reporting component 199.

[0168] Figure 15Figure 1500 illustrates an example of a hardware implementation for device 1504. Device 1504 may be a UE, a component of a UE, or implement UE functionality. In some aspects, device 1504 may include at least one cellular baseband processor 1524 (also referred to as a modem) coupled to one or more transceivers 1522 (e.g., cellular RF transceivers). Cellular baseband processor 1524 may include at least one on-chip memory 1524'. In some aspects, device 1504 may also include one or more Subscriber Identity Module (SIM) cards 1520 and at least one application processor 1506 coupled to a Secure Digital Card (SD) card 1508 and a screen 1510. Application processor 1506 may include on-chip memory 1506'. In some aspects, 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., a barometric pressure sensor / altimeter; motion sensors such as an inertial measurement unit (IMU), gyroscope, and / or accelerometer; light detection and ranging (LIDAR), radio-assisted detection and ranging (RADAR), sound navigation and ranging (SONAR), magnetometer, audio, and / or other technologies for positioning), an additional memory module 1526, a power supply 1530, and / or a camera 1532. Bluetooth module 1512, WLAN module 1514, and SPS module 1516 may include an on-chip transceiver (TRX) (or in some cases, only a receiver (RX)). Bluetooth module 1512, WLAN module 1514, and SPS module 1516 may include their own dedicated antennas and / or communicate using antenna 1580. Cellular baseband processor 1524 communicates with UE 104 and / or RU associated with network entity 1502 via transceiver 1522 through one or more antennas 1580. Cellular baseband processor 1524 and application processor 1506 may each include computer-readable media / memory 1524', 1506'. Additional memory module 1526 may also be considered computer-readable media / memory. Each computer-readable media / memory 1524', 1506', 1526 may be non-transitory. Cellular baseband processor 1524 and application processor 1506 are each responsible for general processing, including executing software stored on the computer-readable media / memory. When executed by cellular baseband processor 1524 / application processor 1506, the software causes cellular baseband processor 1524 / application processor 1506 to perform the various functions described above. Cellular baseband processor 1524 and application processor 1506 are configured to perform the various functions described above based at least in part on information stored in memory.In other words, the cellular baseband processor 1524 and application processor 1506 can be configured to perform a first subgroup of the various functions described above without information stored in memory, and can be configured to perform a second subgroup of the various functions described above based on information stored in memory. The computer-readable medium / memory can also be used to store data manipulated by the cellular baseband processor 1524 / application processor 1506 during software execution. The cellular baseband processor 1524 / application processor 1506 can be a component of the UE 350 and can include at least one of a memory 360 and / or at least one of a TX processor 368, an RX processor 356, and a controller / processor 359. In one configuration, the device 1504 can be at least one processor chip (modem and / or application) and includes only the cellular baseband processor 1524 and / or application processor 1506, while in another configuration, the device 1504 can be the entire UE (e.g., see [link]). Figure 3 The UE 350 includes an additional module of the device 1504.

[0169] As discussed above, component 198 can be configured to predict one or more predicted beams from a first set of beams; perform first beam measurements for the first set of beams including the one or more predicted beams; and send performance information to a network node indicating a difference between a first signal measurement and a second signal measurement based on the first beam measurements, the first signal measurement being associated with the one or more predicted beams, and the second signal measurement being associated with one or more beams in the first set of beams. Component 198 can be further configured to perform a combination Figure 11 and Figure 12 The flowchart described and / or by Figure 10Component 198 may be any aspect of the UE 1002's execution. Component 198 may be within the cellular baseband processor 1524, application processor 1506, or both. Component 198 may be one or more hardware components specifically configured to execute the stated process / algorithm, implemented by one or more processors configured to execute the stated process / algorithm, stored in a computer-readable medium for implementation by one or more processors, or some combination thereof. When multiple processors are implemented, the multiple processors may execute the stated process / algorithm individually or in combination. As shown, apparatus 1504 may include a variety of components configured for various functions. In one configuration, device 1504 (and specifically cellular baseband processor 1524 and / or application processor 1506) includes: means for predicting one or more predicted beams from a first set of beams; means for performing first beam measurements for the first set of beams, including the one or more predicted beams; and means for sending performance information to a network node, the performance information indicating a difference between a first signal measurement and a second signal measurement based on the first beam measurement, the first signal measurement being associated with the one or more predicted beams, and the second signal measurement being associated with one or more beams in the first set of beams. Device 1504 may also include means for performing a combination Figure 11 and Figure 12 The aspects described in the flowchart and / or by Figure 10 The component can be any of the aspects performed by UE 1002. The component can be a component 198 of device 1504 configured to perform the functions described therein. As described above, device 1504 may include a TX processor 368, an RX processor 356, and a controller / processor 359. Therefore, in one configuration, these components can be the TX processor 368, the RX processor 356, and / or the controller / processor 359 configured to perform the functions described therein.

[0170] Figure 16Figure 1600 illustrates an example of a hardware implementation for network entity 1602. Network entity 1602 may be a BS, a component of a BS, or implement BS functionality. Network entity 1602 may include at least one of CU 1610, DU 1630, or RU 1640. For example, depending on the layer functionality processed by component 199, network entity 1602 may include: CU 1610; both CU 1610 and DU 1630; each of CU 1610, DU 1630, and RU 1640; DU 1630; both DU 1630 and RU 1640; or RU 1640. CU 1610 may include at least one CU processor 1612. CU processor 1612 may include on-chip memory 1612'. In some aspects, 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 at least one DU processor 1632. DU processor 1632 may include on-chip memory 1632'. In some aspects, DU 1630 may also include an additional memory module 1634 and a communication interface 1638. DU 1630 communicates with RU 1640 via a fronthaul link. RU 1640 may include at least one RU processor 1642. RU processor 1642 may include on-chip memory 1642'. In some aspects, RU 1640 may also include an additional memory module 1644, one or more transceivers 1646, an antenna 1680, and a communication interface 1648. RU 1640 communicates with UE 104. On-chip memories 1612', 1632', 1642' and additional memory modules 1614, 1634, 1644 may each be considered as computer-readable media / memory. Each computer-readable medium / memory can be non-transitory. Each of processors 1612, 1632, and 1642 is responsible for general processing, including executing software stored on the computer-readable medium / memory. When executed by the corresponding processor, the software causes that processor to perform the various functions described above. The computer-readable medium / memory can also be used to store data manipulated by the processor while executing the software.

[0171] As discussed above, component 199 can be configured to transmit a first set of RS to the UE via a first set of beams to initiate the UE to predict one or more predicted beams from the first set of beams; and to receive performance information from the UE indicating a difference between a first signal measurement and a second signal measurement based on a first beam measurement of the first set of beams, the first signal measurement being associated with the one or more predicted beams from the first set of beams, and the second signal measurement being associated with one or more beams in the first set of beams. Component 199 can be further configured to perform a combination. Figure 13 and Figure 14 The flowchart described and / or by Figure 10 The base station 1004 performs any aspect of the process / algorithm. Component 199 may be located within one or more processors of one or more of CU1610, DU 1630, and RU 1640. Component 199 may be one or more hardware components specifically configured to execute the stated process / algorithm, implemented by one or more processors configured to execute the stated process / algorithm, stored in a computer-readable medium for implementation by one or more processors, or some combination thereof. When multiple processors are implemented, the multiple processors may execute the stated process / algorithm individually or in combination. Network entity 1602 may include a variety of components configured for various functions. In one configuration, network entity 1602 includes: means for transmitting a first set of RS to a UE via a first set of beams to initiate the UE to predict one or more predicted beams from the first set of beams; and means for receiving performance information from the UE, the performance information indicating a difference between a first signal measurement and a second signal measurement based on a first beam measurement of the first set of beams, the first signal measurement being associated with the one or more predicted beams from the first set of beams, and the second signal measurement being associated with one or more beams in the first set of beams. Network entity 1602 may also include means for performing a combination. Figure 13 and Figure 14 The flowchart describes the aspects and / or are composed of Figure 10 The components of the base station 1004 can be any of the components in various aspects of the operation. A component can be a component 199 of network entity 1602 configured to perform the functions described therein. As described above, network entity 1602 may include a TX processor 316, an RX processor 370, and a controller / processor 375. Therefore, in one configuration, these components can be the TX processor 316, the RX processor 370, and / or the controller / processor 375 configured to perform the functions described therein.

[0172] This disclosure provides a method for wireless communication at a UE. The method may include: predicting one or more predicted beams from a first set of beams; performing first beam measurements for each of the first set of beams including the one or more predicted beams; and sending performance information to a network node, the performance information indicating a difference between a first signal measurement and a second signal measurement based on the first beam measurement, the first signal measurement being associated with the one or more predicted beams, and the second signal measurement being associated with one or more beams in the first set of beams. This method improves the reliability and verifiability of beam selection predictions made by AI / ML models. By calculating the difference between the predicted optimal beam and the actual optimal beam (such as L1-RSRP), these methods provide a concrete metric for measuring prediction accuracy. Therefore, these methods improve the accuracy of beam prediction, thereby improving the efficiency and reliability of wireless communication.

[0173] It should be understood that the specific order or hierarchy of the boxes in the disclosed process / flowcharts is merely an example of the exemplary method. It should be understood that the specific order or hierarchy of the boxes in the process / flowcharts may be rearranged based on design preferences. Furthermore, some boxes may be combined or omitted. The appended method claims present the elements of various boxes in a sample order, but are not limited to the given specific order or hierarchy.

[0174] 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 aspects described herein but should be given the full scope consistent with the language of the claims. Unless specifically stated otherwise, references to elements in the singular form do not mean “one and only one” but rather “one or more.” Terms such as “if,” “when,” and “simultaneously” do not imply a direct temporal relationship or reaction. That is, these phrases, such as “when…”, do not imply an immediate action in response to the occurrence of an action or during the occurrence of an action, but simply suggest that if a condition is met, then the action will occur, without requiring a specific or immediate time limit for the occurrence of the action. The word “exemplary” is used herein to mean “serving as an example, instance, or illustration.” Any aspect described herein as “exemplary” is not necessarily to be construed as preferred or superior to other aspects. Unless specifically stated otherwise, 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, and 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" can 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 collection of elements with a number of one or more elements. Therefore, for a set of X, X will include one or more elements. When at least one processor is configured to execute a set of functions, the at least one processor is configured to execute the set of functions individually or in any combination. Therefore, each of the at least one processor can be configured to perform a specific subset of the set of functions, wherein the subset is the complete set, a suitable subset of the set, or an empty subset of the set. If the first device receives data from or sends data to the second device, data can be received / sent directly between the first and second devices, or indirectly between the first and second devices via a set of devices. A device configured to “output” data (such as transmission, signaling, or a message) can, for example, transmit the data using a transceiver, or can transmit the data to the device that sent the data. A device configured to “receive” data (such as transmission, signaling, or a message) can, for example, receive the data using a transceiver, or can obtain the data from the device that received the data.Information stored in memory includes instructions and / or data. All structural and functional equivalents of the elements throughout the various aspects described herein that are known to or will later be known to a person skilled in the art are expressly incorporated herein by reference and are covered by the claims. Furthermore, nothing disclosed herein is intended to be offered to the public, whether or not such disclosure is expressly recited in the claims. The terms “module,” “mechanism,” “element,” “device,” etc., cannot replace the word “component.” Therefore, no claim element will be construed as a functional component unless the element is expressly recited using the phrase “component for…”.

[0175] As used in this article, 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, conditions, factors, etc.) should be interpreted as “based on at least A”, unless specifically stated differently.

[0176] The following aspects are merely illustrative and may be combined with other aspects or teachings described herein without limitation.

[0177] Aspect 1 is a method for performing wireless communication at a UE. The method may include: predicting one or more predicted beams from a first set of beams; performing a first beam measurement for each of the first set of beams including the one or more predicted beams; and sending performance information to a network node, the performance information indicating a difference between a first signal measurement and a second signal measurement based on the first beam measurement, the first signal measurement being associated with the one or more predicted beams, and the second signal measurement being associated with one or more beams in the first set of beams.

[0178] Aspect 2 is the method according to aspect 1, wherein the first signal measurement is a first maximum L1-RSRP on the one or more predicted beams, and the second signal measurement is a second maximum L1-RSRP on the one or more beams in the first set of beams.

[0179] Aspect 3 is the method according to any one of Aspects 1 to 2, wherein the method may further include: performing preliminary beam measurements on a preliminary set of beams before predicting the one or more predicted beams. The first set of beams may be based on the preliminary beam measurements.

[0180] Aspect 4 is the method according to aspect 3, wherein predicting the one or more predicted beams from the first set of beams may include: predicting the one or more predicted beams from the first set of beams based on an artificial intelligence / machine learning (AI / ML) model and the preliminary beam measurement.

[0181] Aspect 5 is a method according to any one of aspects 1 to 4, wherein the method may further include: requesting a set of reference signals (RS); and receiving the first set of RS via the first set of beams. Performing the first beam measurement for the first set of beams may include: performing the first beam measurement for the first set of beams based on the first set of RS.

[0182] Aspect 6 is a method according to any one of Aspects 1 to 4, wherein the one or more predicted beams include a predicted beam, and wherein the performance information indicates the difference between the first maximum L1-RSRP on the one predicted beam and the second maximum L1-RSRP on the one or more beams in the first set of beams.

[0183] Aspect 7 is a method according to any one of aspects 1 to 4, wherein the one or more predicted beams may include a plurality of predicted beams, and the performance information may indicate the difference between the first maximum L1-RSRP on the plurality of predicted beams and the second maximum L1-RSRP on the one or more beams in the first set of beams.

[0184] Aspect 8 is a method according to any one of aspects 1 to 4, wherein sending the performance information indicating the difference may include: sending the performance information indicating the difference to the network node in response to a triggering condition being met.

[0185] Aspect 9 is the method according to aspect 8, wherein the triggering condition may be that the difference is greater than the deviation threshold.

[0186] Aspect 10 is the method according to aspect 9, wherein the method may further include: receiving a threshold configuration indicating the deviation threshold from the network node.

[0187] Aspect 11 is the method according to aspect 8, wherein the triggering condition may be that the difference is greater than the deviation threshold for the first time within a first duration, and the first number may be greater than the counter threshold.

[0188] Aspect 12 is the method according to aspect 11, wherein the information may further include statistical data related to the differences within the first duration.

[0189] Aspect 13 is the method according to aspect 8, wherein the method may further include: performing an LCM operation on the AI / ML model in response to the satisfaction of the triggering condition.

[0190] Aspect 14 is the method according to aspect 13, wherein the AI / ML model may be a first AI / ML model, and the LCM operation may include one or more of the following: activating the first AI / ML model, deactivating the first AI / ML model, switching to a second AI / ML model different from the first AI / ML model, or performing a rollback operation on the first AI / ML model.

[0191] Aspect 15 is the method according to any one of aspects 1 to 4, wherein sending the performance information indicating the difference may include: sending the performance information indicating the difference in a periodic mode or a semi-persistent mode.

[0192] Aspect 16 is the method according to aspect 15, wherein the method may further include: receiving from the network node a report configuration indicating one or more of the periodic mode or the semi-persistent mode.

[0193] Aspect 17 is an apparatus for wireless communication at a UE, the apparatus comprising: at least one memory; and at least one processor coupled to the at least one memory and based at least in part on information stored in the at least one memory, the at least one processor being configured individually or in any combination to cause the UE to perform a method according to any one of aspects 1 to 16.

[0194] Aspect 18 is an apparatus for wireless communication at a UE, the apparatus comprising components for performing each step of the method according to any one of aspects 1 to 16.

[0195] Aspect 19 is an apparatus according to any one of aspects 17 to 18, the apparatus further comprising a transceiver configured to receive or transmit in association with the method according to any one of aspects 1 to 16.

[0196] Aspect 20 is a computer-readable medium (e.g., a non-transitory computer-readable medium) storing computer-executable code at a UE, said code, when executed by at least one processor, causes said at least one processor, alone or in any combination, to cause the UE to perform the method according to any one of aspects 1 to 16.

[0197] Aspect 21 is a method for wireless communication at a network entity. The method may include: transmitting a first set of RS to a UE via a first set of beams to initiate the UE to predict one or more predicted beams from the first set of beams; and receiving performance information from the UE, the performance information indicating a difference between a first signal measurement and a second signal measurement based on a first beam measurement of the first set of beams, the first signal measurement being associated with the one or more predicted beams from the first set of beams, and the second signal measurement being associated with one or more beams in the first set of beams.

[0198] Aspect 22 is the method according to aspect 21, wherein the first signal measurement is a first maximum L1-RSRP on the one or more predicted beams, and the second signal measurement is a second maximum L1-RSRP on the one or more beams in the first set of beams.

[0199] Aspect 23 is a method according to any one of aspects 21 to 22, wherein the method may further include: transmitting a preliminary set of RSs to the UE via a preliminary set of beams before transmitting the first set of RSs via the first set of beams to initiate preliminary beam measurements performed by the UE on the preliminary set of beams. The first set of beams may be based on the preliminary beam measurements.

[0200] Aspect 24 is a method according to any one of aspects 21 to 23, wherein the method may further include: receiving a request from the UE to request a set of RSs, and transmitting the first set of RSs via a first set of beams may include: transmitting the first set of RSs via a first set of beams in response to the request.

[0201] Aspect 25 is a method according to any one of aspects 21 to 22, wherein the one or more predicted beams may include a predicted beam, and the performance information may indicate the difference between the first maximum L1-RSRP on the one predicted beam and the second maximum L1-RSRP on the one or more beams in the first set of beams.

[0202] Aspect 26 is a method according to any one of aspects 21 to 22, wherein the one or more predicted beams may include a plurality of predicted beams, and the performance information may indicate the difference between the first maximum L1-RSRP on the plurality of predicted beams and the second maximum L1-RSRP on the one or more beams in the first set of beams.

[0203] Aspect 27 is a method according to any one of aspects 21 to 22, wherein receiving the performance information indicating the difference may include: receiving the performance information indicating the difference in response to a trigger condition being met.

[0204] Aspect 28 is the method according to aspect 27, wherein the triggering condition may be that the difference is greater than a deviation threshold.

[0205] Aspect 29 is the method according to aspect 28, wherein the method may further include: sending a threshold configuration indicating the deviation threshold to the UE.

[0206] Aspect 30 is the method according to any one of Aspects 27 to 29, wherein the triggering condition may be that the difference is greater than a deviation threshold for a first number of times within a first duration, and the first number of times may be greater than a counter threshold.

[0207] Aspect 31 is the method according to aspect 30, wherein the information may further include statistical data related to the differences within the first duration.

[0208] Aspect 32 is the method according to any one of aspects 21 to 22, wherein receiving the performance information indicating the difference may include: receiving the performance information indicating the difference in a periodic mode or a semi-persistent mode.

[0209] Aspect 33 is the method according to aspect 32, wherein the method may further include: sending a report configuration to the UE indicating one or more of the periodic mode or the semi-persistent mode.

[0210] Aspect 34 is an apparatus for wireless communication at a network entity, the apparatus comprising: at least one memory; and at least one processor coupled to the at least one memory and based at least in part on information stored in the at least one memory, the at least one processor being configured individually or in any combination to cause the network entity to perform a method according to any one of aspects 21 to 33.

[0211] Aspect 35 is an apparatus for wireless communication at a network entity, the apparatus comprising components for performing each step of the method according to any one of aspects 21 to 33.

[0212] Aspect 36 is an apparatus according to any one of aspects 34 to 35, the apparatus further comprising a transceiver configured to receive or transmit in association with the method according to any one of aspects 21 to 33.

[0213] Aspect 37 is a computer-readable medium (e.g., a non-transitory computer-readable medium) storing computer-executable code at a network entity, said code, when executed by at least one processor, causing said at least one processor, alone or in any combination, to cause the network entity to perform the method according to any one of aspects 21 to 33.

Claims

1. An apparatus for wireless communication at a user equipment (UE), the apparatus comprising: At least one memory; and At least one processor, coupled to at least one memory, and configured individually or in any combination, based at least in part on information stored in the at least one memory, to cause the UE to: Predict one or more prediction beams from the first group of beams; Perform a first beam measurement on the first group of beams, including the one or more predicted beams; and The network node sends performance information indicating the difference between a first signal measurement and a second signal measurement based on the first beam measurement, the first signal measurement being associated with one or more predicted beams, and the second signal measurement being associated with one or more beams in the first set of beams.

2. The apparatus of claim 1, further comprising a transceiver coupled to the at least one processor, wherein, In order to transmit the performance information indicating the difference, the at least one processor is configured individually or in any combination to cause the UE to transmit the performance information indicating the difference via the transceiver, and the first signal measurement is a first maximum Layer 1 (L1) reference signal received power (RSRP) on the one or more predicted beams, and the second signal measurement is a second maximum L1-RSRP on the one or more beams in the first set of beams.

3. The apparatus of claim 2, wherein the at least one processor is further configured, individually or in any combination, to cause the UE to: Before predicting the one or more predicted beams, preliminary beam measurements are performed on a preliminary set of beams, wherein the first set of beams is based on the preliminary beam measurements.

4. The apparatus according to claim 3, wherein, In order to predict the one or more predicted beams from the first set of beams, the at least one processor is configured individually or in any combination to cause the UE to: The one or more predicted beams are predicted from the first set of beams based on an artificial intelligence / machine learning (AI / ML) model and the preliminary beam measurements.

5. The apparatus of claim 4, wherein the at least one processor is further configured, individually or in any combination, to cause the UE to: Request a set of reference signals (RS); and The first group of RS is received via the first group of beams, and wherein, In order to perform the first beam measurement for the first group of beams respectively, the at least one processor is configured individually or in any combination to: The first beam measurement is performed on the first group of beams based on the first group of RS.

6. The apparatus of claim 4, wherein the one or more predicted beams comprise a predicted beam, and wherein the performance information indicates the difference between the first maximum L1-RSRP on the one predicted beam and the second maximum L1-RSRP on the one or more beams in the first set of beams.

7. The apparatus of claim 4, wherein the one or more predicted beams comprise a plurality of predicted beams, and wherein the performance information indicates the difference between the first maximum L1-RSRP on the plurality of predicted beams and the second maximum L1-RSRP on the one or more beams in the first set of beams.

8. The apparatus according to claim 4, wherein, In order to send the performance information indicating the difference, the at least one processor is configured individually or in any combination to cause the UE to: In response to the fulfillment of a triggering condition, the performance information indicating the difference is sent to the network node.

9. The apparatus of claim 8, wherein the triggering condition is that the difference is greater than a deviation threshold.

10. The apparatus of claim 9, wherein the at least one processor is further configured, individually or in any combination, to cause the UE to: Receive a threshold configuration indicating the deviation threshold from the network node.

11. The apparatus of claim 8, wherein the triggering condition is that the difference is greater than a deviation threshold for a first number within a first duration, wherein the first number is greater than a counter threshold.

12. The apparatus of claim 11, wherein the performance information further includes statistical data relating to the differences over the first duration.

13. The apparatus of claim 8, wherein the at least one processor is further configured, individually or in any combination, to cause the UE to: In response to the fulfillment of the triggering condition, perform lifecycle management (LCM) operations on the AI / ML model.

14. The apparatus of claim 13, wherein the AI / ML model is a first AI / ML model, and the LCM operation comprises one or more of the following: Activate the first AI / ML model, Deactivate the first AI / ML model. Switch to a second AI / ML model that is different from the first AI / ML model, or Perform a rollback operation on the first AI / ML model.

15. The apparatus according to claim 4, wherein, In order to send the performance information indicating the difference, the at least one processor, individually or in any combination, is further configured to cause the UE to: The performance information indicating the differences is sent in either a periodic or semi-persistent mode.

16. The apparatus of claim 15, wherein the at least one processor is further configured, individually or in any combination, to cause the UE to: Receive a report configuration from the network node indicating one or more of the periodic mode or the semi-persistent mode.

17. An apparatus for wireless communication at a network node, the apparatus comprising: At least one memory; and At least one processor, coupled to at least one memory, and configured individually or in any combination, based at least in part on information stored in the at least one memory, to enable the network node to: A first set of reference signals (RS) is sent to the user equipment (UE) via a first set of beams to initiate the UE to predict one or more prediction beams from the first set of beams; as well as The UE receives performance information indicating a difference between a first signal measurement and a second signal measurement based on a first beam measurement of the first group of beams, the first signal measurement being associated with one or more predicted beams from the first group of beams, and the second signal measurement being associated with one or more beams in the first group of beams.

18. The apparatus of claim 17, further comprising a transceiver coupled to the at least one processor, wherein, In order to receive the performance information indicating the difference, the at least one processor is configured individually or in any combination to cause the network node to receive the performance information indicating the difference via the transceiver, and the first signal measurement is a first maximum Layer 1 (L1) reference signal received power (RSRP) on the one or more predicted beams, and the second signal measurement is a second maximum L1-RSRP on the one or more beams in the first set of beams.

19. The apparatus of claim 18, wherein the at least one processor is further configured, individually or in any combination, to cause the network node to: Before transmitting the first set of RS via the first set of beams, a preliminary set of RS is transmitted to the UE via a preliminary set of beams to initiate the UE to perform preliminary beam measurements on the preliminary set of beams, wherein the first set of beams is based on the preliminary beam measurements.

20. The apparatus of claim 19, wherein the at least one processor is further configured, individually or in any combination, to cause the network node to: The UE receives a request for a set of RSs, and wherein, In order to transmit the first group of RSs via the first group of beams, the at least one processor is configured individually or in any combination to: In response to the request, the first set of RS is transmitted via the first set of beams.

21. The apparatus of claim 18, wherein the one or more predicted beams comprise a predicted beam, and wherein the performance information indicates the difference between the first maximum L1-RSRP on the one predicted beam and the second maximum L1-RSRP on the one or more beams in the first set of beams.

22. The apparatus of claim 18, wherein the one or more predicted beams comprise a plurality of predicted beams, and wherein the performance information indicates the difference between the first maximum L1-RSRP on the plurality of predicted beams and the second maximum L1-RSRP on the one or more beams in the first set of beams.

23. The apparatus according to claim 18, wherein, In order to receive the performance information indicating the difference, the at least one processor is configured individually or in any combination to cause the network node to: The performance information indicating the difference is received in response to the fulfillment of the triggering condition.

24. The apparatus of claim 23, wherein the triggering condition is that the difference is greater than a deviation threshold.

25. The apparatus of claim 24, wherein the at least one processor is further configured, individually or in any combination, to cause the network node to: Send a threshold configuration indicating the deviation threshold to the UE.

26. The apparatus of claim 23, wherein the triggering condition is that the difference is greater than a deviation threshold for a first time within a first duration, wherein the first time is greater than a counter threshold.

27. The apparatus of claim 26, wherein the performance information further includes statistical data relating to the differences over the first duration.

28. The apparatus according to claim 18, wherein, In order to receive the performance information indicating the difference, the at least one processor is configured individually or in any combination to cause the network node to: Receive the performance information indicating the difference in either a periodic or semi-persistent mode.

29. The apparatus of claim 28, wherein the at least one processor is further configured, individually or in any combination, to cause the network node to: Send a report configuration to the UE indicating one or more of the periodic mode or the semi-persistent mode.

30. A method for conducting wireless communication at a user equipment (UE), the method comprising: Predict one or more prediction beams from the first group of beams; Perform a first beam measurement for the first group of beams, which includes one or more of the predicted beams; as well as The network node sends performance information indicating the difference between a first signal measurement and a second signal measurement based on the first beam measurement, the first signal measurement being associated with one or more predicted beams, and the second signal measurement being associated with one or more beams in the first set of beams.

31. A method for wireless communication at a network node, the method comprising: A first set of reference signals (RS) is sent to the user equipment (UE) via a first set of beams to initiate the UE to predict one or more prediction beams from the first set of beams; as well as The UE receives performance information indicating a difference between a first signal measurement and a second signal measurement based on a first beam measurement of the first group of beams, the first signal measurement being associated with one or more predicted beams from the first group of beams, and the second signal measurement being associated with one or more beams in the first group of beams.

Images