MMW beam measurement based on machine learning

Abstract

The UE may measure a metric for a first subset of PO beams of at least one subset of PO beams comprising a plurality of PO beams from a network node, each subset of PO beams being configured to form a PO pattern, and the first subset of PO beams being associated with a first set of narrower RX beams of the UE; estimating metrics for the first set of narrower Rx beams using an ML model based on the metrics for the subset of PO beams; and identifying at least one optimal Rx beam from the first set of narrower Rx beams, the at least one optimal Rx beam associated with an optimal estimation metric in the first set of narrower Rx beams.

Description

Technical Field

[0001] The present disclosure relates generally to communication systems, and more particularly to wireless communications including machine learning (ML) based beam measurement. Background Art

[0002] Wireless communication systems are widely deployed to provide a variety of telecommunication services, such as telephony, video, data, messaging, and broadcast. Typical wireless communication systems may employ multiple access technologies capable of supporting communication with multiple users by sharing available system resources. Examples of such multiple access technologies include code division multiple access (CDMA) systems, time division multiple access (TDMA) systems, frequency division multiple access (FDMA) systems, orthogonal frequency division multiple access (OFDMA) systems, single carrier frequency division multiple access (SC-FDMA) systems, and time division synchronous code division multiple access (TD-SCDMA) systems.

[0003] These multiple access technologies have been adopted in various telecommunication standards to provide a common protocol that enables different wireless devices to communicate at a city, country, region, and even global level. An example telecommunication standard is 5G New Radio (NR). 5G NR is part of the continuous mobile broadband evolution promulgated by the Third Generation Partnership Project (3GPP) to meet new requirements associated with latency, reliability, security, scalability (e.g., with the Internet of Things (IoT)) and other requirements. 5GNR includes services associated with enhanced mobile broadband (eMBB), massive machine type communication (mMTC), and ultra-reliable low latency communication (URLLC). Certain aspects of 5G NR may be based on 4G Long Term Evolution (LTE) standards. It is necessary to further improve 5G NR technology. In addition, these improvements may also be applicable to other multiple access technologies and telecommunication standards that employ these technologies. Summary of the invention

[0004] A simplified summary of one or more aspects is presented below to provide a basic understanding of these aspects. This summary is not an extensive review of all contemplated aspects. This summary neither identifies the key or important elements of all aspects, nor describes the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to a more detailed description presented later.

[0005] In one aspect of the present disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus may include a UE, the UE being configured to: measure a metric of a first PO beam subset of at least one PO beam subset including a plurality of PO beams from a network node, each PO beam subset being configured to form a PO pattern, and the first PO beam subset being associated with a first narrower Rx beam set of the UE; estimate a metric of the first narrower Rx beam set using an ML model based on the metric of the PO beam subset; and identify at least one best Rx beam from the first narrower Rx beam set, the at least one best Rx beam being associated with a best estimated metric in the first narrower Rx beam set.

[0006] In one aspect of the present disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus may include a network entity configured to: obtain at least one coefficient of an ML model for estimating an RX beam set based on a metric of a PO beam subset; and send the at least one coefficient associated with the ML model for a UE to use the ML model to estimate the metric of the Rx beam set based on the at least one coefficient and the metric of the PO beam subset.

[0007] To achieve the aforementioned and related purposes, one or more aspects include the features fully described below and particularly pointed out in the claims. The following description and the accompanying drawings set forth in detail some exemplary features of one or more aspects. However, these features indicate only some of the various ways in which the principles of the various aspects can be employed. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0009] Figure 2A is a diagram illustrating an example of a first frame according to various aspects of the present disclosure.

[0010] Figure 2B is a diagram illustrating an example of downlink (DL) channels within a subframe according to various aspects of the present disclosure.

[0011] Figure 2C is a diagram illustrating an example of a second frame according to various aspects of the present disclosure.

[0012] Figure 2D is a diagram illustrating an example of uplink (UL) channels within a subframe according to various aspects of the present disclosure.

[0013] Figure 3 is a diagram illustrating an example of a base station and a user equipment (UE) in an access network.

[0014] Figure 4is an example of an AI / ML algorithm for wireless communication methods.

[0015] Figure 5 Examples of an L1-level beam, an L2-level beam, and an L3-level beam are illustrated.

[0016] Figure 6 A UE comprising one or more antenna arrays for receiving at least one minimum viable PO beam (MVP) set is illustrated.

[0017] Figure 7 is a diagram of the L3 beam selection timeline.

[0018] Fig. 8A and Figure 8B is a diagram of L1 beam selection.

[0019] Fig.9A , Fig. 9B and Fig. 9C is a diagram of L3 beam estimation.

[0020] Fig.10 is a diagram of scheduling L3 beam estimation.

[0021] Fig.11 is a call flow diagram of a wireless communication method.

[0022] Fig.12 is a flow chart of a wireless communication method.

[0023] Fig.13 is a flow chart of a wireless communication method.

[0024] Fig.14 is a flow chart of a wireless communication method.

[0025] Fig.15 is a flow chart of a wireless communication method.

[0026] Fig.16 are diagrams illustrating examples of hardware implementations for example apparatuses and / or network entities.

[0027] Fig.17 is a diagram illustrating an example of a hardware implementation for an example network entity. DETAILED DESCRIPTION

[0028] Beamforming is a feature associated with 5G NR wireless communications. In order to refine a narrower Rx beam for a UE, the UE may be configured to select a pseudo omnidirectional (PO) beam (e.g., an L1 beam), refine a network node transmit (Tx) beam narrower than the PO beam (e.g., an L2 beam), and then select a UE Rx beam narrower than the network node Tx beam (e.g., an L3 beam). Therefore, selecting a UE Rx beam may take a long time and result in increased power consumption on the UE side. According to aspects of the present disclosure, the UE may use a machine learning (ML) model to estimate or predict an L3 beam based on a set of metrics for a subset of PO beams.

[0029] The specific embodiments described below in conjunction with the accompanying drawings are descriptions of various configurations and do not represent the only configurations in which the concepts described herein can be practiced. In order to provide a thorough understanding of the various concepts, the specific embodiments include specific details. However, these concepts can be practiced without these specific details. In some cases, well-known structures and components are shown in block diagram form to avoid blurring such concepts.

[0030] Several aspects of telecommunication systems are presented with reference to various apparatuses and methods. These apparatuses and methods are described in the following detailed description and illustrated in the accompanying drawings by various blocks, components, circuits, processes, algorithms, etc. (collectively referred to as "elements"). These elements may be implemented using electronic hardware, computer software, or any combination thereof. Whether these elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system.

[0031] As an example, an element, or any part of an element, or any combination of elements can be implemented as a "processing system", which includes one or more processors. Examples of processors include microprocessors, microcontrollers, graphics processing units (GPUs), central processing units (CPUs), application processors, digital signal processors (DSPs), reduced instruction set computing (RISC) processors, systems on chip (SoCs), baseband processors, field programmable gate arrays (FPGAs), programmable logic devices (PLDs), state machines, gated logic components, discrete hardware circuits, and other suitable hardware configured to perform various functionalities described throughout the present disclosure. One or more processors in a processing system can execute software. Whether referred to as software, firmware, middleware, microcode, hardware description language, or other terms, software should be broadly interpreted as meaning instructions, instruction sets, codes, code segments, program codes, programs, subroutines, software components, applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, functions, or any combination thereof.

[0032] Thus, in one or more example aspects, specific implementations and / or use cases, the described functionality may be implemented in hardware, software, or any combination thereof. If implemented in software, the functionality may be stored or encoded as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media. Storage media may be any available media that can be accessed by a computer. As an example, such computer-readable media may include random access memory (RAM), read-only memory (ROM), electrically erasable programmable ROM (EEPROM), optical disk storage, magnetic disk storage, other magnetic storage devices, combinations of these types of computer-readable media, or any other medium that can be used to store computer-executable code in the form of instructions or data structures that can be accessed by a computer.

[0033] Although various aspects, specific implementations and / or use cases are described in this application by the illustration of some examples, additional or different aspects, specific implementations and use cases may be generated in many different arrangements and scenarios. The various aspects, specific implementations and / or use cases described herein can be implemented across many different platform types, devices, systems, shapes, sizes and packaging arrangements. For example, various aspects, specific implementations and / or use cases can be generated via integrated chip specific implementations and other devices based on non-module components (e.g., end-user devices, vehicles, communication equipment, computing equipment, industrial equipment, retail / purchase equipment, medical equipment, artificial intelligence (AI) enabled devices, etc.). Although some examples may or may not be specifically for use cases or applications, the described examples may have a wide range of applicability. Various aspects, specific implementations and / or use cases can be in the range from chip-level or modular components to non-modular, non-chip-level specific implementations, and further to the range of aggregated, distributed or original equipment manufacturer (OEM) devices or systems in conjunction with one or more technologies herein. In some actual settings, the equipment combined with the various aspects and features described may also include additional components and features for implementing and practicing the claimed and described aspects. For example, the transmission and reception of wireless signals necessarily include multiple components for analog and digital purposes (e.g., hardware components including antennas, RF chains, power amplifiers, modulators, buffers, processors, interleavers, adders / summers, etc.) The techniques described herein can be practiced in a wide variety of devices of various sizes, shapes, and configurations, chip-level components, systems, distributed arrangements, aggregated or disaggregated components, end-user devices, etc.

[0034] The deployment of a communication system (such as a 5G NR system) can be arranged with various components or constituent parts in a variety of ways. In a 5G NR system or network, a network node, a network entity, a mobility element of a network, a radio access network (RAN) node, a core network node, a network element or a network equipment (such as a base station (BS), or one or more units (or one or more components) that perform base station functionality can be implemented in an aggregated or decomposed architecture. For example, a BS (such as a Node B (NB), an evolved NB (eNB), an NR BS, a 5G NB, an access point (AP), a transmit receive point (TRP) or a cell, etc.) can be implemented as an aggregated base station (also referred to as an independent BS or a monolithic BS) or a decomposed base station.

[0035] A converged base station may be configured to utilize a radio protocol stack physically or logically integrated within a single RAN node. A decomposed base station may be configured to utilize a protocol stack physically or logically distributed between two or more units, such as one or more central or centralized units (CUs), one or more distributed units (DUs), or one or more radio units (RUs). In some aspects, a CU may be implemented within a RAN node, and one or more DUs may be co-located with the CU, or alternatively, may be geographically or virtually distributed in one or more other RAN nodes. A DU may be implemented to communicate with one or more RUs. Each of a CU, a DU, and a RU may be implemented as a virtual unit, i.e., a virtual central unit (VCU), a virtual distributed unit (VDU), or a virtual radio unit (VRU).

[0036] Base station operation or network design may take into account the aggregated nature of base station functionality. For example, a disaggregated base station may be used in an integrated access backhaul (IAB) network, an open radio access network (O-RAN (network configuration such as that initiated by the O-RAN Alliance)), or a virtualized radio access network (vRAN, also known as a cloud radio access network (C-RAN)). Decomposition may include distributing functionality across two or more units at various physical locations, as well as virtually distributing functionality of at least one unit, which may enable flexibility in network design. Individual units of a disaggregated base station or disaggregated RAN architecture may be configured for wired or wireless communication with at least one other unit.

[0037] Figure 11 is a diagram 100 illustrating an example of a wireless communication system and an access network. The illustrated wireless communication system includes a disaggregated base station architecture. The disaggregated base station architecture may include one or more CUs 110 that may communicate directly with a core network 120 via a backhaul link, or indirectly with the core network 120 through one or more disaggregated base station units, such as a near real-time (near RT) RAN intelligent controller (RIC) 125 via an E2 link, or a non-real-time (non-RT) RIC 115 associated with a service management and orchestration (SMO) framework 105, or both. The CU 110 may communicate with one or more DUs 130 via corresponding midhaul links, such as an F1 interface. The DU 130 may communicate with one or more RUs 140 via corresponding fronthaul links. The RU 140 may communicate with corresponding UEs 104 via one or more radio frequency (RF) access links. In some implementations, a UE 104 may be served simultaneously by multiple RUs 140.

[0038] Each of these units (i.e., CU 110, DU 130, RU 140, and near-RT RIC 125, non-RT RIC 115, and SMO framework 105) may include or be coupled to one or more interfaces configured to receive or transmit signals, data, or information (collectively, signals) via a wired or wireless transmission medium. Each of these units or an associated processor or controller that provides instructions to the communication interface of these units may be configured to communicate with one or more of the other units via a transmission medium. For example, these units may include a wired interface configured to receive signals or transmit signals to one or more of the other units via a wired transmission medium. Additionally, these units may include a wireless interface that may include a receiver, transmitter, or transceiver (such as an RF transceiver) configured to receive and / or transmit signals to one or more of the other units via a wireless transmission medium.

[0039] In some aspects, CU 110 may host one or more higher layer control functions. Such control functions may include radio resource control (RRC), packet data convergence protocol (PDCP), service data adaptation protocol (SDAP), etc. Each control function may be implemented using an interface that is configured to communicate signals with other control functions hosted by CU 110. CU 110 may be configured to handle user plane functionality (i.e., central unit-user plane (CU-UP)), control plane functionality (i.e., central unit-control plane (CU-CP)), or a combination thereof. In some specific implementations, CU 110 may be logically split into one or more CU-UP units and one or more CU-CP units. When implemented in an O-RAN configuration, the CU-UP unit may communicate bidirectionally with the CU-CP unit via an interface (such as an E1 interface). As needed, CU 110 may be implemented to communicate with DU 130 for network control and signaling.

[0040] DU 130 may correspond to a logical unit that includes one or more base station functions for controlling the operation of one or more RUs 140. In some aspects, DU 130 may host one or more of a radio link control (RLC) layer, a medium access control (MAC) layer, and one or more high physical (PHY) layers (such as modules for forward error correction (FEC) encoding and decoding, scrambling, modulation and demodulation, etc.) at least in part according to a functional split such as those defined by 3GPP. In some aspects, DU 130 may also host one or more low PHY layers. Each layer (or module) may be implemented using an interface that is configured to communicate signals with other layers (and modules) hosted by DU 130 or with control functions hosted by CU 110.

[0041] The lower layer functionality may be implemented by one or more RUs 140. In some deployments, the RU 140 controlled by the DU 130 may correspond to a logical node that hosts RF processing functions, or low PHY layer functions (such as performing Fast Fourier Transform (FFT), Inverse FFT (iFFT), digital beamforming, physical random access channel (PRACH) extraction and filtering, etc.), or both, based at least in part on functional splitting (such as lower layer functional splitting). In such an architecture, the RU 140 may be implemented to handle over-the-air (OTA) communications with one or more UEs 104. In some specific implementations, real-time and non-real-time aspects of control plane and user plane communications with the RU 140 may be controlled by the corresponding DU 130. In some scenarios, this configuration may enable the implementation of the DU 130 and the CU 110 in a cloud-based RAN architecture (such as a vRAN architecture).

[0042] The SMO framework 105 may be configured to support RAN deployment and provisioning of non-virtualized network elements and virtualized network elements. For non-virtualized network elements, the SMO framework 105 may be configured to support the deployment of dedicated physical resources for RAN coverage requirements, which may be managed via an operation and maintenance interface (such as an O1 interface). For virtualized network elements, the SMO framework 105 may be configured to interact with a cloud computing platform (such as an open cloud (O-Cloud) 190) to perform network element lifecycle management (such as to instantiate virtualized network elements) via a cloud computing platform interface (such as an O2 interface). Such virtualized network elements may include, but are not limited to, CU 110, DU 130, RU 140, and near-RT RIC 125. In some specific implementations, the SMO framework 105 may communicate with hardware aspects of the 4G RAN (such as an open eNB (O-eNB) 111) via the O1 interface. Additionally, in some specific implementations, the SMO framework 105 may communicate directly with one or more RUs 140 via the O1 interface. The SMO framework 105 may also include a non-RT RIC 115 configured to support the functionality of the SMO framework 105 .

[0043] The non-RT RIC 115 may be configured to include logic functions that enable non-real-time control and optimization of RAN elements and resources, artificial intelligence (AI) / machine learning (ML) (AI / ML) workflows including model training and updating, or policy-based guidance of applications / features in the near-RT RIC 125. The non-RT RIC 115 may be coupled to or in communication with the near-RT RIC 125 (such as via an A1 interface). The near-RT RIC 125 may be configured to include logic functions that enable near-real-time control and optimization of RAN elements and resources via data collection and actions through an interface (such as via an E2 interface) that connects one or more CUs 110, one or more DUs 130, or both, and the O-eNB with the near-RT RIC 125.

[0044] In some implementations, in order to generate an AI / ML model to be deployed in the near-RT RIC 125, the non-RT RIC 115 may receive parameters or external enrichment information from an external server. Such information may be utilized by the near-RT RIC 125 and may be received from a non-network data source or from a network function at the SMO framework 105 or the non-RT RIC 115. In some examples, the non-RT RIC 115 or the near-RT RIC 125 may be configured to tune RAN behavior or performance. For example, the non-RT RIC 115 may monitor long-term trends and patterns of performance and employ AI / ML models to perform corrective actions through the SMO framework 105 (such as via reconfiguration of O1) or via the creation of RAN management policies (such as A1 policies).

[0045] At least one of the CU 110, the DU 130, and the RU 140 may be referred to as a base station 102. Therefore, the base station 102 may include one or more of the CU 110, the DU 130, and the RU 140 (each component is indicated by a dotted line to indicate that each component may be included in the base station 102 or may not be included in the base station). The base station 102 provides an access point to the core network 120 for the UE 104. The base station 102 may include a macro cell (a high-power cellular base station) and / or a small cell (a low-power cellular base station). Small cells include femto cells, pico cells, and micro cells. A network including both small cells and macro cells may be referred to as a heterogeneous network. A heterogeneous network may also include a home evolved Node B (eNB) (HeNB), which may provide services to a restricted group referred to as a closed subscriber group (CSG). The communication link between RU 140 and UE 104 may include uplink (UL) (also known as reverse link) transmission from UE 104 to RU 140 and / or downlink (DL) (also known as forward link) transmission from RU 140 to UE 104. The communication link may use multiple-input multiple-output (MIMO) antenna technology, including spatial multiplexing, beamforming and / or transmit diversity. The communication link may be through one or more carriers. For each carrier allocated in a carrier aggregation of up to Yx MHz (x component carriers) for transmission in each direction, the base station 102 / UE 104 may use a spectrum of up to Y MHz (e.g., 5MHz, 10MHz, 15MHz, 20MHz, 100MHz, 400MHz, etc.) bandwidth. These carriers may or may not be adjacent to each other. The allocation of carriers may be equivalent to DL and UL asymmetric (e.g., more or fewer carriers may be allocated to DL than to UL). Component carriers may include a primary component carrier and one or more secondary component carriers. The primary component carrier may be referred to as a primary cell (PCell) and the secondary component carrier may be referred to as a secondary cell (SCell).

[0046] Some UEs 104 may communicate with each other using a device-to-device (D2D) communication link 158. The D2D communication link 158 may use DL / UL wireless wide area network (WWAN) spectrum. The D2D communication link 158 may use one or more sidelink channels, such as a physical sidelink broadcast channel (PSBCH), a physical sidelink discovery channel (PSDCH), a physical sidelink shared channel (PSSCH), and a physical sidelink control channel (PSCCH). The D2D communication may be through a variety of wireless D2D communication systems, such as, for example, Bluetooth, Wi-Fi based on the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standard, LTE, or NR.

[0047] The wireless communication system may also include a Wi-Fi AP 150 that communicates with a UE 104 (also referred to as a Wi-Fi station (STA)) via a communication link 154, for example, in a 5 GHz unlicensed spectrum, etc. When communicating in an unlicensed spectrum, the UE 104 / AP 150 may perform a clear channel assessment (CCA) to determine whether a channel is available prior to communication.

[0048] The wireless communication system may also include a dedicated server 152 for training an AI / ML model used by the UE to estimate the L3 beam. The dedicated server 152 may be configured to communicate directly with the UE 104 or communicate with the UE 104 via a network (e.g., the core network 120 or the BS 102).

[0049] The electromagnetic spectrum is typically subdivided into various categories, bands, channels, etc. based on frequency / wavelength. In 5G NR, two initial operating bands have been identified as frequency range designations FR1 (410 MHz-7.125 GHz) and FR2 (24.25 GHz-52.6 GHz). Although a portion of FR1 is greater than 6 GHz, FR1 is often (interchangeably) referred to as the "sub-6 GHz" band in various documents and articles. A similar naming issue sometimes occurs with respect to FR2, which is often (interchangeably) referred to as the "millimeter wave" band in documents and articles, although different from the extremely high frequency (EHF) band (30 GHz-300 GHz) identified as the "millimeter wave" band by the International Telecommunication Union (ITU).

[0050] Frequencies between FR1 and FR2 are generally referred to as mid-band frequencies. Recent 5G NR research has identified the operating bands for these mid-band frequencies as frequency range designation FR3 (7.125GHz-24.25GHz). The bands falling within FR3 can inherit FR1 characteristics and / or FR2 characteristics, so the features of FR1 and / or FR2 can be effectively extended to mid-band frequencies. In addition, higher frequency bands are currently being explored to extend 5G NR operations to more than 52.6GHz. For example, three higher operating bands have been identified as frequency range designations FR2-2 (52.6GHz-71GHz), FR4 (71GHz-114.25GHz) and FR5 (114.25GHz-300GHz). Each of these higher frequency bands falls within the EHF band.

[0051] In view of the above, unless otherwise specified, if the term "6 GHz or less" is used herein, it may broadly refer to frequencies that may be less than 6 GHz, may be within FR1, or may include mid-band frequencies. In addition, unless otherwise specified, if the term "millimeter wave" is used herein, it may broadly refer to frequencies that may include mid-band frequencies, may be within FR2, FR4, FR2-2, and / or FR5, or may be within the EHF band.

[0052] The base station 102 and the UE 104 may each include multiple antennas (such as antenna elements, antenna panels, and / or antenna arrays) to facilitate beamforming. The base station 102 may send a beamformed signal 182 to the UE 104 in one or more transmit directions. The UE 104 may receive the beamformed signal from the base station 102 in one or more receive directions. The UE 104 may also send a beamformed signal 184 to the base station 102 in one or more transmit directions. The base station 102 may receive the beamformed signal from the UE 104 in one or more receive directions. The base station 102 / UE 104 may perform beam training to determine the best receive direction and transmit direction for each of the base station 102 / UE 104. The transmit direction and receive direction of the base station 102 may be the same or different. The transmit direction and receive direction of the UE 104 may be the same or different.

[0053] The base station 102 may include and / or be referred to as a gNB, a Node B, an eNB, an access point, a base transceiver station, a radio base station, a radio transceiver, a transceiver function, a basic service set (BSS), an extended service set (ESS), a transmit receive point (TRP), a network node, a network entity, a network equipment, or some other suitable term. The base station 102 may be implemented as an integrated access and backhaul (IAB) node, a relay node, a sidelink node, an aggregated (monolithic) base station with a baseband unit (BBU) (including a CU and a DU) and a RU, or as a decomposed base station including one or more of a CU, a DU, and / or a RU. A set of base stations that may include decomposed base stations and / or aggregated base stations may be referred to as a next generation (NG) RAN (NG-RAN).

[0054] The core network 120 may include an access and mobility management function (AMF) 161, a session management function (SMF) 162, a user plane function (UPF) 163, a unified data management (UDM) 164, one or more location servers 168, and other functional entities. AMF 161 is a control node that handles signaling between UE 104 and core network 120. AMF 161 supports registration management, connection management, mobility management, and other functions. SMF 162 supports session management and other functions. UPF 163 supports packet routing, packet forwarding, and other functions. UDM 164 supports the generation of authentication and key agreement (AKA) credentials, user identity handling, access authorization, and subscription management. One or more location servers 168 are illustrated as including a gateway mobile location center (GMLC) 165 and a location management function (LMF) 166. However, in general, the one or more location servers 168 may include one or more location / positioning servers, which may include one or more of the GMLC 165, LMF 166, position determination entity (PDE), serving mobile location center (SMLC), mobile positioning center (MPC), etc. GMLC 165 and LMF 166 support UE location services. GMLC 165 provides an interface for clients / applications (e.g., emergency services) to access UE positioning information. LMF 166 receives measurement and assistance information from NG-RAN and UE 104 via AMF 161 to calculate the location of UE 104. NG-RAN may determine the location of UE 104 using one or more positioning methods. Positioning UE 104 may involve signal measurements, position estimation, and optional speed calculation based on these measurements. Signal measurements may be performed by UE 104 and / or serving base station 102. The measured signals may be based on a satellite positioning system (SPS) 170 (e.g., one or more of a global navigation satellite system (GNSS), a global positioning system (GPS), a non-terrestrial network (NTN), or other satellite positioning / positioning systems), LTE signals, wireless local area network (WLAN) signals, Bluetooth signals, a terrestrial beacon system (TBS), sensor-based information (e.g., an atmospheric pressure sensor, a motion sensor), an NR enhanced cell ID (NR E-CID) method, NR signals (e.g., multi-round trip time (multi-RTT), DL angle of departure (DL-AoD), DL time difference of arrival (DL-TDOA), UL time difference of arrival (UL-TDOA), and UL angle of arrival (UL-AoA) positioning), and / or one or more of other systems / signals / sensors.

[0055] Examples of UE 104 include cellular phones, smart phones, session initiation protocol (SIP) phones, laptops, personal digital assistants (PDAs), satellite radios, global positioning systems, multimedia devices, video devices, digital audio players (e.g., MP3 players), cameras, game consoles, tablet computers, smart devices, wearable devices, vehicles, electric meters, gas pumps, large or small kitchen appliances, healthcare equipment, implants, sensors / actuators, displays, or any other similarly functional devices. Some of the UEs 104 may be referred to as IoT devices (e.g., parking meters, gas pumps, toasters, vehicles, heart monitors, etc.). UE 104 may also be referred to as stations, mobile stations, subscriber stations, mobile units, subscriber units, wireless units, remote units, mobile devices, wireless devices, wireless communication devices, remote devices, mobile subscriber stations, access terminals, mobile terminals, wireless terminals, remote terminals, mobile phones, user agents, mobile clients, clients, or some other suitable terminology. In some scenarios, the term UE may also be applied to one or more supporting devices, such as in a device cluster arrangement. One or more of these devices may access the network collectively and / or individually.

[0056] Reference again Figure 1 In certain aspects, the UE 104 may include an L3 beam estimation component 198 configured to: measure a metric of a first PO beam subset of at least one PO beam subset including a plurality of PO beams from a network node, each PO beam subset being configured to form a PO pattern, and the first PO beam subset being associated with a first narrower RX beam set of the UE; estimate a metric of the first narrower Rx beam set using an ML model based on the metric of the PO beam subset; and identify at least one best Rx beam from the first narrower Rx beam set, the at least one best Rx beam being associated with a best estimated metric in the first narrower Rx beam set. In certain aspects, the base station 102 may include an ML model training component 199 configured to: obtain at least one coefficient of an ML model for estimating a set of RX beams based on a metric of a subset of PO beams; and transmit the at least one coefficient associated with the ML model for the UE to use the ML model to estimate the metric of the set of Rx beams based on the at least one coefficient and the metric of the subset of PO beams. Although the following description may focus on 5G NR, the concepts described herein may be applicable to other similar fields, such as LTE, LTE-A, CDMA, GSM, and other wireless technologies.

[0057] Figure 2A FIG200 is a diagram illustrating an example of a first subframe within a 5G NR frame structure. Figure 2BFIG230 is a diagram illustrating an example of DL channels within a 5G NR subframe. Figure 2C FIG250 is a diagram illustrating an example of a second subframe within a 5G NR frame structure. Figure 2D FIG280 is a diagram illustrating an example of UL channels within a 5G NR subframe. The 5G NR frame structure may be frequency division duplex (FDD) (wherein for a particular set of subcarriers (carrier system bandwidth), subframes within that subcarrier set are dedicated to either DL or UL), or may be time division duplex (TDD) (wherein for a particular set of subcarriers (carrier system bandwidth), subframes within that subcarrier set are dedicated to both DL and UL). Figure 2A , Figure 2C In the example provided, the 5G NR frame structure is assumed to be TDD, where subframe 4 is configured with slot format 28 (most of which are DL), where D is DL, U is UL, and F is flexible between DL / UL, and subframe 3 is configured with slot format 1 (all of which are UL). Although subframes 3 and 4 are shown as having slot formats 1 and 28, respectively, any particular subframe may be configured with any of the various available slot formats 0-61. Slot formats 0 and 1 are full DL and full UL, respectively. Other slot formats 2-61 include a mix of DL, UL and flexible symbols. The UE is configured with the slot format through the received slot format indicator (SFI) (dynamically configured through DL control information (DCI) or semi-statically / statically configured through radio resource control (RRC) signaling). Note that the following description also applies to the 5G NR frame structure as TDD.

[0058] FIG. 2A to FIG. 2DThe frame structure is illustrated, and various aspects of the present disclosure may be applicable to other wireless communication technologies that may have different frame structures and / or different channels. A frame (10 milliseconds (ms)) may be divided into 10 subframes (1ms) of equal size. Each subframe may include one or more time slots. The subframe may also include a microslot, which may include 7, 4, or 2 symbols. Each time slot may include 14 or 12 symbols, depending on whether the cyclic prefix (CP) is normal or extended. For a normal CP, each time slot may include 14 symbols, and for an extended CP, each time slot may include 12 symbols. The symbol on the DL may be a CP orthogonal frequency division multiplexing (OFDM) (CP-OFDM) symbol. The symbol on the UL may be a CP-OFDM symbol (for high throughput scenarios) or a discrete Fourier transform (DFT) spread OFDM (DFT-s-OFDM) symbol (also known as a single carrier frequency division multiple access (SC-FDMA) symbol) (for power-limited scenarios; limited to single-stream transmission). The number of slots within a subframe is based on the CP and the parameter set. The parameter set defines the subcarrier spacing (SCS) (see Table 1). The symbol length / duration can be scaled with 1 / SCS.

[0059]

[0060] Table 1: Parameter set, SCS and CP

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

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

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

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

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

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

[0067] Figure 33 is a block diagram of a server 310 communicating with a UE 350 in an access network. In the DL, Internet Protocol (IP) packets may be provided to a controller / processor 375. The controller / processor 375 implements layer 3 and layer 2 functionality. Layer 3 includes a radio resource control (RRC) layer, and layer 2 includes a service data adaptation protocol (SDAP) layer, a packet data convergence protocol (PDCP) layer, a radio link control (RLC) layer, and a medium access control (MAC) layer. The controller / processor 375 provides RRC layer functionality associated with broadcasting of system information (e.g., MIB, SIB), RRC connection control (e.g., RRC connection paging, RRC connection establishment, RRC connection modification, and RRC connection release), inter-radio access technology (RAT) mobility, and measurement configuration for UE measurement reporting; PDCP layer functionality associated with header compression / decompression, security (encryption, decryption, integrity protection, integrity verification), and handover support functions; RLC layer functionality associated with transfer of upper layer packet data units (PDUs), error correction through ARQ, concatenation, segmentation and reassembly of RLC service data units (SDUs), re-segmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functionality associated with mapping between logical channels and transport channels, multiplexing of MAC SDUs onto transport blocks (TBs), demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction through HARQ, priority handling, and logical channel prioritization.

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

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

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

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

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

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

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

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

[0076] Figure 4 400 is an example of an AI / ML algorithm 400 of a wireless communication method. Here, the AI / ML algorithm 400 may be included in a UE or a network node (e.g., a source network node or a target network node of a handover procedure) to provide mobility-related predictions based on AI / ML. The AI / ML algorithm 400 may include various functions, including a data collection function 402, a model training function 404, a model inference function 406, and an actor 408.

[0077] The data collection function 402 may be a function that provides input data to the model training function 404 and the model inference function 406. The data collection function 402 may include any form of data preparation, and it may not be specific to the specific implementation of the AI / ML algorithm (e.g., data preprocessing and cleaning, formatting, and transformation). Examples of input data may include, but are not limited to, measurements from network entities including UEs or network nodes, feedback from the actor 408, and output from another AI / ML model. The data collection function 402 may include training data and inference data, wherein the training data refers to data to be transmitted as input to the model training function 404, and the inference data refers to data transmitted as input to the model inference function 406.

[0078] The model training function 404 may be a function that performs ML model training, validation, and testing, which may generate model performance metrics as part of the model testing procedure. The model training function 404 may also be responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on the training data delivered or received from the data collection function 402. The model training function 404 may deploy or update the trained, validated, and tested AI / ML models to the model inference function 406, and receive model performance feedback from the model inference function 406.

[0079] The model inference function 406 may be a function that provides a model inference output (e.g., a prediction or decision). The model inference function 406 may also perform data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on the inference data delivered from the data collection function 402. The output of the model inference function 406 may include the inference output of the AI / ML model generated by the model inference function 406. The details of the inference output may be use case specific.

[0080] Model performance feedback may refer to information derived from the model inference function 406 that may be suitable for improving the AI / ML model trained in the model training function 404. Feedback from actors 408 or other network entities (via the data collection function 402) may be implemented for the model inference function 406 to create model performance feedback.

[0081] The actor 408 may be a function that receives output from the model inference function 406 and triggers or performs a corresponding action. The actor 408 may trigger an action for a network entity including other network entities or itself. The actor 408 may also provide feedback information for the model training function 404 or the model inference function 406 to derive training or inference data or performance feedback. The feedback may be sent back to the data collection function 402.

[0082] UE and / or network entities (centralized and / or distributed units) may use machine learning algorithms, deep learning algorithms, neural networks, reinforcement learning, regression, boosting or advanced signal processing methods for various aspects of wireless communications, such as with a base station, a TRP, another UE, etc.

[0083] In some aspects described herein, a coding device (e.g., UE) may train one or more neural networks to learn the dependence of the measured quality on various parameters. In addition, examples of machine learning models or neural networks that may be included in the UE and / or network entities include artificial neural networks (ANNs); decision tree learning; convolutional neural networks (CNNs); deep learning architectures, in which the output of a first layer of neurons becomes the input of a second layer of neurons, etc.; support vector machines (SVMs), for example, which include a separating hyperplane (e.g., a decision boundary) for classifying data; regression analysis; Bayesian networks; genetic algorithms; deep convolutional networks (DCNs), which are configured with additional pooling and normalization layers; and deep belief networks (DBNs).

[0084] A machine learning model, such as an artificial neural network (ANN), may include a set of interconnected artificial neurons (e.g., a neuron model) and may be a computing device or may represent a method to be performed by a computing device. The connections of the neuron model may be modeled as weights. The machine learning model may provide predictive models, adaptive control, and other applications by training via a data set. The model may be adaptive based on external or internal information processed by the machine learning model. Machine learning may provide nonlinear statistical data models or decision making, and may model complex relationships between input data and output information.

[0085] The machine learning model may include multiple layers and / or operations, which may be formed by cascading one or more of the cited operations. Examples of operations that may be involved include: extraction of various features of data, convolution operations, fully connected operations that may be activated or deactivated, compression, decompression, quantization, flattening, etc. As used herein, the "layer" of the machine learning model may be used to represent operations on input data. For example, convolutional layers, fully connected layers, etc. may be used to refer to associated operations on data input to the layer. Convolution AxB operations refer to operations that convert multiple input features A into multiple output features B. "Kernel size" may refer to the number of neighboring coefficients combined in a dimension. As used herein, "weights" may be used to represent one or more coefficients used in operations for combining individual rows and / or columns of input data in each layer. For example, a fully connected layer operation may have an output y, which is determined at least in part based on the product of the input matrix x and the weight A (which may be a matrix) and the sum of the bias value B (which may be a matrix). The term "weight" may be generally used herein to refer to both weights and bias values. Weights and biases are examples of parameters of a trained machine learning model. Different layers of a machine learning model can be trained independently.

[0086] Machine learning models may include various connectivity patterns, for example, including any of feedforward networks, hierarchies, recursive architectures, feedback connections, etc. The connections between layers of a neural network may be fully connected or locally connected. In a fully connected neural network, a neuron in a first layer may communicate its output to each neuron in a second layer, and each neuron in a second layer may receive input from each neuron in the first layer. In a locally connected network, a neuron in a first layer may be connected to a limited number of neurons in a second layer. In some aspects, a convolutional network may be locally connected and configured with a shared connection strength associated with the input of each neuron in the second layer. A locally connected layer of a network may be configured so that each neuron in the layer has the same or similar connectivity pattern, but with different connection strengths.

[0087] A machine learning model or neural network may be trained. For example, a machine learning model may be trained based on supervised learning. During training, the machine learning model may be presented with inputs that the model uses to calculate to produce an output. The actual output may be compared to the target output, and the difference may be used to adjust the parameters of the machine learning model (such as weights and biases) to provide an output closer to the target output. Before training, the output may be incorrect or less accurate, and the error or difference between the actual output and the target output may be calculated. The weights of the machine learning model may then be adjusted so that the output is more closely aligned with the target. In order to adjust the weights, the learning algorithm may calculate a gradient vector for the weights. The gradient may indicate the amount by which the error will increase or decrease if the weights are slightly adjusted. At the top layer, the gradient may directly correspond to the value of the weights connecting the activated neurons in the penultimate layer and the neurons in the output layer. In the lower layers, the gradient may depend on the value of the weights and the calculated error gradients of the higher layers. The weights may then be adjusted to reduce the error or move the output closer to the target. This way of adjusting the weights may be referred to as back propagation through a neural network. The process may continue until the achievable error rate stops decreasing, or until the error rate has reached a target level.

[0088] These machine learning models may include computational complexity and a large number of processors for training machine learning models. The output of one node is connected as an input to another node. The connection between nodes may be referred to as an edge, and weights may be applied to the connection / edge to adjust the output from one node, which is used as an input to another node. Nodes may apply thresholds to determine whether or when to provide output to a connected node. The output of each node may be calculated as a nonlinear function of the sum of the inputs to the node. A neural network may include any number of nodes and any type of connection between the nodes. A neural network may include one or more hidden nodes. Nodes may be aggregated into layers, and different layers of a neural network may perform different kinds of transformations on the input. A signal may travel from an input at the first layer through multiple layers of a neural network to an output at the last layer of the neural network, and may traverse these layers multiple times.

[0089] Figure 5 An example 500 of L1-level beams, L2-level beams, and L3-level beams is illustrated. In some aspects, to support mmWave (mmW) communications, the network node 504 and the UE may perform beamforming using more than one beam set including different beam levels with different configurations. For example, the beams may include L1-level beams (e.g., L1 beams 510), L2-level beams (e.g., L2 beams 520), and L3-level beams (e.g., L3 beams 530).

[0090] First, L1 beam 510 may be used for initial beam selection. For example, L1 beam 510 may be an SSB beam, e.g., a beam direction in which an SSB signal is transmitted. Network node 504 may perform SSB beam scanning by transmitting an SSB set in different directions and / or angles to facilitate beamforming. Network node 504 may scan the beams, and the UE may select a beam and report the selected beam to network node 504.

[0091] One or more L2 beams 520 may be used for beam refinement for the network node 504, and each L2 beam may be narrower than the L1 beam. The L2 beam 520 may be referred to as a transmit (Tx) beam of the network node 504. After beam selection using the L1 beam 510, the network node 504 and the UE may use the L2 beam 520 to perform network node 504 Tx beam refinement. The L2 beam 520 may be a CSI-RS beam, for example, a CSI-RS may be sent on the beam, and the CSI-RS may be measured for beam refinement. That is, the network node 504 may send a set of L2 beams carrying a set of CSI-RS based on the L1 beam 510 selected by the UE. Here, the L2 beam may be sent within the selected L1 beam 510. That is, the L2 beam 520 may be narrower than the L1 beam 510, and the UE may measure the CSI-RS received at the narrower beam within the selected L1 beam 510 selected at the UE for the beam pair link.

[0092] L3 level beams can be used for beam refinement for UE. L3 beam 530 may be referred to as a UE receive (Rx) beam. After beam selection using L1 beam 510 and network node 504 Tx beam refinement using L2 beam 520, network node 504 and UE may use one or more L3 beams for UE Rx beam refinement. L3 beam 530 may have, for example, a narrower angle than L1 beam and / or L2 beam, and may have the most accurate beam level for mmW measurement among L1 beam, L2 beam, and L3 beam. Within L2 beam 520 selection, UE may refine UE Rx beam and set spatial filters on Rx antenna array. L3 beam 530 may have the highest gain among L1 beam 510, L2 beam 520, and L3 beam 530, and may expand the cell range of wireless communication.

[0093] Since L3 beams are narrower beams, the network node 504 and the UE may be configured with a relatively large number of L3 beams, and if L3 beams 530 are configured in the codebook, the network node 504 and the UE may not be able to or may take a longer time to scan the complete list of L3 beams (e.g., a polling method) compared to L1 beams 510. The network node 504 and the UE may be configured with an intelligent algorithm to select a subset of L3 beams for scanning.

[0094] Here, the L1 beam 510 may also be referred to as a pseudo omni (PO) beam, and according to the number of PO beams supported by the UE, the L1 beam 510 may have a relatively large angular range (e.g., 90 degrees or 60 degrees). The L2 beam 520 may have an angular range smaller than that of the L1 beam 510 (e.g., half the angular range of the L1 beam 510). The L3 beam 530 may have an angular range smaller than that of the L2 beam 520 (e.g., half the angular range of the L2 beam 520).

[0095] Figure 6 A UE 600 including one or more antenna arrays for receiving at least one minimum viable PO beam (MVP) set is illustrated. Here, the MVP set may refer to a set of PO beams that can form a PO pattern. For example, for a PO beam with an angular range of 90 degrees, the MVP set may include four (4) PO beams to form a PO pattern. The UE 600 600 may include a plurality of antenna array panels 602, 604, 606, and 608. The UE 600 may be configured with one or more antenna array panels 602, 604, 606, and 608 for receiving directional PO beams. That is, the UE 600 may include one or more antenna array panels, and each antenna panel may be configured to receive at least one directional beam.

[0096] For example, a first MVP set may include PO beams with indices 0, 1, 2, and 3, a second MVP set may include PO beams with indices 4, 5, 6, and 7, a third MVP set may include PO beams with indices 8, 9, 10, and 11, and a fourth MVP set may include PO beams with indices 12, 13, 14, and 15. Here, the PO beams may be L1 beams. Here, the first antenna array panel 602 may be configured to receive PO beams with indices 0, 4, 8, and 12, the second antenna array panel 604 may be configured to receive PO beams with indices 1, 5, 9, and 13, the third antenna array panel 606 may be configured to receive PO beams with indices 2, 6, 10, and 14, and the fourth antenna array panel 608 may be configured to receive PO beams with indices 3, 7, 11, and 15.

[0097] In order for the UE 600 to find the best L3 beam, the UE 600 may spend a lot of time performing L1 beam selection for the PO beam using a large antenna array, and then refining the beam selection using the associated L2 beam and L3 beam. The amount of time used to find the best L3 beam may degrade performance at the UE, and performing beam measurements for L1, L2, and L3 level beam selection / refinement may consume a lot of power at the UE.

[0098] Figure 7700 is a diagram of an L3 beam selection timeline. Diagram 700 includes a first timeline 710 of a first UE configured with a measurement window to measure one beam per single opportunity (e.g., a 1x measurement window), and a second timeline 720 of a second UE configured with a measurement window to measure three (3) beams per single opportunity (e.g., a 3x measurement window). Here, the PO L1 beams may include 20 PO L1 beams, each PO L1 beam includes seven (7) L2 beams, and each L2 beam includes nine (9) L3 beams.

[0099] Until the UE selects an appropriate L3 beam, the UE may be configured with an L3 beam with a relatively low measurement result. The longer it takes to make an L3 beam selection, the longer the UE uses a lower quality L3 beam with a relatively low measurement result.

[0100] To complete L3 beam selection, the UE may perform measurements on 20 PO beams (e.g., L1 beam), perform service beam monitoring (SBM), perform measurements on seven (7) L2 beams, and perform measurements on nine (9) L3 beams, including multiple search opportunities for an identified best L2 beam and a best L3 beam based on the measurements of the L2 beams and the L3 beams.

[0101] The first UE of the first timeline 710 may spend 25 opportunities to perform measurements on 20 PO beams (e.g., L1 beam) and five (5) SBM opportunities inserted therebetween. The second UE of the second timeline 720 may spend nine (9) opportunities to perform measurements on 20 PO beams (e.g., L1 beam) and two (2) SBM opportunities inserted therebetween. The first UE of the first timeline 710 may spend 24 opportunities to perform measurements on seven (7) L2 beams and nine (9) L3 beams and four (4) SBM opportunities and four (4) search opportunities inserted therebetween. The second UE of the second timeline 720 may spend 10 opportunities to perform measurements on seven (7) L2 beams and nine (9) L3 beams and two (2) SBM opportunities and two (2) search opportunities inserted therebetween. Therefore, to achieve the best L3 beam, the first UE of the first timeline 710 may spend 49 opportunities (e.g., at least 980ms) or the second UE of the second timeline 720 may spend 19 opportunities (e.g., at least 380ms). Performing a complete L3 beam selection may result in a large amount of power consumption per frequency measurement.

[0102] Fig. 8A and Figure 8B800 and 850 are diagrams of L1 beam selection. The UE may be configured to monitor or measure 20 PO beam pairs including five (5) MVP sets, each MVP set including four (4) PO beams that may form a PO pattern. The UE may measure each MVP set until 1) all 20 PO beams are measured, 2) the early exit criteria for mmW beams are met, or 3) the timer for beamforming expires.

[0103] The diagram 800 of L1 beam selection includes complete measurements of 20 PO beams. The UE may perform a first measurement of a first MVP set 802, a second measurement of a second MVP set 804, and so on, until a fifth measurement of a fifth MVP set. Based on the measurements of the first MVP set to the fifth MVP set, the UE may transmit the measured metrics of the OP beam (e.g., L1 beam) to the network node at 806 for beam selection based on the PO beam.

[0104] Here, the metric may refer to at least one measurement result of a received reference signal (RS). For example, the metric may include, but is not limited to, a received signal strength indicator (RSSI), a reference signal received power (RSRP), a reference signal received quality (RSRQ), a signal to interference plus noise ratio (SINR), a signal to noise plus interference ratio (SNIR), or a signal to noise ratio (SNR).

[0105] Diagram 850 of L1 beam selection includes early termination of PO beam measurement based on early exit criteria. The UE may be configured with a threshold associated with the L1 beam metric, and once the UE measures that one of the L1 beams (e.g., the PO beam) may have a metric greater than the threshold associated with the L1 beam metric, the UE may stop measuring the L1 beam. Here, the threshold may be referred to as an early exit criterion, and at 856, the UE may stop measuring the L1 beam and transmit the L1 metric to the network node. For example, the UE may perform a first measurement on a first MVP set 852 and a second measurement on a second MVP set 854, and determine that the metric of one L1 beam of the first MVP set 852 and the second MVP set 854 meets the early exit criterion. Based on determining that the metric of the one L1 beam meets the early exit criterion, the UE may stop the L1 beam measurement and transmit the metric of the L1 beam to the network node for beam selection based on the PO beam.

[0106] In some aspects, the UE may be configured to estimate the L3 beam based on a set of metrics of the L1 beam. That is, the UE may measure at least a set of MVPs to measure the metrics of the L1 beam, and estimate the best L3 beam based on the metrics of the MVP set. The UE may include an AI / ML model configured to estimate the best L3 beam based on the metrics of at least one MVP set, and the UE may use the AI / ML model to estimate the best L3 beam based on the metrics of at least one MVP set. The AI / ML model may further estimate the metrics of the estimated L3 beam, and the UE may determine whether to exit early from the L1 beam selection based on the metrics of at least one MVP set. Based on the estimated best L3 beam, the UE may search for the best L3 beam estimated by the AI / ML, and set a spatial filter on the Rx antenna array to communicate the refined beam to the network node.

[0107] Fig.9A , Fig. 9B and Fig. 9C 900, 930, and 960 are diagrams of L3 beam estimation. After measuring each set of 4 beams in consecutive mmW SSB opportunities, the UE may request a prediction engine (e.g., an AI / ML model) to use the measurements of the set of 4 beams to give an estimated best L3 beam. That is, the UE may be configured to include an AI / ML model for estimating the best L3 beam based on a metric of at least one MVP set.

[0108] Fig.9A 900 is a diagram of L3 beam estimation based on metrics of a first MVP set 902. At 910, the UE may input the metrics of the first MVP set 902 into the AI / ML model, and the AI / ML model may estimate an optimal L3 beam 912 based on the metrics of the first MVP set 902. Based on the estimated L3 beam having sufficient quality (e.g., a metric greater than a threshold), the UE may transmit the metric to the network node in advance and exit PO beam scanning. At 906, based on the estimated best L3 beam 912, the UE may transmit the metrics of the first MVP set 902 to the network node for L1 beam selection, and further refine the UE's Rx beam based on the best L3 beam estimated by the AI / ML model.

[0109] Based on the predicted best beam not having sufficient quality (e.g., a metric less than or equal to a threshold), the UE may proceed to the next MVP set and thereafter transmit the complete PO beam measurement results to the machine learning engine.

[0110] Fig. 9B930 is a diagram of L3 beam estimation based on metrics of a first MVP set 932 and a second MVP set 934. The UE may input the metrics of the first MVP set 932 to an AI / ML model 940, and the AI / ML model 940 may estimate an optimal L3 beam 942 based on the metrics of the first MVP set 932. Based on the predicted optimal beam not having sufficient quality (e.g., a metric less than or equal to a threshold), the UE may proceed to the next MVP set. The UE may input the metrics of the first MVP set 932 and the second MVP set 934 to an AI / ML model 950, and the AI / ML model 950 may estimate an optimal L3 beam 952 based on the metrics of the first MVP set 932 and the second MVP set 934. Based on the estimated L3 beam having sufficient quality (e.g., a metric greater than a threshold) at 950, the UE may transmit the metrics of the first MVP set 932 and the second MVP set 934 to the network node in advance at 936 and exit PO beam scanning. At 936 , the UE may transmit metrics of the first MVP set 932 and the second MVP set 934 to the network node for L1 beam selection and further refine the UE's Rx beam based on the best L3 beam 952 estimated by the AI / ML model 950 .

[0111] In one aspect, the AI / ML model may run past the beam selection point. In one example, the UE may use this opportunity for the next MVP set. In another example, if the timeline is completely overtaken by the AI / ML model, the UE may lose this opportunity. Fig. 9C 960 is a diagram of L3 beam estimation based on a timer expiration based on a metric of a first MVP set 962. Here, the timer may be a beam selection timer. The UE may input the metric of the first MVP set 962 into an AI / ML model 970, and the AI / ML model may estimate an optimal L3 beam 972 based on the metric of the first MVP set 962. In one case, the beam selection timer may expire, and the UE may determine to exit L1 beam selection. The UE may obtain an optimal L3 beam 972 through the AI / ML model 970 based on the metric of the first MVP set 962, and the UE may transmit the metric to the network node and exit PO beam scanning. At 966, based on the estimated optimal L3 beam 972, the UE may transmit the metric of the first MVP set 962 to the network node for L1 beam selection, and further refine the UE's Rx beam based on the optimal L3 beam estimated by the AI / ML model.

[0112] The machine learning algorithm may be embedded in a digital signal processor (DSP) of the UE, and the UE may obtain the configuration of the AI / ML model from a network calibration configuration embedded in the DSP. For example, the configuration of the AI / ML model may include AI / ML model coefficients for establishing an optimal L3 beam and its metrics based on measured metrics of a set of L1 beams (e.g., PO beams). In one example, the optimal L3 beam may be derived based on static prediction coefficients and a measured set of L1 beams. Based on an increased number of metrics from the set of L1 beams, the estimation of the L3 beam may have improved accuracy. In addition, the AI / ML model may be trained using measurements of the set of L1 beams to provide improved accuracy in estimating the optimal L3 beam and its metrics.

[0113] In some aspects of the present disclosure, the UE may use an AI / ML model (such as in combination with Figure 4 The model described above is used to refine the L3 beam and reduce the processing time and power consumption of L2 beam and L3 beam measurement and scanning.

[0114] Fig.10 1000 is a diagram of scheduling L3 beam estimation. The ML prediction (or estimation) period may be configured based on the number of PO beams of each MVP set, the number of L3 schedules, and the search period. That is, the period of AI / ML estimation of L3 beams may be based at least on the number of PO beams of each MVP set, the number of L3 schedules, and the search period. Here, the period of L3 beam estimation may be expressed as (the number of PO beams of each MVP set + the number of L3 schedules) * search period. Here, the number of PO beams of each MVP set may be configured based on the number of PO beams that the UE can support, and the number of L3 schedules may be configured based on the capabilities of the UE. For example, Figure 1000 shows that the number of PO beams of each MVP set may be four (4) (e.g., four (4) PO beams in each MVP set), and the number of L3 beam schedules may be three (3). An AI / ML cycle may be configured between the first ML estimation 1010 and the second ML estimation 1012 , the AI / ML cycle including three (3) opportunities for L3 beam searching 1020 and four (4) opportunities for PO beam searching 1004 .

[0115] In one aspect, the AI / ML model estimation may be requested based on the expiration of the ML estimation timer. That is, the UE may include an ML estimation timer, and perform ML estimation of the L3 beam based on the expiration of the ML estimation timer. For example, the UE may start the ML estimation timer, and when the ML estimation timer expires, the UE may measure the L1 beam (e.g., the PO beam). When the ML estimation timer expires, the UE may run the AI / ML model to estimate the best L3 beam and its metric based on the measured L1 beam.

[0116] In another aspect, AI / ML model estimation may be requested based on a neighboring cell metric being greater than a threshold value than the serving cell. For example, the UE may be configured to request AI / ML model estimation for the best L3 beam based on the difference between the best PO beam metric of the neighboring cell and the best PO beam metric of the serving cell (e.g., best PO RSRP of the best neighboring cell - best PO RSRP of the serving cell) being greater than a threshold value. (e.g., best PO RSRP of the best neighboring cell - best PO RSRP of the serving cell > offset + 2dB). That is, based on the metric of the best L1 PO beam of the neighboring cell being greater than the metric of the best L1 PO beam of the serving cell by a threshold value, a machine learning request may be requested based on all measured metrics (e.g., RSRP) of the PO beams from the serving cell and the neighboring cell.

[0117] In some aspects, upon machine learning confirmation, the measurement scheduler may sort and pick the top N L3 beams estimated for subsequent search scheduling. That is, based on the results of the estimated metrics of the L3 beams, the UE may pick a set of top N3 beams and perform an L3 beam search. For example, the UE may be configured to pick the top three (3) estimated L3 beams with the top three (3) largest estimated metrics. Based on the estimation of the L3 beam metrics, the UE may determine at least one best L3 beam and schedule the estimated best L3 beam. That is, the UE may measure the estimated best L3 beam during a static search procedure.

[0118] In one aspect, during the static search procedure, if the UE detects that there is an estimated best L3 beam, the UE may assign a higher priority to scheduling the PO beam (e.g., L1 beam). That is, the UE may be configured to assign a higher priority to the estimated best L3 beam for scheduling wireless communications.

[0119] In another aspect, the UE may configure the allowed beam list to include the estimated L3 beam. That is, the UE may be configured to schedule wireless communications using the best L3 beam. If the UE determines that the best L3 beam is an unallowed beam, the UE may continue to schedule wireless communications on the PO beam (e.g., L1 beam).

[0120] In another aspect, once the L3 estimation beam is scheduled, the UE may resume scheduling the PO beam. The UE may schedule the estimated L3 beam on the component carrier identifier (CC ID) that initiated the AI / ML estimation request. For example, if the AI / ML estimation is requested based on the best neighboring cell, the UE may schedule the estimated L3 beam on the CC ID of the best neighboring cell.

[0121] Based on the AI / ML-based estimation of the L3 beam based on the measurements of the L1 beam (e.g., MVP set), the UE can select the best L3 beam in a small (or short timeline) MVP measurement round with relatively small time cost and power consumption. Based on the AI / ML estimation (which is based on the known metrics of the L1 beam), the UE can also quickly enter the connection mode with the best L3 beam. Since the L3 beam is estimated during the L1 beam selection procedure, the L3 beam refinement can be automatically started in advance from the neighbor cells and parent neighbor cells. Therefore, the UE can select the best PO beam, which has the advantage that the UE is already located on the best L3 beam (e.g., Rx beam).

[0122] In some aspects, the AI / ML model of the UE for L3 estimation may be configured with corresponding coefficients for the AI / ML learning algorithm. The AI / ML estimation model may be configured with a default parameter set generated as part of the hardware design. Here, the default parameter set may be based on measured electric field data and / or a codebook designed according to the measured L1 beam metric. In addition, the parameters or coefficients of the AI / ML model may be generated by a network entity and sent to the UE for specific implementation. That is, the network entity (e.g., a dedicated server) may include an AI / ML model trainer and generate AI / ML model parameters or coefficients for the AI / ML model of the UE. For example, the dedicated server may be configured to receive a data set including the results of the measured L1 metric and / or the AI / ML model from the UE, and train the AI / ML model based on the data set received from the UE. The UE may input and output data processed via a network-based beam characteristic application.

[0123] Fig.11The call flow diagram 1100 is a wireless communication method. The call flow diagram 1100 may include a UE 1102, a first network node 1104, a second network node 1105, and an ML training server 1106. Here, the first network node 1104 may be associated with a serving cell, and the second network node 1105 may be associated with a neighboring cell of the serving cell. The UE 1102 may measure a metric of at least one MVP set (e.g., including an L1 beam) from a network node (e.g., the first network node 1104 or the second network node 1105), estimate a metric of a narrower Rx beam (e.g., an L3 beam) set using an ML model based on the metric of the at least one MVP set, and identify at least one best Rx beam from the first narrower Rx beam set, the at least one best Rx beam being associated with the best estimated metric. The ML training server may obtain at least one coefficient of the ML model, and the at least one coefficient of the ML model may be transmitted to the UE 1102. The UE 1102 may configure the ML model for estimating the metric of the narrower Rx beam set. The UE 1102 may send the metric of the PO beam subset or at least a portion of the estimated metric of the Rx beam set to the ML model training server, and the ML model training server may obtain at least one coefficient of the ML modem based on the metric of the PO beam subset or at least a portion of the estimated metric of the Rx beam set received from the UE 1102.

[0124] At 1108, the first network node 1104 may transmit a signal on the plurality of PO beams. The UE 1102 may receive a signal on the plurality of PO beams. The signal may include an SSB or a reference signal such as a CSI-RS. The plurality of PO beams may include at least one PO beam subset, each PO beam subset being configured to form a PO pattern. Here, each PO beam may be associated with a narrower Rx beam set of the UE 1102.

[0125] At 1110, the UE 1102 may start a timer before measuring the metric of the first PO beam subset at 1112. Here, the metric of the first Rx beam set may be estimated based on the expiration of the timer at 1124. Here, the timer may be a beam selection timer. The UE 1102 may be configured to start a timer, and when the timer expires, the UE 1102 may stop measuring the metric of the PO beam subset at 1112, and start using the ML model to estimate the metric of the narrower Rx beam set at 1116.

[0126] At 1112, UE 1102 may measure a metric of a PO beam subset in at least one PO beam subset of the plurality of PO beams received from the network node at 1108. Here, the PO beam subset may refer to an MVP set including PO beams configured to form a PO pattern, and the first PO beam subset is associated with a first narrower RX beam set of UE 1102.

[0127] In one aspect, the PO beam subset may include a first PO beam subset, and the first narrower Rx beam set estimated using the ML model at 1124 may be estimated based on a metric of the first PO beam subset. Based on the estimated metric of the narrower Rx beam being greater than a threshold (e.g., a first threshold), the UE 1102 may stop measuring the PO beam subset and estimating the narrower Rx beam.

[0128] In another aspect, based on the metric of the narrower Rx beam estimated based on the first PO beam subset being less than or equal to the first threshold, UE 1102 may measure a second PO beam subset, and may use an ML model at 1124 to estimate a second narrower Rx beam set based on the metrics of the first PO beam subset and the second PO beam subset.

[0129] At 1114, second network node 1105 may send a signal to UE 1102 on another set of multiple PO beams including the third PO beam subset (e.g., similar to 1108). UE 1102 may receive another set of multiple PO beams including the third PO beam subset from second network node 1105. Here, second network node 1105 may be associated with a neighboring cell.

[0130] At 1116, UE 1102 may measure a metric of a third PO beam subset from a neighboring network node, and the third PO beam subset may be associated with a third Rx beam set. Here, based on the received metric of the third PO beam subset, UE 1102 may estimate a third narrower Rx beam set using the ML model at 1124 based on the metric of the third PO beam subset being greater than the metric of the first PO beam subset by a second threshold.

[0131] At 1120, the ML training server 1106 may obtain at least one coefficient of the ML model for estimating the RX beam set based on the metric of the PO beam subset. The at least one coefficient of the ML model may be obtained based on at least a portion of the metric of the PO beam subset or the estimated metric of the Rx beam set received from the UE 1102 (e.g., at 1126). That is, the ML training server 1106 may train the ML model using at least a portion of the metric of the PO beam subset or the estimated metric of the Rx beam set received from the UE 1102, and generate at least one coefficient of the ML model for the UE 1102.

[0132] At 1122, the ML training server 1106 may send at least one coefficient associated with the ML model for the UE 1102 to estimate the metric of the Rx beam set using the ML model based on the at least one coefficient and the metric of the PO beam subset. The UE 1102 may receive at least one coefficient associated with the ML model, and may estimate the metric of the Rx beam set using the ML model at 1124 based on the at least one coefficient and the metric of the PO beam subset (e.g., the first PO beam subset or the second PO beam subset received from the first network node 1104 at 1108 or the third PO beam subset received from the second network node 1105 at 1114). Here, the at least one coefficient received from the ML model training server may be based at least on the metric of the first PO beam subset or at least a portion of the estimated metric of the first Rx beam set.

[0133] At 1124, the UE 1102 may estimate the metric of the narrower Rx beam set based on the metric of the PO beam subset using the ML model. Here, the metric of the Rx beam may be estimated in each estimation cycle, each estimation cycle including measurement of the metric of at least one PO beam subset and search for at least one Rx beam. The UE 1102 may estimate the metric of the first Rx beam set based on at least one coefficient received from the ML training server 1106 at 1122 using the ML model.

[0134] In one example, the narrower Rx beam set may be a first narrower Rx beam set estimated using an ML model based on the metrics of the first PO beam subset measured at 1112. In another example, the narrower Rx beam set may be a second narrower Rx beam set estimated using an ML model based on the metrics of the first PO beam subset and the second PO beam subset measured at 1112.

[0135] In another example, the narrower Rx beam set may be a third narrower Rx beam set estimated using an ML model based on a metric of a third PO beam subset received at 1114, based on the metric of the third PO subset being greater than a metric of the first PO beam subset by a second threshold.

[0136] At 1126, the UE 1102 may send at least a portion of the metric of the PO beam subset or the estimated metric of the Rx beam set to the ML model training server. The ML training server 1106 may receive at least a portion of the metric of the PO beam subset or the estimated metric of the Rx beam set from the UE 1102. At least one coefficient of the ML model may be obtained at 1120 based on at least a portion of the metric of the PO beam subset or the estimated metric of the Rx beam set received from the UE 1102.

[0137] In one example, the metric of the PO beam subset may be a first PO beam subset, and the narrower Rx beam set may include a first narrower Rx beam set estimated using an ML model at 1124 based on the metric of the first PO beam subset. In another example, the metric of the PO beam subset may be a first PO beam subset and a second PO beam subset, and the narrower Rx beam set may include a second narrower Rx beam set estimated using an ML model at 1124 based on the metric of the first PO beam subset and the second PO beam subset. In another example, the metric of the PO beam subset may be a third PO beam subset received from the second network node 1105 at 1114, and the narrower Rx beam set may include a third narrower Rx beam set estimated using an ML model at 1124 based on the metric of the third PO beam subset.

[0138] At 1128, the UE 1102 may identify at least one best Rx beam from the narrower Rx beam set, the at least one best Rx beam being associated with the best estimated metric in the first narrower Rx beam set. In one example, the narrower Rx beam set may be a first narrower Rx beam set estimated using an ML model based on the metric of the first PO beam subset measured at 1112. In another example, the narrower Rx beam set may be a second narrower Rx beam set estimated using an ML model based on the metric of the first PO beam subset and the second PO beam subset measured at 1112. In another example, the narrower Rx beam set may include a third narrower Rx beam set estimated using an ML model at 1124 based on the metric of the third PO beam subset measured at 1116.

[0139] At 1130, UE 1102 may report the metric of the PO beam subset to the network node based on the estimated metric of at least one Rx beam being greater than the first threshold. In one example, based on the estimated metric of the first narrower Rx beam set being greater than the first threshold, the metric of the PO beam subset may be the first PO beam subset. In another example, based on the second narrower Rx beam set being greater than the first threshold, the metric of the PO beam subset may be the first PO beam subset and the second PO beam subset. In another example, based on the metric of the third PO subset being greater than the metric of the first PO beam subset by the second threshold, the metric of the PO beam subset may be the third PO beam subset received from the second network node 1105 at 1114.

[0140] At 1132, the UE 1102 may search the Rx beam set for at least one best Rx beam associated with a best estimation metric.

[0141] At 1134, the UE 1102 may use the at least one best Rx beam to communicate data with the network node based on the estimated metric of the at least one best Rx beam being greater than the first threshold. Here, the UE 1102 may use a refined Rx beam estimated using an ML model based on a metric of at least one MVP set. Here, at 1130, the UE 1102 may use a narrower Rx beam (e.g., an L3 beam) without reporting the L3 beam to the network node.

[0142] Fig.12 1200 is a flowchart of a wireless communication method. The method may be performed by a UE (e.g., UE 104; device 1604). The UE may measure a metric of at least one MVP set (e.g., including an L1 beam) from a network node (e.g., a serving network node or a neighboring network node), estimate a metric of a narrower Rx beam set (e.g., an L3 beam) using an ML model based on the metric of the at least one MVP set, and identify at least one best Rx beam from a first narrower Rx beam set, the at least one best Rx beam being associated with the best estimated metric. The UE may receive at least one coefficient of the ML model from an ML training server and configure the ML model for estimating the metric of the narrower Rx beam set. The UE may send a metric of a subset of PO beams or at least a portion of the estimated metric of the Rx beam set to the ML model training server to obtain at least one coefficient of an ML modem.

[0143] At 1208, the UE may receive a plurality of PO beams. The plurality of PO beams may include at least one PO beam subset, each PO beam subset being configured to form a PO pattern. Here, each PO beam may be associated with a narrower Rx beam set of the UE. For example, at 1108, the UE 1102 may receive a plurality of PO beams. In addition, 1208 may be performed by the L3 beam estimation component 198.

[0144] At 1210, the UE may start a timer before measuring the metrics of the first PO beam subset at 1212. Here, the metrics of the first Rx beam set may be estimated at 1224 based on the expiration of the timer. Here, the timer may be a beam selection timer. The UE may be configured to start a timer, and when the timer expires, the UE may stop measuring the metrics of the PO beam subset at 1212 and start using the ML model to estimate the metrics of the narrower Rx beam set at 1216. For example, at 1110, the UE 1102 may start a timer before measuring the metrics of the first PO beam subset at 1112. In addition, 1210 may be performed by the L3 beam estimation component 198.

[0145] At 1212, the UE may measure a metric of a PO beam subset in at least one PO beam subset of the plurality of PO beams received from the network node at 1208. Here, the PO beam subset may refer to an MVP set including PO beams configured to form a PO pattern, and the first PO beam subset is associated with a first narrower RX beam set of the UE. For example, at 1112, the UE 1102 may measure a metric of a PO beam subset in at least one PO beam subset of the plurality of PO beams received from the network node at 1108. In addition, 1212 may be performed by the L3 beam estimation component 198.

[0146] In one aspect, the PO beam subset may include a first PO beam subset, and the first narrower Rx beam set estimated using the ML model at 1224 may be estimated based on a metric of the first PO beam subset. Based on the estimated metric of the narrower Rx beam being greater than a threshold (e.g., a first threshold), the UE may stop measuring the PO beam subset and estimating the narrower Rx beam.

[0147] In another aspect, based on the metric of the narrower Rx beam estimated based on the first PO beam subset being less than or equal to the first threshold, the UE may measure the second PO beam subset, and may use the ML model at 1224 to estimate the second narrower Rx beam set based on the metrics of the first PO beam subset and the second PO beam subset.

[0148] At 1214, the UE may receive another set of multiple PO beams including the third PO beam subset from the second network node. Here, the second network node may be associated with a neighboring cell. For example, at 1114, UE 1102 may receive another set of multiple PO beams including the third PO beam subset from the second network node 1105. In addition, 1214 may be performed by L3 beam estimation component 198.

[0149] At 1216, the UE may measure a metric of a third PO beam subset from a neighboring network node, and the third PO beam subset may be associated with a third Rx beam set. Here, based on the received metric of the third PO beam subset, the UE may estimate a third narrower Rx beam set using the ML model at 1224 based on the metric of the third PO beam subset being greater than the metric of the first PO beam subset by a second threshold. For example, at 1116, the UE 1102 may measure a metric of a third PO beam subset from a neighboring network node, and the third PO beam subset may be associated with a third Rx beam set. In addition, 1216 may be performed by the L3 beam estimation component 198.

[0150] At 1222, the UE may receive at least one coefficient associated with the ML model, and may estimate the metric of the Rx beam set using the ML model at 1224 based on the at least one coefficient and the metric of the PO beam subset. Here, the PO beam subset may include the first PO beam subset or the second PO beam subset received from the first network node at 1208, or the third PO beam subset received from the second network node at 1214. The at least one coefficient received from the ML model training server may be based at least on the metric of the first PO beam subset or at least a portion of the estimated metric of the first Rx beam set. For example, at 1122, the UE 1102 may receive at least one coefficient associated with the ML model, and may estimate the metric of the Rx beam set using the ML model at 1124 based on the at least one coefficient and the metric of the PO beam subset. In addition, 1222 may be performed by the L3 beam estimation component 198.

[0151] At 1224, the UE may estimate the metric of the narrower Rx beam set using the ML model based on the metric of the PO beam subset. Here, the metric of the Rx beam may be estimated in each estimation cycle, each estimation cycle including measurement of the metric of at least one PO beam subset and search for at least one Rx beam. The UE may estimate the metric of the first Rx beam set using the ML model based on at least one coefficient received from the ML training server at 1222. For example, at 1124, the UE 1102 may estimate the metric of the narrower Rx beam set using the ML model based on the metric of the PO beam subset. In addition, 1224 may be performed by the L3 beam estimation component 198.

[0152] In one example, the narrower Rx beam set may be a first narrower Rx beam set estimated using an ML model based on the metrics of the first PO beam subset measured at 1212. In another example, the narrower Rx beam set may be a second narrower Rx beam set estimated using an ML model based on the metrics of the first PO beam subset and the second PO beam subset measured at 1212.

[0153] In another example, the narrower Rx beam set may be a third narrower Rx beam set estimated using an ML model based on a metric of a third PO beam subset received at 1214 and based on the metric of the third PO subset being greater than a metric of the first PO beam subset by a second threshold.

[0154] At 1226, the UE may send at least a portion of the metric of the PO beam subset or the estimated metric of the Rx beam set to the ML model training server. The ML training server may receive at least a portion of the metric of the PO beam subset or the estimated metric of the Rx beam set from the UE. At least one coefficient of the ML model may be obtained at 1220 based on at least a portion of the metric of the PO beam subset or the estimated metric of the Rx beam set received from the UE. For example, at 1126, the UE 1102 may send at least a portion of the metric of the PO beam subset or the estimated metric of the Rx beam set to the ML model training server. In addition, 1226 may be performed by the L3 beam estimation component 198.

[0155] In one example, the metric of the PO beam subset may be a first PO beam subset, and the narrower Rx beam set may include a first narrower Rx beam set estimated using an ML model at 1224 based on the metric of the first PO beam subset. In another example, the metric of the PO beam subset may be a first PO beam subset and a second PO beam subset, and the narrower Rx beam set may include a second narrower Rx beam set estimated using an ML model at 1224 based on the metric of the first PO beam subset and the second PO beam subset. In another example, the metric of the PO beam subset may be a third PO beam subset received from the second network node at 1214, and the narrower Rx beam set may include a third narrower Rx beam set estimated using an ML model at 1224 based on the metric of the third PO beam subset.

[0156] At 1228, the UE may identify at least one best Rx beam from the narrower Rx beam set, the at least one best Rx beam being associated with the best estimated metric in the first narrower Rx beam set. In one example, the narrower Rx beam set may be a first narrower Rx beam set estimated using an ML model based on the metric of the first PO beam subset measured at 1212. In another example, the narrower Rx beam set may be a second narrower Rx beam set estimated using an ML model based on the metric of the first PO beam subset and the second PO beam subset measured at 1212. In another example, the narrower Rx beam set may include a third narrower Rx beam set estimated using an ML model at 1224 based on the metric of the third PO beam subset measured at 1216. For example, at 1128, the UE 1102 may identify at least one best Rx beam from the narrower Rx beam set, the at least one best Rx beam being associated with the best estimated metric in the first narrower Rx beam set. Furthermore, 1228 may be performed by the L3 beam estimation component 198 .

[0157] At 1230, the UE may report the metric of the PO beam subset to the network node based on the estimated metric of at least one Rx beam being greater than the first threshold. In one example, the metric of the PO beam subset may be the first PO beam subset based on the estimated metric of the first narrower Rx beam set being greater than the first threshold. In another example, the metric of the PO beam subset may be the first PO beam subset and the second PO beam subset based on the second narrower Rx beam set being greater than the first threshold. In another example, the metric of the PO beam subset may be the third PO beam subset received from the second network node at 1214 based on the metric of the third PO subset being greater than the metric of the first PO beam subset by a second threshold. For example, at 1130, the UE 1102 may report the metric of the PO beam subset to the network node based on the estimated metric of at least one Rx beam being greater than the first threshold. In addition, 1230 may be performed by the L3 beam estimation component 198.

[0158] At 1232, the UE may search the Rx beam set for at least one best Rx beam associated with the best estimation metric. For example, at 1132, the UE 1102 may search the Rx beam set for at least one best Rx beam associated with the best estimation metric. In addition, 1232 may be performed by the L3 beam estimation component 198.

[0159] At 1234, the UE may use the at least one best Rx beam to communicate data with the network node based on the estimated metric of the at least one best Rx beam being greater than the first threshold. Here, the UE may use a refined Rx beam that is estimated using an ML model based on a metric of at least one MVP set. Here, at 1230, the UE may use a narrower Rx beam (e.g., an L3 beam) without reporting the L3 beam to the network node. For example, at 1134, the UE 1102 may use the at least one best Rx beam to communicate data with the network node based on the estimated metric of the at least one best Rx beam being greater than the first threshold. In addition, 1234 may be performed by the L3 beam estimation component 198.

[0160] Fig.131300 is a flowchart of a wireless communication method. The method may be performed by a UE (e.g., UE 104; device 1604). The UE may measure a metric of at least one MVP set (e.g., including an L1 beam) from a network node (e.g., a serving network node or a neighboring network node), estimate a metric of a narrower Rx beam set (e.g., an L3 beam) using an ML model based on the metric of the at least one MVP set, and identify at least one best Rx beam from a first narrower Rx beam set, the at least one best Rx beam being associated with the best estimated metric. The UE may receive at least one coefficient of the ML model from an ML training server, and configure the ML model for estimating the metric of the narrower Rx beam set. The UE may send a metric of a subset of PO beams or at least a portion of the estimated metric of the Rx beam set to the ML model training server to obtain at least one coefficient of an ML modem.

[0161] At 1312, the UE may measure a metric of a PO beam subset of at least one PO beam subset of the plurality of PO beams received from the network node. Here, the PO beam subset may refer to an MVP set including PO beams configured to form a PO pattern, and the first PO beam subset is associated with a first narrower RX beam set of the UE. For example, at 1112, the UE 1102 may measure a metric of a PO beam subset of at least one PO beam subset of the plurality of PO beams received from the network node at 1108. In addition, 1312 may be performed by the L3 beam estimation component 198.

[0162] In one aspect, the PO beam subset may include a first PO beam subset, and the first narrower Rx beam set estimated using the ML model at 1324 may be estimated based on a metric of the first PO beam subset. Based on the estimated metric of the narrower Rx beam being greater than a threshold (e.g., a first threshold), the UE may stop measuring the PO beam subset and estimating the narrower Rx beam.

[0163] In another aspect, based on the metric of the narrower Rx beam estimated based on the first PO beam subset being less than or equal to the first threshold, the UE may measure the second PO beam subset, and may use the ML model at 1324 to estimate the second narrower Rx beam set based on the metrics of the first PO beam subset and the second PO beam subset.

[0164] At 1324, the UE may estimate the metric of the narrower Rx beam set using the ML model based on the metric of the PO beam subset. Here, the metric of the Rx beam may be estimated in each estimation cycle, each estimation cycle including the measurement of the metric of at least one PO beam subset and the search for at least one Rx beam. The UE may estimate the metric of the first Rx beam set using the ML model based on at least one coefficient received from the ML training server. For example, at 1124, the UE 1102 may estimate the metric of the narrower Rx beam set using the ML model based on the metric of the PO beam subset. In addition, 1324 may be performed by the L3 beam estimation component 198.

[0165] In one example, the narrower Rx beam set may be a first narrower Rx beam set estimated using an ML model based on the metrics of the first PO beam subset measured at 1312. In another example, the narrower Rx beam set may be a second narrower Rx beam set estimated using an ML model based on the metrics of the first PO beam subset and the second PO beam subset measured at 1312.

[0166] In another example, the narrower Rx beam set may be a third narrower Rx beam set estimated using an ML model based on a metric of a received third PO beam subset and based on the metric of the third PO subset being greater than a metric of the first PO beam subset by a second threshold.

[0167] At 1328, the UE may identify at least one best Rx beam from the narrower Rx beam set, the at least one best Rx beam being associated with the best estimated metric in the first narrower Rx beam set. In one example, the narrower Rx beam set may be a first narrower Rx beam set estimated using an ML model based on the metric of the first PO beam subset measured at 1312. In another example, the narrower Rx beam set may be a second narrower Rx beam set estimated using an ML model based on the metric of the first PO beam subset and the second PO beam subset measured at 1312. In another example, the narrower Rx beam set may include a third narrower Rx beam set estimated using an ML model at 1324 based on the metric of the measured third PO beam subset. For example, at 1128, the UE 1102 may identify at least one best Rx beam from the narrower Rx beam set, the at least one best Rx beam being associated with the best estimated metric in the first narrower Rx beam set. Furthermore, 1328 may be performed by the L3 beam estimation component 198 .

[0168] Fig.141400 is a flowchart of a wireless communication method. The method may be performed by a network entity (e.g., an ML training server 1106; device 1704). Here, the network entity may be an ML training server. The ML training server may obtain at least one coefficient of an ML model, and at least one coefficient of the ML model may be transmitted to a UE. The UE may configure the ML model for estimating a metric of a narrower Rx beam set. The network entity may receive at least a portion of a metric of a PO beam subset or an estimated metric of an Rx beam set from the UE, and the ML model training server may obtain at least one coefficient of an ML modem based on at least a portion of the metric of the PO beam subset or the estimated metric of the Rx beam set received from the UE.

[0169] At 1420, the network entity may obtain at least one coefficient of an ML model for estimating an RX beam set based on a metric of a PO beam subset. The at least one coefficient of the ML model may be obtained based on at least a portion of a metric of a PO beam subset or an estimated metric of an Rx beam set received from a UE (e.g., at 1426). That is, the ML training server may train the ML model using at least a portion of a metric of a PO beam subset or an estimated metric of an Rx beam set received from a UE, and generate at least one coefficient of an ML model for the UE. For example, at 1120, the network entity 1120 may obtain at least one coefficient of an ML model for estimating an RX beam set based on a metric of a PO beam subset. In addition, 1420 may be performed by an ML model training component 199.

[0170] At 1422, the network entity may send at least one coefficient associated with the ML model for the UE to estimate the metric of the Rx beam set using the ML model based on the at least one coefficient and the metric of the PO beam subset. The PO beam subset may include a first PO beam subset or a second PO beam subset received from the first network node, or a third PO beam subset received from the second network node. Here, the at least one coefficient received from the ML model training server may be based at least on the metric of the first PO beam subset or at least a portion of the estimated metric of the first Rx beam set. For example, at 1122, the ML training server 1106 may send at least one coefficient associated with the ML model for the UE 1102 to estimate the metric of the Rx beam set using the ML model based on the at least one coefficient and the metric of the PO beam subset. In addition, 1422 may be performed by the ML model training component 199.

[0171] At 1426, the network entity may receive at least a portion of the metric of the PO beam subset or the estimated metric of the Rx beam set from the UE. At least one coefficient of the ML model may be obtained at 1420 based on at least a portion of the metric of the PO beam subset or the estimated metric of the Rx beam set received from the UE. For example, at 1126, the ML training server 1106 may receive at least a portion of the metric of the PO beam subset or the estimated metric of the Rx beam set from the UE 1102. In addition, 1426 may be performed by the ML model training component 199.

[0172] In one example, the metric of the PO beam subset may be a first PO beam subset, and the narrower Rx beam set may include a first narrower Rx beam set estimated using an ML model based on the metric of the first PO beam subset. In another example, the metric of the PO beam subset may be a first PO beam subset and a second PO beam subset, and the narrower Rx beam set may include a second narrower Rx beam set estimated using an ML model based on the metric of the first PO beam subset and the second PO beam subset. In another example, the metric of the PO beam subset may be a third PO beam subset received from a second network node, and the narrower Rx beam set may include a third narrower Rx beam set estimated using an ML model based on the metric of the third PO beam subset.

[0173] Fig.15 1500 is a flowchart of a wireless communication method. The method may be performed by a network entity (e.g., ML training server 1106; device 1704). Here, the network entity may be an ML training server. The ML training server may obtain at least one coefficient of an ML model, and at least one coefficient of the ML model may be transmitted to a UE. The UE may configure the ML model for estimating a metric of a narrower Rx beam set. The network entity may receive at least a portion of a metric of a PO beam subset or an estimated metric of an Rx beam set from the UE, and the ML model training server may obtain at least one coefficient of an ML modem based on at least a portion of the metric of the PO beam subset or the estimated metric of the Rx beam set received from the UE.

[0174] At 1520, the network entity may obtain at least one coefficient of an ML model for estimating an RX beam set based on a metric of a PO beam subset. The at least one coefficient of the ML model may be obtained based on at least a portion of a metric of a PO beam subset or an estimated metric of an Rx beam set received from a UE (e.g., at 1526). That is, the ML training server may train the ML model using at least a portion of a metric of a PO beam subset or an estimated metric of an Rx beam set received from a UE, and generate at least one coefficient of an ML model for the UE. For example, at 1120, the network entity 1120 may obtain at least one coefficient of an ML model for estimating an RX beam set based on a metric of a PO beam subset. In addition, 1520 may be performed by an ML model training component 199.

[0175] At 1526, the network entity may receive at least a portion of the metric of the PO beam subset or the estimated metric of the Rx beam set from the UE. At least one coefficient of the ML model may be obtained at 1520 based on at least a portion of the metric of the PO beam subset or the estimated metric of the Rx beam set received from the UE. For example, at 1126, the ML training server 1106 may receive at least a portion of the metric of the PO beam subset or the estimated metric of the Rx beam set from the UE 1102. In addition, 1526 may be performed by the ML model training component 199.

[0176] In one example, the metric of the PO beam subset may be a first PO beam subset, and the narrower Rx beam set may include a first narrower Rx beam set estimated using an ML model based on the metric of the first PO beam subset. In another example, the metric of the PO beam subset may be a first PO beam subset and a second PO beam subset, and the narrower Rx beam set may include a second narrower Rx beam set estimated using an ML model based on the metric of the first PO beam subset and the second PO beam subset. In another example, the metric of the PO beam subset may be a third PO beam subset received from a second network node, and the narrower Rx beam set may include a third narrower Rx beam set estimated using an ML model based on the metric of the third PO beam subset.

[0177] Fig.161600 is a diagram illustrating an example of a hardware implementation for an apparatus 1604. The apparatus 1604 may be a UE, a component of a UE, or may implement UE functionality. In some aspects, the apparatus 1604 may include a cellular baseband processor 1624 (also referred to as a modem) coupled to one or more transceivers 1622 (e.g., a cellular RF transceiver). The cellular baseband processor 1624 may include on-chip memory 1624'. In some aspects, the apparatus 1604 may also include one or more subscriber identity module (SIM) cards 1620 and an application processor 1606 coupled to a secure digital (SD) card 1608 and a screen 1610. The application processor 1606 may include on-chip memory 1606'. In some aspects, the device 1604 may also include a Bluetooth module 1612, a WLAN module 1614, an SPS module 1616 (e.g., a GNSS module), one or more sensor modules 1618 (e.g., an atmospheric pressure sensor / altimeter; a motion sensor such as an inertial measurement unit (IMU), a gyroscope, and / or an accelerometer; light detection and ranging (LIDAR), radio-aided detection and ranging (RADAR), sound navigation and ranging (SONAR), a magnetometer, audio, and / or other technologies for positioning), an additional memory module 1626, a power source 1630, and / or a camera 1632. The Bluetooth module 1612, the WLAN module 1614, and the SPS module 1616 may include an on-chip transceiver (TRX) (or in some cases, only a receiver (RX)). The Bluetooth module 1612, the WLAN module 1614, and the SPS module 1616 may include their own dedicated antennas and / or communicate using antennas 1680. The cellular baseband processor 1624 communicates with the UE 104 and / or with the RU associated with the network entity 1602 through the transceiver 1622 via one or more antennas 1680. The cellular baseband processor 1624 and the application processor 1606 may each include a computer-readable medium / memory 1624', 1606', respectively. The additional memory module 1626 may also be considered as a computer-readable medium / memory. Each computer-readable medium / memory 1624', 1606', 1626 may be non-transitory. The cellular baseband processor 1624 and the application processor 1606 are each responsible for general processing, including executing software stored on a computer-readable medium / memory. The software enables the cellular baseband processor 1624 / application processor 1606 to perform the various functions described above when executed by the cellular baseband processor 1624 / application processor 1606. The computer-readable medium / memory can also be used to store data manipulated by the cellular baseband processor 1624 / application processor 1606 when executing the software.The cellular baseband processor 1624 / application processor 1606 may be a component of the UE 350 and may include the memory 360 and / or at least one of the TX processor 368, the RX processor 356, and the controller / processor 359. In one configuration, the device 1604 may be a processor chip (modem and / or application) and include only the cellular baseband processor 1624 and / or the application processor 1606, and in another configuration, the device 1604 may be the entire UE (e.g., see. Figure 3 350) and includes additional modules of device 1604.

[0178] As discussed above, component 198 is configured to: measure a metric of a first PO beam subset of at least one PO beam subset including a plurality of PO beams from a network node, each PO beam subset being configured to form a PO pattern, and the first PO beam subset being associated with a first narrower Rx beam set of the UE; estimate a metric of the first narrower Rx beam set using an ML model based on the metric of the PO beam subset; and identify at least one best Rx beam from the first narrower Rx beam set, the at least one best Rx beam being associated with the best estimated metric in the first narrower Rx beam set. Component 198 may be within the cellular baseband processor 1624, the application processor 1606, or both the cellular baseband processor 1624 and the application processor 1606. Component 198 may be one or more hardware components specifically configured to perform the process / algorithm, implemented by one or more processors configured to perform the process / algorithm, stored in a computer-readable medium for implementation by one or more processors, or some combination thereof. As shown, the device 1604 may include a variety of components configured for various functions. In one configuration, the device 1604 (and specifically, the cellular baseband processor 1624 and / or the application processor 1606) includes: a component for measuring a metric of a first PO beam subset of at least one PO beam subset including a plurality of PO beams from a network node, each PO beam subset being configured to form a PO pattern, and the first PO beam subset being associated with a first narrower Rx beam set of the UE; a component for estimating a metric of the first narrower Rx beam set using an ML model based on the metric of the PO beam subset; and a component for identifying at least one best Rx beam from the first narrower Rx beam set, the at least one best Rx beam being associated with a best estimated metric in the first narrower Rx beam set. In one configuration, the device 1604 (and in particular, the cellular baseband processor 1624 and / or the application processor 1606) further includes a component for communicating data with a network node using the at least one best Rx beam based on the estimated metric of the at least one best Rx beam being greater than a first threshold. In one configuration, the device 1604 (and in particular, the cellular baseband processor 1624 and / or the application processor 1606) further includes a component for reporting the metric of the first PO beam subset to the network node based on the estimated metric of the at least one Rx beam being greater than the first threshold. In one configuration, the device 1604 (and in particular, the cellular baseband processor 1624 and / or the application processor 1606) further includes a component for estimating a metric of a second PO beam subset of the at least one PO beam subset based on the estimated metric of the at least one best Rx beam being less than or equal to the first threshold, the first PO beam subset being associated with a second RX beam set.In one configuration, the device 1604 (and in particular, the cellular baseband processor 1624 and / or the application processor 1606) further includes a component for identifying at least one best Rx beam from the second Rx beam set, the at least one best Rx beam being associated with a best estimated metric in the second Rx beam set. In one configuration, the device 1604 (and in particular, the cellular baseband processor 1624 and / or the application processor 1606) further includes a component for reporting the metric of the first PO beam subset and the second PO beam subset to the network node based on the estimated metric of the second best Rx beam being greater than the first threshold. In one configuration, the device 1604 (and in particular, the cellular baseband processor 1624 and / or the application processor 1606) further includes a component for searching the first Rx beam set for the at least one best Rx beam associated with the best estimated metric. In one configuration, a metric of an Rx beam is estimated in each estimation cycle, and each estimation cycle includes measurement of a metric of at least one PO beam subset and a search for at least one Rx beam. In one configuration, the device 1604 (and specifically, the cellular baseband processor 1624 and / or the application processor 1606) also includes a component for starting a timer before measuring the metric of the first PO beam subset, wherein the metric of the first Rx beam set is estimated based on the expiration of the timer. In one configuration, the device 1604 (and specifically, the cellular baseband processor 1624 and / or the application processor 1606) also includes: a component for measuring a metric of a third PO beam subset from a neighboring network node, the third PO beam subset being associated with a third Rx beam set; and a component for using the ML model to estimate the metric of the third Rx beam set based on the metric of the third PO beam subset being greater than the metric of the first PO beam subset by a second threshold. In one configuration, the metric of the first Rx beam set is estimated using the ML model based on at least one coefficient and the metric of the PO beam subset. In one configuration, the device 1604 (and in particular, the cellular baseband processor 1624 and / or the application processor 1606) further includes a component for receiving at least one coefficient associated with the ML model, the metric of the first Rx beam set being estimated using the ML model based on the at least one coefficient and the metric of the PO beam subset. In one configuration, the device 1604 (and in particular, the cellular baseband processor 1624 and / or the application processor 1606) further includes a component for sending the metric of the first PO beam subset or at least a portion of the estimated metric of the first Rx beam set to an ML model training server, wherein the at least one coefficient received from the ML model training server is at least based on the metric of the first PO beam subset or the at least a portion of the estimated metric of the first Rx beam set.A means may be a component 198 of the apparatus 1604 configured to perform the functions recited by the means. As described above, the apparatus 1604 may include the TX processor 368, the RX processor 356, and the controller / processor 359. Thus, in one configuration, a means may be the TX processor 368, the RX processor 356, and / or the controller / processor 359 configured to perform the functions recited by the means.

[0179] Fig.171700 is a diagram illustrating an example of a hardware implementation for an apparatus 1704. The apparatus 1704 may be a server for ML training, a component of a server, or may implement server functionality. In some aspects, the apparatus 1604 may include a cellular baseband processor 1724 (also referred to as a modem) coupled to one or more transceivers 1722 (e.g., a cellular RF transceiver). The cellular baseband processor 1724 may include on-chip memory 1724'. In some aspects, the apparatus 1704 may also include one or more subscriber identity module (SIM) cards 1720 and an application processor 1706 coupled to a secure digital (SD) card 1708 and a screen 1710. The application processor 1706 may include on-chip memory 1706'. In some aspects, the device 1704 may also include a Bluetooth module 1712, a WLAN module 1714, an SPS module 1716 (e.g., a GNSS module), one or more sensor modules 1718 (e.g., an atmospheric pressure sensor / altimeter; a motion sensor such as an inertial measurement unit (IMU), a gyroscope, and / or an accelerometer; light detection and ranging (LIDAR), radio-aided detection and ranging (RADAR), sound navigation and ranging (SONAR), a magnetometer, audio, and / or other technologies for positioning), an additional memory module 1726, a power source 1730, and / or a camera 1732. The Bluetooth module 1712, the WLAN module 1714, and the SPS module 1716 may include an on-chip transceiver (TRX) (or in some cases, only a receiver (RX)). The Bluetooth module 1712, the WLAN module 1714, and the SPS module 1716 may include their own dedicated antennas and / or communicate using an antenna 1780. The cellular baseband processor 1724 communicates with the UE 104 and / or with the RU associated with the network entity 1702 through the transceiver 1722 via one or more antennas 1780. The cellular baseband processor 1724 and the application processor 1706 may each include a computer-readable medium / memory 1724', 1706', respectively. The additional memory module 1726 may also be considered as a computer-readable medium / memory. Each computer-readable medium / memory 1724', 1706', 1726 may be non-transitory. The cellular baseband processor 1724 and the application processor 1706 are each responsible for general processing, including executing software stored on a computer-readable medium / memory. The software enables the cellular baseband processor 1724 / application processor 1706 to perform the various functions described above when executed by the cellular baseband processor 1724 / application processor 1706. The computer-readable medium / memory can also be used to store data manipulated by the cellular baseband processor 1724 / application processor 1706 when executing the software.The cellular baseband processor 1724 / application processor 1706 may be a component of the server 310 and may include the memory 376 and / or at least one of the TX processor 316, the RX processor 370, and the controller / processor 375. In one configuration, the device 1704 may be a processor chip (modem and / or application) and only include the cellular baseband processor 1724 and / or the application processor 1706, and in another configuration, the device 1704 may be the entire UE (e.g., see. Figure 3 310) and includes additional modules of device 1704.

[0180] As discussed above, the ML model training component 199 is configured to obtain at least one coefficient of the ML model for estimating the RX beam set based on the metric of the PO beam subset, and transmit the at least one coefficient associated with the ML model for the UE to use the ML model to estimate the metric of the Rx beam set based on the at least one coefficient and the metric of the PO beam subset. The ML model training component 199 may be within the cellular baseband processor 1724, the application processor 1706, or both the cellular baseband processor 1724 and the application processor 1706. The ML model training component 199 may be one or more hardware components that are specifically configured to perform the process / algorithm, implemented by one or more processors configured to perform the process / algorithm, stored in a computer-readable medium for implementation by one or more processors, or some combination thereof. As shown, the device 1704 may include a variety of components configured for various functions. In one configuration, the device 1704 (and in particular, the cellular baseband processor 1724 and / or the application processor 1706) includes: a component for obtaining at least one coefficient of an ML model for estimating the RX beam set based on a metric of a PO beam subset; and a component for sending the at least one coefficient associated with the ML model for the UE to use the ML model to estimate the metric of the Rx beam set based on the at least one coefficient and the metric of the PO beam subset. In one configuration, the device 1604 (and in particular, the cellular baseband processor 1624 and / or the application processor 1606) also includes a component for receiving at least a portion of the metric of the PO beam subset or the estimated metric of the Rx beam set from the UE, wherein the at least one coefficient of the ML model is obtained based on at least a portion of the metric of the PO beam subset or the estimated metric of the Rx beam set received from the UE. The component can be the ML model training component 199 of the device 1704 configured to perform the functions recited by the component. As described above, the apparatus 1704 may include the TX processor 316, the RX processor 370, and the controller / processor 375. Thus, in one configuration, the components may be the TX processor 316, the RX processor 370, and / or the controller / processor 375 configured to perform the functions recited by the components.

[0181] According to some aspects of the present disclosure, a UE may be configured to: measure a metric of a first PO beam subset of at least one PO beam subset including a plurality of PO beams from a network node, each PO beam subset being configured to form a PO pattern, and the first PO beam subset being associated with a first narrower Rx beam set of the UE; estimate a metric of the first narrower Rx beam set using an ML model based on the metric of the PO beam subset; and identify at least one best Rx beam from the first narrower Rx beam set, the at least one best Rx beam being associated with the best estimated metric in the first narrower Rx beam set. The network node may be an ML training server, and may be configured to: obtain at least one coefficient of an ML model for estimating an RX beam set based on the metric of the PO beam subset; and send the at least one coefficient associated with the ML model for the UE to estimate the metric of the Rx beam set using the ML model based on the at least one coefficient and the metric of the PO beam subset.

[0182] It should be understood that the specific order or hierarchy of the blocks in the disclosed process / flowchart is merely an illustration of the exemplary method. It should be understood that the specific order or hierarchy of the blocks in the process / flowchart may be rearranged based on design preferences. Further, some blocks may be combined or omitted. The attached method claims provide the elements of the various blocks in a sample order, but are not limited to the specific order or hierarchy provided.

[0183] The foregoing description is provided to enable any person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects. Therefore, the claims are not limited to the various aspects described herein, but should be given the full scope consistent with the language claims. Unless otherwise specified, reference to an element in the singular form does not mean "one and only one", but "one or more". Terms such as "if", "when" and "while" do not mean a direct temporal relationship or reaction. That is, these phrases, such as "when ...", do not mean an immediate action in response to the occurrence of an action or during the occurrence of an action, but simply imply that if the conditions are met, the action will occur, but no specific or immediate time limit is required for the occurrence of the action. The word "exemplary" is used herein to mean "used as an example, instance, or illustration". Any aspect described as "exemplary" herein is not necessarily interpreted as being preferred or having advantages over other aspects. Unless otherwise specified, the term "some" refers to one or more. Combinations such as "at least one of A, B, or C", "one or more of A, B, or C", "at least one of A, B and C", "one or more of A, B, and C", and "A, B, C, or any combination thereof" include any combination of A, B, and / or C, which may include multiple A, multiple B, or multiple C. Specifically, combinations such as "at least one of A, B, or C", "one or more of A, B, or C", "at least one of A, B, and C", "one or more of A, B, and C", and "A, B, C, or any combination thereof" may be only A, only B, only C, A and B, A and C, B and C, or A and B and C, where any such combination may contain one or more members of A, B, or C. A set should be interpreted as a set of elements, where the number of elements is one or more. Thus, for a set of X, X will include one or more elements. If the first device receives data from the second device or sends data to the second device, the data may be directly received / sent between the first device and the second device, or indirectly received / sent between the first device and the second device through a collection of devices. All structural and functional equivalents of the elements throughout the various aspects described in this disclosure that are known or will later be known to a person of ordinary skill in the art are expressly incorporated herein by reference and are covered by the claims. In addition, nothing disclosed herein is intended to be dedicated to the public, regardless of whether such disclosure is explicitly stated in the claims. Words such as "module", "mechanism", "element", "device" cannot replace the word "component". Therefore, no claim element will be understood as a component plus function unless the element is explicitly stated using the phrase "component for..."

[0184] As used herein, the phrase "based on" should not be interpreted as referring to a closed set of information, one or more conditions, one or more factors, etc. In other words, the phrase "based on A" (where "A" can be information, a condition, a factor, etc.) should be interpreted as "based at least on A" unless specifically stated differently.

[0185] The following aspects are merely illustrative and may be combined with other aspects or teachings described herein without limitation.

[0186] Aspect 1 is a method for performing wireless communication at a UE, the method comprising: measuring a metric of a first PO beam subset among at least one PO beam subset including multiple PO beams from a network node, each PO beam subset being configured to form a PO pattern, and the first PO beam subset being associated with a first narrower RX beam set of the UE; estimating a metric of the first narrower Rx beam set using an ML model based on the metric of the PO beam subset; and identifying at least one best Rx beam from the first narrower Rx beam set, the at least one best Rx beam being associated with a best estimated metric in the first narrower Rx beam set.

[0187] Aspect 2 is a method according to aspect 1, the method further comprising: based on an estimated metric of the at least one best Rx beam being greater than a first threshold, using the at least one best Rx beam to communicate data with the network node.

[0188] Aspect 3 is a method according to any one of Aspects 1 and 2, and the method also includes: based on the estimated metric of the at least one Rx beam being greater than a first threshold, reporting the metric of the first PO beam subset to the network node.

[0189] Aspect 4 is a method according to any one of Aspects 1 to 3, the method further comprising: estimating a metric of a second PO beam subset among the at least one PO beam subset based on an estimated metric of the at least one optimal Rx beam being less than or equal to a first threshold, the first PO beam subset being associated with a second RX beam set.

[0190] Aspect 5 is a method according to aspect 4, the method further comprising: identifying at least one best Rx beam from the second Rx beam set, the at least one best Rx beam being associated with a best estimation metric in the second Rx beam set.

[0191] Aspect 6 is a method according to Aspect 5, and the method also includes: based on the estimated metric of the second best Rx beam being greater than the first threshold, reporting the metrics of the first PO beam subset and the second PO beam subset to the network node.

[0192] Aspect 7 is a method according to any one of aspects 1 to 6, the method further comprising: searching the first Rx beam set for the at least one best Rx beam associated with the best estimation metric.

[0193] Aspect 8 is a method according to Aspect 7, wherein the metric of the Rx beam is estimated in each estimation cycle, and each estimation cycle includes measurement of the metric of at least one PO beam subset and the search for the at least one Rx beam.

[0194] Aspect 9 is a method according to any one of Aspects 1 to 8, the method further comprising: starting a timer before measuring a metric of the first PO beam subset, wherein the metric of the first Rx beam set is estimated based on expiration of the timer.

[0195] Aspect 10 is a method according to any one of Aspects 1 to 9, the method further comprising: measuring a metric of a third PO beam subset from an adjacent network node, the third PO beam subset being associated with a third Rx beam set; and using the ML model to estimate the metric of the third Rx beam set based on the metric of the third PO beam subset being greater than the metric of the first PO beam subset by a second threshold.

[0196] Aspect 11 is a method according to any one of Aspects 1 to 10, wherein the metric of the first Rx beam set is estimated using the ML model based on at least one coefficient and the metric of the PO beam subset.

[0197] Aspect 12 is a method according to any one of Aspects 1 to 11, the method further comprising: receiving at least one coefficient associated with the ML model, the metric of the first Rx beam set being estimated using the ML model based on the at least one coefficient and the metric of the PO beam subset.

[0198] Aspect 13 is a method according to Aspect 12, and the method further includes: sending at least a part of the metric of the first PO beam subset or the estimated metric of the first Rx beam set to an ML model training server, wherein the at least one coefficient received from the ML model training server is at least based on the metric of the first PO beam subset or the at least a part of the estimated metric of the first Rx beam set.

[0199] Aspect 14 is an apparatus for wireless communication, the apparatus comprising: at least one processor, the at least one processor being coupled to a memory and configured to implement any one of aspects 1 to 13, the apparatus further comprising a transceiver coupled to the at least one processor.

[0200] Aspect 15 is an apparatus for wireless communication, the apparatus comprising means for implementing any one of aspects 1 to 13.

[0201] Aspect 16 is a non-transitory computer readable medium storing computer executable code, wherein the code, when executed by a processor, causes the processor to implement any one of aspects 1 to 13.

[0202] Aspect 17 is a method for performing wireless communications at a network entity, the method comprising: obtaining at least one coefficient of an ML model for estimating an RX beam set based on a measurement of a PO beam subset; and sending the at least one coefficient associated with the ML model for a UE to use the ML model to estimate the measurement of the Rx beam set based on the at least one coefficient and the measurement of the PO beam subset.

[0203] Aspect 18 is a method according to Aspect 17, the method further comprising: receiving at least a portion of a measurement of a PO beam subset or an estimated measurement of an Rx beam set from the UE, wherein at least one coefficient of the ML model is obtained based on the at least a portion of the measurement of the PO beam subset or the estimated measurement of the Rx beam set received from the UE.

[0204] Aspect 19 is an apparatus for wireless communication, the apparatus comprising at least one processor coupled to a memory and configured to implement any one of aspects 17 and 18, the apparatus further comprising a transceiver coupled to the at least one processor.

[0205] Aspect 20 is an apparatus for wireless communication, the apparatus comprising means for implementing any one of aspects 17 and 18.

[0206] Aspect 21 is a non-transitory computer readable medium storing computer executable code, wherein the code, when executed by a processor, causes the processor to implement any one of aspects 17 and 18.

Claims

1. An apparatus for wireless communication at a user equipment (UE), the apparatus comprising: Memory; and at least one processor coupled to the memory and based at least in part on the information stored in the memory, the at least one processor configured to: measuring a metric of a first pseudo omnidirectional (PO) beam subset of at least one PO beam subset including a plurality of PO beams from a network node, each PO beam subset being configured to form a PO pattern, and the first PO beam subset being associated with a first narrower receive (Rx) beam set of the UE; estimating a metric of the first set of narrower Rx beams using a machine learning (ML) model based on the metric of the PO beam subset; as well as At least one best Rx beam is identified from the first set of narrower Rx beams, the at least one best Rx beam being associated with a best estimated metric among the first set of narrower Rx beams.

2. The apparatus of claim 1 , wherein the at least one processor is further configured to: Based on the estimated metric of the at least one best Rx beam being greater than a first threshold, data is communicated with the network node using the at least one best Rx beam.

3. The apparatus of claim 1 , wherein the at least one processor is further configured to: Based on the estimated metric of the at least one Rx beam being greater than a first threshold, reporting the metric of the first PO beam subset to the network node.

4. The apparatus of claim 1 , wherein the at least one processor is further configured to: A metric of a second PO beam subset among the at least one PO beam subset is estimated based on the estimated metric of the at least one best Rx beam being less than or equal to a first threshold, the first PO beam subset being associated with a second RX beam set.

5. The apparatus of claim 4, wherein the at least one processor is further configured to: At least one best Rx beam is identified from the second Rx beam set, the at least one best Rx beam being associated with a best estimation metric in the second Rx beam set.

6. The apparatus of claim 5, wherein the at least one processor is further configured to: Based on the estimated metric of the second best Rx beam being greater than the first threshold, the metrics of the first PO beam subset and the second PO beam subset are reported to the network node.

7. The apparatus of claim 1, wherein the at least one processor is further configured to: The at least one best Rx beam associated with the best estimation metric is searched among the first Rx beam set.

8. The apparatus according to claim 7, wherein the metric of the Rx beam is estimated in each estimation cycle, each estimation cycle comprising measurement of the metric of at least one PO beam subset and the search for the at least one Rx beam.

9. The apparatus of claim 1, wherein the at least one processor is further configured to: starting a timer before measuring a metric of said first subset of PO beams, Wherein the metric of the first Rx beam set is estimated based on expiration of the timer.

10. The apparatus of claim 1, wherein the at least one processor is further configured to: measuring metrics of a third PO beam subset from a neighboring network node, the third PO beam subset being associated with a third Rx beam set; and Based on the metric of the third PO beam subset being greater than the metric of the first PO beam subset by a second threshold, the metric of the third Rx beam set is estimated using the ML model.

11. The apparatus of claim 1, wherein the metric of the first Rx beam set is estimated using the ML model based on at least one coefficient and the metric of the PO beam subset.

12. The apparatus of claim 1, wherein the at least one processor is further configured to: At least one coefficient associated with the ML model is received, and the metric of the first Rx beam set is estimated using the ML model based on the at least one coefficient and the metric of the PO beam subset.

13. The apparatus of claim 12, wherein the at least one processor is further configured to: Sending the metric of the first PO beam subset or at least a portion of the estimated metric of the first Rx beam set to an ML model training server, Wherein the at least one coefficient received from the ML model training server is based at least on the metric of the first PO beam subset or at least a portion of the estimated metric of the first Rx beam set.

14. An apparatus for wireless communication at a network entity, the apparatus comprising: Memory; and at least one processor coupled to the memory and based at least in part on the information stored in the memory, the at least one processor configured to: obtaining at least one coefficient of a machine learning (ML) model for estimating a set of receive (Rx) beams based on a metric of a subset of pseudo omnidirectional (PO) beams; as well as The at least one coefficient associated with the ML model is sent for a user equipment (UE) to estimate the metric of the Rx beam set using the ML model based on the at least one coefficient and the metric of the PO beam subset.

15. The apparatus of claim 14, wherein the at least one processor is further configured to: receiving, from the UE, at least a portion of a metric of a subset of PO beams or an estimated metric of a set of Rx beams, Wherein the at least one coefficient of the ML model is obtained based on the at least a portion of the metric of the PO beam subset or the estimated metric of the Rx beam set received from the UE.

16. A method of wireless communication at a user equipment (UE), the method comprising: measuring a metric of a first pseudo omnidirectional (PO) beam subset of at least one PO beam subset including a plurality of PO beams from a network node, each PO beam subset being configured to form a PO pattern, and the first PO beam subset being associated with a first narrower receive (Rx) beam set of the UE; estimating a metric of the first set of narrower Rx beams using a machine learning (ML) model based on the metric of the PO beam subset; as well as At least one best Rx beam is identified from the first set of narrower Rx beams, the at least one best Rx beam being associated with a best estimated metric among the first set of narrower Rx beams.

17. The method according to claim 16, further comprising: Based on the estimated metric of the at least one best Rx beam being greater than a first threshold, data is communicated with the network node using the at least one best Rx beam.

18. The method according to claim 16, further comprising: Based on the estimated metric of the at least one Rx beam being greater than a first threshold, reporting the metric of the first PO beam subset to the network node.

19. The method according to claim 16, further comprising: A metric of a second PO beam subset among the at least one PO beam subset is estimated based on the estimated metric of the at least one best Rx beam being less than or equal to a first threshold, the first PO beam subset being associated with a second RX beam set.

20. The method according to claim 19, further comprising: At least one best Rx beam is identified from the second Rx beam set, the at least one best Rx beam being associated with a best estimation metric in the second Rx beam set.

21. The method according to claim 20, further comprising: Based on the estimated metric of the second best Rx beam being greater than the first threshold, the metrics of the first PO beam subset and the second PO beam subset are reported to the network node.

22. The method according to claim 16, further comprising: The at least one best Rx beam associated with the best estimation metric is searched among the first Rx beam set.

23. The method of claim 22, wherein the metric of the Rx beam is estimated in each estimation cycle, each estimation cycle comprising measurement of the metric of at least one PO beam subset and the search for the at least one Rx beam.

24. The method according to claim 16, further comprising: starting a timer before measuring a metric of said first subset of PO beams, Wherein the metric of the first Rx beam set is estimated based on expiration of the timer.

25. The method according to claim 16, further comprising: measuring a metric of a third PO beam subset from a neighboring network node, the third PO beam subset being associated with a third Rx beam set; as well as Based on the metric of the third PO beam subset being greater than the metric of the first PO beam subset by a second threshold, the metric of the third Rx beam set is estimated using the ML model.

26. The method of claim 16, wherein the metric of the first Rx beam set is estimated using the ML model based on at least one coefficient and the metric of the PO beam subset.

27. The method according to claim 16, further comprising: At least one coefficient associated with the ML model is received, and the metric of the first Rx beam set is estimated using the ML model based on the at least one coefficient and the metric of the PO beam subset.

28. The method according to claim 27, further comprising: Sending the metric of the first PO beam subset or at least a portion of the estimated metric of the first Rx beam set to an ML model training server, Wherein the at least one coefficient received from the ML model training server is based at least on the metric of the first PO beam subset or at least a portion of the estimated metric of the first Rx beam set.

29. A method for wireless communication at a network entity, the method comprising: obtaining at least one coefficient of a machine learning (ML) model for estimating a set of receive (Rx) beams based on a metric of a subset of pseudo omnidirectional (PO) beams; as well as The at least one coefficient associated with the ML model is sent for a user equipment (UE) to estimate the metric of the Rx beam set using the ML model based on the at least one coefficient and the metric of the PO beam subset.

30. The method according to claim 29, further comprising: receiving, from the UE, at least a portion of a metric of a subset of PO beams or an estimated metric of a set of Rx beams, Wherein the at least one coefficient of the ML model is obtained based on the at least a portion of the metric of the PO beam subset or the estimated metric of the Rx beam set received from the UE.

Images