WO2025010733A1

WO2025010733A1 - Method for ue data collection for machine learning based beam management

Info

Publication number: WO2025010733A1
Application number: PCT/CN2023/107278
Authority: WO
Inventors: Yushu Zhang
Original assignee: Google LLC
Current assignee: Google LLC
Priority date: 2023-07-13
Filing date: 2023-07-13
Publication date: 2025-01-16
Anticipated expiration: 2026-01-13

Abstract

This disclosure provides systems, devices, apparatus, and methods, including computer programs encoded on storage media, for a UE to collect beam measurement data used for training, refinement, and monitoring of a machine learning model for beam management or beam prediction on the UE side. A signaling framework allows a network entity to configure the UE with parameters associated with data collection. A UE (102) receives (904), from a network entity (104), a signaling to configure a codebook for beams of a plurality of downlink reference signals configured for data collection associated with machine learning based beam prediction and feature parameters associated with the downlink reference signals. The UE (102) receives (910), from the network entity (104), the downlink reference signals based on the signaling. The UE (102) generates 912 beam quality data based on the received downlink reference signals, the beam quality data being associated with the data collection.

Description

METHOD FOR UE DATA COLLECTION FOR MACHINE LEARNING BASED BEAM MANAGEMENT

TECHNICAL FIELD

The present disclosure relates generally to wireless communication, and more particularly, to techniques for a user equipment (UE) to collect beam measurement data used for training, refinement, and monitoring of a machine learning model for beam management on the UE side.

BACKGROUND

The Third Generation Partnership Project (3GPP) specifies a radio interface referred to as fifth generation (5G) new radio (NR) (5G NR) . An architecture for a 5G NR wireless communication system includes a 5G core (5GC) network, a 5G radio access network (5G-RAN) , a user equipment (UE) , etc. The 5G NR architecture seeks to provide increased data rates, decreased latency, and/or increased capacity compared to prior generation cellular communication systems.

Wireless communication systems, in general, provide various telecommunication services (e.g., telephony, video, data, messaging, broadcasts, etc. ) based on multiple-access technologies, such as orthogonal frequency division multiple access (OFDMA) technologies, that support communication with multiple UEs. Improvements in mobile broadband continue the progression of such wireless communication technologies. For example, for beam management, a UE and a network entity may collaborate to identify and maintain the optimal or preferred beams for transmission in the uplink and downlink directions. Beam management may also be used to support beamforming at the network entity and/or the UE. Effective beam management is critical as the communication system provides increased capacity under different deployment scenarios.

BRIEF SUMMARY

The following presents a simplified summary of one or more aspects in order to provide a basic understanding of such aspects. This summary is not an extensive overview of all contemplated aspects. This summary neither identifies key or critical elements of all aspects nor delineates the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description that is presented later.

In beam management, a UE and a network entity may collaborate to identify and maintain the optimal or preferred beams for transmission in the uplink and downlink directions. Beam management may also be used to support beamforming at the network entity and/or the UE. For example, in the downlink direction, the network entity and the UE may perform beam management procedure in a hierarchical manner to identify a relatively wide beam for initial acquisition and then to identify more directional and higher gain beams for the physical downlink shared channel (PDSCH) and the physical downlink control channel (PDCCH) . Beam selection and refinement may be based on downlink reference signals such as the synchronization signal/physical broadcast channel (SS/PBCH) blocks (referred to as SSB) and channel state information reference signals (CSI-RS) configured as channel measurement resource (CMR) . The network entity may apply beamforming coefficients to a set of SSBs to generate relatively wide beams for initial acquisition by the UE. The network entity may then apply beam coefficients to a set of CSI-RS resources to generate more directional beams (e.g., narrower beams) for subsequent beam refinement. The UE may measure the downlink reference signals and provide feedback to the network entity in a CSI report to allow rapid and responsive switching between beams. The CSI report may include the SSB block resource indicator (SSBRI) or CSI-RS resource indicator (CRI) to indicate one or more preferred SSB or CSI-RS beams. The CSI report may also include the layer 1 reference signal received power (L1-RSRP) or layer 1 signal-to-interference plus noise ratio (L1-SINR) of the preferred SSB block or CSI-RS beams measured by the UE.

Machine learning may be used to aid beam management. For example, in spatial domain beam prediction, a machine learning model may predict one or more best downlink beams based on the beam quality measurements of a limited number of beams of the downlink reference signals such as CSI-RS resources configured as CMR. In temporal domain beam prediction, a machine learning model may predict one or more best downlink beams for multiple future time instances based on a limited number of beam quality measurements of the downlink reference signals made at different time instances in the past. One key step in machine learning is data collection, which is the collection of the input and output data used by the machine learning model for model training, model refinement, model monitoring, etc. The UE may collect the input and output data including the beam quality measurements and index (es) of the best beams. For example, the collected data may include one or more of the L1-RSRP, L1-SINR, SSBRI, or CRI.

A machine learning model for beam management may reside on the UE side. Data collection to support machine learning based beam management such as spatial domain and temporal domain beam prediction may need more functionalities than those provided by existing UE beam measurements. Data collection for machine learning based beam management also introduces other complexities. For example, the UE may perform receive beam sweeping to identify the best UE receive beam to receive the downlink reference signals for data collection. If the downlink reference signals overlap with other downlink signals in the time domain, the UE may face the issue of determining whether and how to receive the downlink reference signals to identify the best beams.

Aspects of the present disclosure address the complexities associated with collecting data by a UE to support machine learning based beam prediction performed on the UE side. In some aspects, a signaling framework is disclosed for the network entity to configure the UE with parameters associated with data collection. The parameters may include a beam codebook that identifies the beam patterns or beam shapes of the downlink reference signals, and/or feature such as time resources, frequency resources, power, time-domain behavior, etc., of the downlink reference signals. In some aspects, the network entity may configure an uplink resource for the UE to request downlink reference signals for data collection. The UE may use the configured uplink resource to request the downlink reference signals. In some aspects, the network entity may configure a measurement gap for the data collection associated with the machine learning based beam prediction. The UE may measure the downlink reference signals to collect data during the measurement gap when the downlink reference signals are shared between data collection for machine learning based beam prediction and beam measurements for other beam management functionalities. In some aspects, the UE may report information on its capability for data collection associated with UE-side machine learning based beam prediction for the network entity to configure the parameters based on the reported capability.

According to some aspects, a UE receives, from a network entity, a signaling to configure a codebook for beams of a plurality of downlink reference signals and feature parameters associated with the downlink reference signals. The downlink reference signals are configured for data collection associated with machine learning based beam prediction. The UE receives, from the network entity, the downlink reference signals based on the signaling. The UE generates beam quality data based on the downlink reference signals. The beam quality data are associated with the data collection.

According to some aspects, a network entity transmits, to a UE, a control signaling to configure a codebook for beams of a plurality of downlink reference signals and feature parameters associated with the downlink reference signals. The downlink reference signals are configured for data collection associated with machine learning based beam prediction by the UE. The network entity transmits, to the UE, the downlink reference signals based on the signaling.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 illustrates a diagram of a wireless communications system that includes a plurality of user equipment (UEs) and network entities in communication over one or more cells according to an embodiment.

FIG. 2 illustrates an example of a machine learning model predicting a set of best beams in the spatial domain based on beam quality measurements of a limited number of beams according to an embodiment.

FIG. 3 illustrates an example of a machine learning model predicting best beams in the temporal domain based on beam quality measurements from a number of time reporting instances according to an embodiment.

FIG. 4 is a signaling diagram illustrating communications between a UE and a network entity for the UE to collect data for supporting UE-side machine learning based beam prediction according to an embodiment.

FIG. 5 illustrates an example of a beam codebook for beams of the downlink reference signals configured for data collection by the UE with the beams indexed along the azimuth of departure (AoD) direction followed by the zenith of departure (ZoD) direction according to an embodiment.

FIG. 6 illustrates an example of a beam codebook for beams of the downlink reference signals configured for data collection by the UE with the beams indexed along the zenith of departure (ZoD) direction followed by the azimuth of departure (AoD) direction according to an embodiment.

FIG. 7 illustrates an example of a signaling sequence for the UE to request downlink reference signals for data collection and the response by the network entity according to an embodiment.

FIG. 8 illustrates an example of time-multiplexing operations of the UE between data collection to support machine learning beam prediction and other beam measurement operations when the downlink reference signals are shared between various beam management functionalities.

FIG. 9 is a flowchart of a method of wireless communication at a UE for receiving configuration information and downlink reference signals to collect data to support UE-side machine learning based beam prediction according to an embodiment.

FIG. 10 is a flowchart of a method of wireless communication at a network entity for transmitting configuration information and downlink reference signals to support UE-side machine learning based beam management according to an embodiment.

FIG. 11 is a diagram illustrating a hardware implementation for an example UE apparatus according to some embodiments.

FIG. 12 is a diagram illustrating a hardware implementation for one or more example network entities according to some embodiments.

DETAILED DESCRIPTION

FIG. 1 illustrates a diagram 100 of a wireless communications system associated with a plurality of cells 190 according to one embodiment. The wireless communications system includes user equipment (UEs) 102 and base stations/network entities 104. Some base stations may include an aggregated base station architecture and other base stations may include a disaggregated base station architecture. The aggregated base station architecture utilizes a radio protocol stack that is physically or logically integrated within a single radio access network (RAN) node. A disaggregated base station architecture utilizes a protocol stack that is physically or logically distributed among two or more units (e.g., radio unit (RU) 106, distributed unit (DU) 108, central unit (CU) 110) . For example, a CU 110 is implemented within a RAN node, and one or more DUs 108 may be co-located with the CU 110, or alternatively, may be geographically or virtually distributed throughout one or multiple other RAN nodes. The DUs 108 may be implemented to communicate with one or more RUs 106. Any of the RU 106, the DU 108 and the CU 110 can be implemented as virtual units, such as a virtual radio unit (VRU) , a virtual distributed unit (VDU) , or a virtual central unit (VCU) . The base station/network entity 104 (e.g., an aggregated base station or disaggregated units of the base station, such as the RU 106 or the DU 108) , may be referred to as a transmission reception point (TRP) .

Operations of the base station 104 and/or network designs may be based on aggregation characteristics of base station functionality. For example, disaggregated base station architectures are utilized in an integrated access backhaul (IAB) network, an open-radio access network (O-RAN) network, or a virtualized radio access network (vRAN) , which may also be referred to a cloud radio access network (C-RAN) . Disaggregation may include distributing functionality across the two or more units at various physical locations, as well as distributing functionality for at least one unit virtually, which can enable flexibility in network designs. The various units of the disaggregated base station architecture, or the disaggregated RAN architecture, can be configured for wired or wireless communication with at least one other unit. For example, the base stations 104d, 104e and/or the RUs 106a, 106b, 106c, 106d may communicate with the UEs 102a, 102b, 102c, 102d, and/or 102s via one or more radio frequency (RF) access links based on a Uu interface. In examples, multiple RUs 106 and/or base stations 104 may simultaneously serve the UEs 102, such as by intra-cell and/or inter-cell access links between the UEs 102 and the RUs 106/base stations 104.

The RU 106, the DU 108, and the CU 110 may include (or may be coupled to) one or more interfaces configured to transmit or receive information/signals via a wired or wireless transmission medium. For example, a wired interface can be configured to transmit or receive the information/signals over a wired transmission medium, such as via the fronthaul link 160 between the RU 106d and the baseband unit (BBU) 112 of the base station 104d associated with the cell 190d. The BBU 112 includes a DU 108 and a CU 110, which may also have a wired interface (e.g., midhaul link) configured between the DU 108 and the CU 110 to transmit or receive the information/signals between the DU 108 and the CU 110. In further examples, a wireless interface, which may include a receiver, a transmitter, or a transceiver, such as an RF transceiver, configured to transmit and/or receive the information/signals via the wireless transmission medium, such as for information communicated between the RU 106a of the cell 190a and the base station 104e of the cell 190e via cross-cell communication beams 136-138 of the RU 106a and the base station 104e.

The RUs 106 may be configured to implement lower layer functionality. For example, the RU 106 is controlled by the DU 108 and may correspond to a logical node that hosts RF processing functions, or lower layer PHY functionality, such as execution of fast Fourier transform (FFT) , inverse FFT (iFFT) , digital beamforming, physical random access channel (PRACH) extraction and filtering, etc. The functionality of the RU 106 may be based on the functional split, such as a functional split of lower layers.

The RUs 106 may transmit or receive over-the-air (OTA) communication with one or more UEs 102. For example, the RU 106b of the cell 190b communicates with the UE 102b of the cell 190b via a first set of communication beams 132 of the RU 106b and a second set of communication beams 134b of the UE 102b, which may correspond to inter-cell communication beams or, in some examples, cross-cell communication beams. For instance, the UE 102b of the cell 190b may communicate with the RU 106a of the cell 190a via a third set of communication beams 134a of the UE 102b and a fourth set of communication beams 136 of the RU 106a. DUs 108 can control both real-time and non-real-time features of control plane and user plane communications of the RUs 106.

Any combination of the RU 106, the DU 108, and the CU 110, or reference thereto individually, may correspond to a base station 104. Thus, the base station 104 may include at least one of the RU 106, the DU 108, or the CU 110. The base stations 104 provide the UEs 102 with access to a core network. The base stations 104 may relay communications between the UEs 102 and the core network (not shown) . The base stations 104 may be associated with macrocells for higher-power cellular base stations and/or small cells for lower-power cellular base stations. For example, the cell 190e may correspond to a macrocell, whereas the cells 190a-190d may correspond to small cells. Small cells include femtocells, picocells, microcells, etc. A network that includes at least one macrocell and at least one small cell may be referred to as a “heterogeneous network. ”

Transmissions from a UE 102 to a base station 104/RU 106 are referred to as uplink (UL) transmissions, whereas transmissions from the base station 104/RU 106 to the UE 102 are referred to as downlink (DL) transmissions. Uplink transmissions may also be referred to as reverse link transmissions and downlink transmissions may also be referred to as forward link transmissions. For example, the RU 106d utilizes antennas of the base station 104d of cell 190d to transmit a downlink/forward link communication to the UE 102d or receive an uplink/reverse link communication from the UE 102d based on the Uu interface associated with the access link between the UE 102d and the base station 104d/RU 106d.

Communication links between the UEs 102 and the base stations 104/RUs 106 may be based on multiple-input and multiple-output (MIMO) antenna technology, including spatial multiplexing, beamforming, and/or transmit diversity. The communication links may be associated with one or more carriers. The UEs 102 and the base stations 104/RUs 106 may utilize a spectrum bandwidth of Y MHz (e.g., 5, 10, 15, 20, 100, 400, 800, 1600, 2000, etc. MHz) per carrier allocated in a carrier aggregation of up to a total of Yx MHz, where x component carriers (CCs) are used for communication in each of the uplink and downlink directions. The carriers may or may not be adjacent to each other along a frequency spectrum. In examples, uplink and downlink carriers may be allocated in an asymmetric manner, with more or fewer carriers allocated to either the uplink or the downlink. A primary component carrier and one or more secondary component carriers may be included in the component carriers. The primary component carrier may be associated with a primary cell (PCell) and a secondary component carrier may be associated with a secondary cell (SCell) .

Some UEs 102, such as the UEs 102a and 102s, may perform device-to-device (D2D) communications over sidelink. For example, a sidelink communication/D2D link utilizes a spectrum for a wireless wide area network (WWAN) associated with uplink and downlink communications. Such sidelink/D2D communication may be performed through various wireless communications systems, such as wireless fidelity (Wi-Fi) systems, Bluetooth systems, Long Term Evolution (LTE) systems, New Radio (NR) systems, etc.

The UEs 102 and the base stations 104/RUs 106 may each include a plurality of antennas. The plurality of antennas may correspond to antenna elements, antenna panels, and/or antenna arrays that may facilitate beamforming operations. For example, the RU 106b transmits a downlink beamformed signal based on a first set of communication beams 132 to the UE 102b in one or more transmit directions of the RU 106b. The UE 102b may receive the downlink beamformed signal based on a second set of communication beams 134b from the RU 106b in one or more receive directions of the UE 102b. In a further example, the UE 102b may also transmit an uplink beamformed signal (e.g., sounding reference signal (SRS) ) to the RU 106b based on the second set of communication beams 134b in one or more transmit directions of the UE 102b. The RU 106b may receive the uplink beamformed signal from the UE 102b in one or more receive directions of the RU 106b. The UE 102b may perform beam training to determine the best receive and transmit directions for the beamformed signals. The transmit and receive directions for the UEs 102 and the base stations 104/RUs 106 may or may not be the same.

In further examples, beamformed signals may be communicated between a first base station/RU 106a and a second base station 104e. For instance, the base station 104e of the cell 190e may transmit a beamformed signal to the RU 106a based on the communication beams 138 in one or more transmit directions of the base station 104e. The RU 106a may receive the beamformed signal from the base station 104e of the cell 190e based on the RU communication beams 136 in one or more receive directions of the RU 106a. In further examples, the base station 104e transmits a downlink beamformed signal to the UE 102e based on the communication beams 138 in one or more transmit directions of the base station 104e. The UE 102e receives the downlink beamformed signal from the base station 104e based on UE communication beams 130 in one or more receive directions of the UE 102e. The UE 102e may also transmit an uplink beamformed signal to the base station 104e based on the UE communication beams 130 in one or more transmit directions of the UE 102e, such that the base station 104e may receive the uplink beamformed signal from the UE 102e in one or more receive directions of the base station 104e.

The base station 104 may include and/or be referred to as a network entity. That is, “network entity” may refer to the base station 104 or at least one unit of the base station 104, such as the RU 106, the DU 108, and/or the CU 110. The base station 104 may also include and/or be referred to as a next generation evolved Node B (ng-eNB) , a next generation NB (gNB) , an evolved NB (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 TRP, a network node, network equipment, or other related terminology. The base station 104 or an entity at the base station 104 can be implemented as an IAB node, a relay node, a sidelink node, an aggregated (monolithic) base station, or a disaggregated base station including one or more RUs 106, DUs 108, and/or CUs 110. A set of aggregated or disaggregated base stations may be referred to as a next generation-radio access network (NG-RAN) . In some examples, the UE 102a operates in dual connectivity (DC) with the base station 104e and the base station/RU 106a. In such cases, the base station 104e can be a master node and the base station/RU 160a can be a secondary node.

Still referring to FIG. 1, in certain aspects, any of the UEs 102 may include a data collection for UE-side machine learning based beam prediction component 140 (also referred to as ML data collection component 140) configured to collect data to support training, refinement, or monitoring of a UE-side machine learning model for downlink beam prediction. The ML data collection component 140 may receive from the base station/network entity 104 a control signaling to configure a codebook for beams of downlink reference signals configured for data collection associated with machine learning based beam prediction. The control signaling may also configure feature parameters associated with the downlink reference signals. The ML data collection component 140 may receive from the base station/network entity 104 the downlink reference signals based on the control signaling. The ML data collection component 140 may generate beam quality data based on the downlink reference signals. The beam quality data is associated with the data collection.

In certain aspects, any of the base stations 104 or a network entity of the base stations 104 may include a UE-side machine learning based beam prediction configuration component 150 (also referred to as ML data collection configuration component 150) configured to control UE data collection to support training, refinement, or monitoring of a UE-side machine learning model for downlink beam prediction. The ML data collection configuration component 150 may transmit to any of the UEs 102 a control signaling to configure a codebook for beams of downlink reference signals. The configured downlink reference signals are measured for data collection by the UEs 102 associated with machine learning based beam prediction on the UE side. The control signaling may also configure feature parameters associated with the downlink reference signals. The ML data collection configuration component 150 may transmit to the UEs 102 the downlink reference signals based on the control signaling.

Accordingly, FIG. 1 describes a wireless communication system that may be implemented in connection with aspects of one or more other figures described herein. Further, although the following description may be focused on 5G NR, the concepts described herein may be applicable to other similar areas, such as 5G-Advanced and future versions, LTE, LTE-advanced (LTE-A) , and other wireless technologies, such as 6G.

A machine learning model to support downlink beam management or prediction may reside on the network side or the UE side. The machine learning model may predict one or more best downlink beams in the spatial domain or the temporal domain based on a limited number of beam measurements of downlink reference signals configured as channel measurement resources (CMRs) . A network entity 104 may configure a UE 102 with a codebook for beams of the downlink reference signals. The network entity may also configure feature parameters associated with the downlink reference signals. The UE 102 may receive and measure the downlink reference signals based on the configuration. Training, refinement, or monitoring of the machine learning model may rely on data collection of beam measurements performed by the UE 102.

For example, when a machine learning model for beam prediction resides on the UE side, the UE 102 may receive the downlink reference signals in a range of azimuth and elevation (may also be referred to as zenith) angles as configured by the network entity 104. The UE 102 may collect beam quality measurements such as the L1-RSRP or L1-SINR of beams of the downlink reference signals to apply as input training data to the machine learning model. The UE 102 may determine one or more best beams based on the L1-RSRP or L1-SINR of the downlink reference signals to apply as output training data to the machine learning model. The best beams may be specified with the preferred azimuth and elevation angles. Once trained, the UE 102 may use the machine learning model to predict the best beams for downlink transmission of data or control signals based on a limited number of beam measurements of the downlink reference signals monitored by the UE 102. In one aspect, the UE 102 may transmit information on the predicted best beams to the network entity 104 for the network entity 104 to perform downlink beam management.

FIG. 2 illustrates an example 200 of a machine learning model 210 predicting a set of best beams 230 in the spatial domain based on beam quality measurements of a limited number of beams according to one embodiment. A network entity 104 may transmit the beams carrying downlink reference signals in the spatial domain to cover a range of azimuth angles of departure (AoD) and a zenith angles of departure (ZoD) . The downlink reference signals may be synchronization signal/physical broadcast channel (SS/PBCH) blocks (referred to as SSB) or channel state information reference signals (CSI-RS) configured as CMRs. FIG. 2 shows an array of four beams in the ZoD dimension and 8 beams in the AoD dimension for a total of 32 beams in the spatial domain. A UE 102 may measure the beam quality of four randomly selected beams 220 of the downlink reference signals instead of measuring all 32 beams to reduce computational load for beam management. The machine learning model 210 may apply the beam quality measurements of the four beams 220 to predict or infer a set of best beams 230 for downlink transmission. A subset of the best beams 230 may be used to transmit the physical downlink shared channel (PDSCH) and the physical downlink control channel (PDCCH) to the UE 102.

FIG. 3 illustrates an example 300 of a machine learning model 310 predicting the best beam or a set of best beams 360 in the temporal domain based on beam quality measurements from a number of time reporting instances according to one embodiment. A network entity 104 may transmit beams carrying downlink reference signals over a number of time instances, such as by periodically transmitting the beams over a time span. In one aspect, for each time instance, the network entity 104 may transmit multiple beams to cover a range of AoD and ZoD in the spatial domain. A UE 102 may make beam measurements 320, 330, 340 of the beams at three time instances. In one implementation, each beam measurement at a time instance may include beam quality measurements of the multiple beams corresponding to the time instance. The machine learning model 310 may apply beam quality measurements 320, 330, and 340 from the three time instances to predict or infer the best beams 350 and 360 for downlink transmission at two future time instances.

Aspects of the present disclosure address the complexities associated with data collection by a UE to support machine learning based beam prediction performed on the UE side. In some aspects, a signaling framework is disclosed for the network entity to configure the UE with parameters associated with data collection. The parameters may include a beam codebook that identifies the beam patterns or beam shapes of the downlink reference signals for data collection, and/or feature such as time resources, frequency resources, power, time-domain behavior, etc., of the downlink reference signals. The network entity may configure periodic, semi-persistent or aperiodic downlink reference signals for data collection. The downlink reference signals for data collection may be synchronization signal block (SSB) or channel state information reference signal (CSI-RS) .

In some aspects, the network entity may configure an uplink resource through which the UE may request the configured the downlink reference signals. The UE may use the configured uplink resource to request a subset of the downlink reference signals and their associated parameters such as the spatial, frequency, timing features, etc., of the downlink reference signals. The network entity may respond to the request by transmitting a trigger signal to trigger or activate a subset of the configured downlink reference signals for data collection. The network entity may then transmit at least one instances of the requested downlink reference signals.

In some aspects, the network entity may configure a measurement gap for the data collection associated with the machine learning based beam prediction. The UE may measure the downlink reference signals to collect data within the measurement gap when the downlink reference signals are shared between data collection for machine learning based beam prediction and beam measurements for other beam management functionalities, such as beam failure detection, radio link monitoring, beam report, pathloss measurement, etc. In some aspects, the UE may report information on its capability for data collection associated with UE-side machine learning based beam prediction. The network entity may configure the codebook and the other features parameters of the downlink reference signals based on the reported capability.

Advantageously, the techniques for data collection described herein may support model training, refinement, and monitoring of the machine learning model for beam management. The collected data may improve the performance and prediction accuracy of the machine learning model, allowing the network entity to select better beams to improve system performance.

FIG. 4 is a signaling diagram 400 illustrating communications between a UE 102 and a network entity 104 for the UE 102 to collect data for supporting UE-side machine learning based beam prediction according to an embodiment. The network entity 104 may correspond to a base station or a unit of a base station, such as the RU 106, the DU 108, the CU 110, etc.

The UE 102 may transmit 402, to the network entity 104, (or the network entity 104 may receive 402 from the UE 102) information on the UE’s capability (also referred to as assistance information) pertaining to supported, recommended, or preferred configuration for data collection for machine learning based beam prediction. In one implementation, the capability information may include at least one of: a preferred periodicity for the data collection; a minimum periodicity for the data collection; a maximum periodicity for the data collection; a preferred number of instances of the downlink reference signals for the data collection; a minimum number of instances of the downlink reference signals for the data collection; a maximum number of instances of the downlink reference signals for the data collection; a preferred interval between two consecutive instances of the downlink reference signals for the data collection; a minimum interval between two consecutive instances of the downlink reference signals for the data collection; a maximum interval between two consecutive instances of the downlink reference signals for the data collection; a preferred time-domain behavior of the downlink reference signals for the data collection, etc.

In one implementation, the UE 102 may report the recommended or preferred configurations for the data collection for beam prediction by a Radio Resource Control (RRC) message. For example, the UE 102 may report such information by a dedicated RRC message for data collection. In another example, the UE may report such information based on the extension of existing RRC message, e.g., UEAssistanceInformation. The network entity 104 may configure the data collection based on the UE’s capability information.

The network entity 104 may transmit 404, to the UE 102, (or the UE 102 may receive 404 from the network entity 104) control signaling to configure beam measurements of the downlink reference signals for data collection. The controlling signaling may configure a list of candidate downlink reference signals for data collection and a beam codebook for the beams that may be configured to transmit the candidate downlink reference signals. The network entity 104 may configure a candidate network beam by the beam codebook to transmit a candidate downlink reference signal. The beam codebook may configure at least one of: an azimuth angle of departure (AoD) and a zenith angle of departure (ZoD) corresponding to the beams; an angular span of the AoD and ZoD for the beams (e.g., a minimum and maximum AoD, a minimum and maximum ZoD) ; a number of the beams in a horizontal direction; a number of the beams in a vertical direction; a number of horizontal antenna ports; a number of vertical antenna ports; an oversampling factor for a number of the beams in a horizontal direction; an oversampling factor for a number of the beams in a vertical direction.

In one implementation, the number of beams in the horizontal/vertical direction may be a product of the number of horizontal/vertical antenna ports and the oversampling factor for the number of beams in the horizontal/vertical direction. Thus, the network entity 104 may configure either the number of beams or the oversampling factor in the horizontal/vertical direction for the UE 102 to derive the missing parameter based on the number of horizontal/vertical antenna ports. In one implementation, the network entity 104 may configure the AoD and ZoD for each beam. In one implementation, the network entity 104 may configure the angular span of the AoD and the angular span of the ZoD for the beams. The UE 102 may then determine the AoD and the ZoD for each beam based on the number of beams in the horizontal and vertical directions and the configured AoD/ZoD angular span.

In one implementation, when different beam patterns or beam shapes are associated with the input and output data used by the machine learning model for model training, model refinement, model monitoring, or other purposes, the network entity 104 may configure two beam codebooks and two lists of downlink reference signals for data collection. For example, the first beam codebook and the first list of downlink reference signals may be configured for data collection for model input and the second beam codebook and the second list of downlink reference signals may be configured for data collection for model output. In one implementation, the UE 102 may report information on its capability indicating the maximum number of supported beam codebooks and/or the maximum number of lists of downlink reference signals for data collection.

In one implementation, the network entity 104 may explicitly configure the beam pattern or beam shape for each downlink reference signal for data collection. In one implementation, the network entity 104 may configure the beam index for each downlink reference signal. The beam pattern or beam shape corresponding to each beam index may then be determined based on the configured beam codebook.

Referring now to FIG. 5 which illustrates an example 500 of a beam codebook for beams of the downlink reference signals configured for data collection by the UE with the beams 510 indexed along the azimuth of departure (AoD) direction followed by the zenith of departure (ZoD) direction according to an embodiment. For example, the first 8 beams are indexed [0, 1, 2, 3, 4, 5, 6, 7] along the azimuth direction at the lowest zenith angle; the next 8 beams are indexed [8, 9, 10, 11, 12, 13, 14, 15] along the azimuth direction at the next higher zenith angle, so and on. When the network entity 104 configures a candidate beam for a candidate downlink reference signal, the network entity 104 may configure the beam pattern corresponding to the candidate downlink reference signal based on the beam index [0, 1, …, 31] of the beam codebook.

Referring now to FIG. 6 which illustrates an example 600 of a beam codebook for beams of the downlink reference signals configured for data collection by the UE with the beams 610 indexed along the azimuth of departure (ZoD) direction followed by the azimuth of departure (AoD) direction according to an embodiment. For example, the first 4 beams are indexed [0, 1, 2, 3] along the zenith direction at the lowest azimuth angle; the next 4 beams are indexed [4, 5, 6, 7] along the zenith direction at the next higher azimuth angle, so and on. The network entity 104 may configure the beam pattern for a candidate downlink reference signal using the beam index [0, 1, …, 31] of the beam codebook.

Referring back to FIG. 4, the controlling signaling configuring a list of candidate downlink reference signals for data collection may configure the frequency resources, time resources, power, time-domain behavior, bandwidth, and other characteristics or features associated with the downlink reference signals. In one implementation, the network entity 104 may configure the time and frequency resource for each downlink reference signal for data collection. For example, the network entity 104 may configure the downlink reference signals within a slot or S slots, e.g., S=4, where the maximum value of S may be predefined or reported by the UE 102 via UE capability report.

In one implementation, the network entity 104 may configure a common or separate time-domain behavior for the downlink reference signals. The time-domain behavior may include the periodicity of the downlink reference signals when they are periodic or semi-persistent. In one implementation, the network entity 104 may refrain from configuring different time-domain behavior for the downlink reference signals. For example, the network entity 104 may refrain from configuring different periodicity for the downlink reference signals.

The time-domain behavior may also include the number of repetitions of the downlink reference signals and/or the interval between two consecutive repetitions of the downlink reference signals. In one implementation, the network entity 104 may configure a common or separate number of instances or repetitions for the downlink reference signals. In one implementation, the network entity 104 may refrain from configuring different number of instances or repetitions for the downlink reference signals. The network entity 104 may configure or indicate the number of instances or repetitions by RRC signaling, Medium Access Control (MAC) Control Element (CE) (MAC CE) , or Downlink Control Information (DCI) .

In one implementation, each downlink reference signal corresponding to a beam may be a CSI-RS resource set. The network entity 104 may configure a list of CSI-RS resources that are from the same antenna port (s) . In one example, the network entity 104 may configure the RRC parameter repetition to be ‘on’ for each CSI-RS resource set. The network entity 104 may transmit repetitions of the CSI-RS by applying the same beamforming to the CSI-RS corresponding to the CSI-RS resources of the CSI-RS resource set. Then the UE 102 may perform receive beam sweeping operation to receive the CSI-RS resources in the CSI-RS resource set to identify the best UE receive beam corresponding to the network beam of the CSI-RS resource set.

In one implementation, the network entity 104 may configure the downlink reference signals by a CSI report configuration (e.g., CSI-ReportConfig) without configuring the report quantity parameter (e.g., reportQuantity) , or with the report quantity parameters configured as ‘none. ’ In this case, the UE 102 does not provide the network entity 104 with a CSI report. For example, when the network entity 104 configures the RRC parameter repetition to be ‘on’ for a CSI-RS resource set for the UE 102 to perform receive beam sweeping operation to identify the best UE receive beam to receive the downlink reference signals, the network entity does not need knowledge of the receive beam selected by the UE 102.

In one implementation, the network entity 104 may configure the bandwidth part, the bandwidth part index, and/or the component carrier within a frequency band associated with the downlink reference signals. In one implementation, the network entity 104 may refrain from configuring different bandwidth part index for the downlink reference signals. In one implementation, the network entity 104 may configure a separate transmission power for each downlink reference signal or a common transmission power for all the downlink reference signals. In one implementation, the network entity 104 may configure the serving cell index (es) associated with the downlink reference signals. In one implementation, the network entity 104 may refrain from configuring different associated serving cell indexes for the downlink reference signals.

In one implementation, with regard to cross-cell data collection, the network entity 104 may configure the information on physical cell identifier (PCI) for each downlink reference signal. For example, the network entity 104 may configure the PCI associated with each downlink reference signal. In another example, the network entity 104 may configure a list of candidate PCIs by RRC signaling and may configure the associated index (es) of the candidate PCIs for each downlink reference signal. In one implementation, if the information on PCI is not provided, the UE 102 may assume the downlink reference signal is associated with the physical serving cell.

The UE 102 may transmit 406, to the network entity 104, (or network entity may receive 406 from the UE) a request for the configured downlink reference signals to trigger the data collection. In one implementation, the network entity 104 may configure an uplink resource for the UE 102 to make the request. The network entity 102 may further configure parameters associated with the UE-triggered data collection procedure. The parameters may include: a prohibit timer for use by the UE 102 to initiate the request; a maximum number of retransmissions of the request; a duration of the monitoring window for the UE 102 to monitor a response to the request; a retransmission interval between retransmissions of the request; a downlink resource for the UE 102 to receive a response to the request, etc. In one implementation, at least one of the parameters associated with the UE-triggered data collection procedure may be predefined.

In one implementation, the UE 102 may transmit a request for data collection if the configured prohibit timer counting down a wait interval from a trigger event or a timer counting down the configured retransmission interval between retransmissions of the request expires. In one implementation, the UE 102 may restart or reset the prohibit timer (e.g., trigger event) or the timer counting down the retransmission interval under one of the following conditions: the UE 102 receives the downlink reference signals for data collection or a triggering signal (e.g., a MAC CE or DCI) triggering the downlink reference signals for data collection; The UE 102 switches to another physical cell after a handover procedure or a low-layer triggered mobility procedure; the UE 102 activates a secondary cell (SCell) , where the SCell may correspond to a new frequency band or a new band combination; the UE 102 adds a primary secondary serving cell (PSCell) , where the PSCell may correspond to a new frequency band or a new band combination, etc.

In one implementation, the UE 102 may transmit the request if the prohibit timer expires and the downlink beam quality (e.g., layer 1 reference signal received power (L1-RSRP) or layer 1 signal-to-interference plus noise ratio (L1-SINR) ) of a previously measured downlink reference signal is above a threshold. In one implementation, the threshold may be predefined or configured by the network entity 104 via RRC signaling, MAC CE, or DCI. In one example, the UE 102 may measure the beam quality from the downlink reference signal indicated in one of the active transmission configuration indication (TCI) state, e.g., the first TCI state. In another example, the UE 102 may measure the beam quality from the downlink reference signal indicated in one TCI state configured or indicated by the network entity 102. In another example, the UE 102 may measure the beam quality from a set of downlink reference signals, and determine the beam quality based on the minimum, maximum, or average of the beam quality for the set of downlink reference signals. In one implementation, the downlink reference signals may be predefined, e.g., the downlink reference signals indicated in active TCI states or all the SSBs, or configured or indicated by the network entity 104 via RRC signaling, MAC CE, or DCI.

In one implementation, when the UE 102 transmit 406 a request for the configured downlink reference signals to trigger the data collection, the UE 102 may transmit at least one of the following information: a serving cell index associated with the downlink reference signals for data collection; a bandwidth part index associated with the downlink reference signals for data collection; beams or beam groups corresponding to the downlink reference signals (e.g., the beam index of the candidate network beam from the beam codebook corresponding to the downlink reference signals) ; a number of repetitions for the downlink reference signals for data collection; an interval between two consecutive repetitions of the downlink reference signals for data collection, etc.

In one implementation, for each request, the UE 102 may request the full beams in a beam codebook for data collection. Thus, the UE 102 may not request the beams or beam groups for individual downlink reference signals for data collection in the request. In one implementation, the UE 102 may request a subset of the beams for data collection, e.g., the beams around the beam for an SSB, e.g., SSB with the strongest beam quality.

In one implementation, the UE 102 may transmit the request by physical uplink control channel (PUCCH) . For example, the network entity 104 may configure at least one PUCCH resource for the request for data collection by RRC signaling. In one implementation, the UE 102 may transmit the request by MAC CE or RRC message via physical uplink shared channel (PUSCH) . In one implementation, the UE 102 may transmit a scheduling request (SR) by PUCCH if the UE did not receive an uplink grant for the PUSCH. The network entity 104 may configure the SR via RRC signaling. In one implementation, the UE 102 may transmit the request by PRACH. The network entity 104 may configure the UE 102 with different PRACH resources and the UE 102 may transmit the content of the request implicitly by selecting the corresponding PRACH resource.

The network entity 104 may transmit 408, to the UE 102, (or the UE 102 may receive 408 from the network entity 104) a response to the request for data collection such as a trigger for the downlink reference signals. In one implementation, after X slots or symbols from when the UE 102 transmits the first or last symbol of the request, the UE 102 may start the configured monitoring window to monitor the response from the network entity 104. The X interval may be predefined, e.g., X=0 or X=4, or configured by the network entity 104 via RRC signaling. The UE 102 may start or reset a monitoring timer for the configured monitoring window. If the UE 102 detects a response to the request, the UE 102 may stop or reset the monitoring timer. On the other hand, if the monitoring timer expires without detecting the response to the request, the UE 102 may retransmit the request if the number of retransmissions of the request is smaller than the configured maximum number of retransmissions of the request. In one implementation, the UE 102 may retransmit the request if the interval from the previous transmission satisfies the configured retransmission interval between consecutive retransmission of the request.

In one implementation, the network entity 104 may transmit the response via a physical downlink control channel (PDCCH) . For example, the network entity 104 may transmit the response via a PDCCH in a dedicated search space or control resource set configured by the network entity 104. In another example, the network entity 104 may transmit the response via a PDCCH scheduling the downlink reference signals for data collection. For example, for semi-persistent or aperiodic downlink reference signals, such as semi-persistent or aperiodic CSI-RS, the network entity 104 may transmit a MAC CE or DCI (e.g., in PDCCH) to trigger the downlink reference signals. In another example, the network entity may transmit the response via a PDCCH associated with a radio network temporary identifier (RNTI) configured by the network entity 104 or as predefined. In another example, the network entity 104 may transmit the response via a PDCCH scheduling a new transmission for the same HARQ process as the PUSCH containing the MAC CE for the data collection request.

In one implementation, the network entity 104 may transmit the response via MAC CE in PDSCH. For example, the network entity 104 may transmit the response as a MAC CE to activate or trigger the downlink reference signals for data collection. In another example, the network entity 104 may transmit the response as a dedicated MAC CE for the data collection response.

The network entity 104 may transmit 410, to the UE 102, (or the UE 102 may receive 410 from the network entity 104) the downlink reference signals for the UE 102 to perform the data collection.

The UE 102 may generate 412, beam quality data for the data collection based on the downlink reference signals. The beam quality data may include a layer-1 reference signal received power (L1-RSRP) for the downlink reference signals; a layer-1 signal-to-interference-plus-noise ratio (L1-SINR) for the downlink reference signals; or index (es) of the best beams (e.g., SSB block resource indicator (SSBRI) or CSI-RS resource indicator (CRI) ) .

FIG. 7 illustrates an example of a signaling sequence 700 for the UE 102 to request downlink reference signals for data collection and the response by the network entity 104 according to an embodiment. FIG. 7 shows an example of the UE 102 transmitting the request by MAC CE or RRC message via PUSCH.

The UE 102 may transmit a scheduling request (SR) by a PUCCH at time 710 to request an uplink grant for PUSCH that will be used to transmit the data collection request. The UE 102 may receive a PDCCH (e.g., uplink grant) scheduling the PUSCH at time 720. The UE 102 may transmit the data collection request by MAC CE or RRC message via the PUSCH at time 730. The data collection request may contain a request for M downlink reference signals with N repetitions of the M downlink reference signals for data collection. The M downlink reference signals may be a subset of the downlink reference signals configured by the network entity 104. The network entity 104 may have also configured the time-domain behavior of N repetitions of the M downlink reference signals.

The UE 102 may receive a response to the data collection request via a PDCCH or a PDSCH at time 740. The response may contain a MAC CE to activate or trigger the M downlink reference signals configured for data collection. Based on the configured time-domain behavior for the N repetitions of the downlink reference signals, the UE 102 may receive a first instance of the M downlink reference signals for data collection at time 750, a second instance of the M downlink reference signals for data collection at time 760 and so on until receiving an N^th instance of the M downlink reference signals at time 770.

In one implementation, the downlink reference signals may be used for beam management functionalities other than for data collection to support machine learning based beam prediction, e.g., beam failure detection (BFD) , radio link monitoring (RLM) , beam report, pathloss measurement, etc. In one implementation, the network entity 104 may further configure a measurement gap for the data collection associated with the machine learning based beam prediction (e.g., a measurement window for the data collection associated with the machine learning based beam prediction) within which the UE may measure the downlink reference signals for data collection. In one implementation, the network entity 104 may configure the time instance (s) of the downlink reference signals at which the UE 102 may perform the measurement for data collection.

In one implementation, the network entity 104 may configure the periodicity, slot offset and/or duration of the measurement gap or the time instance (s) for measuring the downlink reference signals for data collection. The UE 102 may only receive the downlink reference signals for data collection within the configured measurement gap or at the configured time instance (s) . The UE 102 may refrain from receiving other downlink signals within the configured measurement gap or at the configured time instance (s) . In one implementation, the UE 102 may refrain from transmitting uplink signals within the configured measurement gap or at the configured time instance (s) . In one implementation, the measurement gap or time instance (s) may be applicable for one serving cell. In one implementation, the measurement gap or time instance (s) may be applicable for a list of serving cells, where the serving cell lists may be configured by the network entity 104, reported by the UE 102, or may be predefined, e.g., serving cells within a band.

In one implementation, the time instances of the downlink reference signals configured for the measurement for data collection may not be counted as the time instances used for other functionalities. In this scenario, the UE 102 may determine the number of time instances of the downlink reference signals used for other functionalities based on the number of time instances not used for data collection. In one implementation, the UE 102 may determine the action delay for transmission configuration indicator (TCI) switching or activation, or the delay for pathloss measurement based on the number of time instances of the downlink reference signals other than those used for data collection. In one implementation, the interval for BFD and/or RLM may be extended if some of the time instances of the downlink reference signals are used for data collection.

FIG. 8 illustrates an example of time-multiplexing operations 800 of the UE 102 between data collection to support machine learning beam prediction and other beam measurement operations when the downlink reference signals are shared between various beam management functionalities. In FIG. 8, the downlink reference signals are shared between data collection for machine learning beam prediction 810 and pathloss measurement 820. The pathloss measurement may be configured based on receiving five time instances of the downlink reference signals.

If data collection for machine learning based beam prediction is disabled, the delay 850 for the pathloss measurement functionality may be represented by the time interval for receiving the first five downlink reference signals (871, 872, 873, 874, 875) . However, if data collection for machine learning based beam prediction is enabled, four downlink reference signals (871, 872, 876, 877) may be configured for data collection 810 and five downlink reference signals (873, 874, 875, 878, 879) may be configured for pathloss measurement 820. Due to time-multiplexing of the downlink reference signals between the two operations, the delay 860 for the pathloss measurement functionality may be stretched to encompass the time interval for all nine downlink reference signals.

In one implementation, the UE 102 may report the UE capability indicating whether it supports data collection for machine learning based beam prediction and for other beam management functionalities, e.g., BFD, RLM, pathloss measurement, L1-RSRP, L1-SINR measurement, for instances of the downlink reference signal.

In one implementation, the network entity 104 may configure dedicated downlink reference signals for data collection. For the symbols with the dedicated downlink reference signals for data collection, the UE 102 may only receive the downlink reference signals. Thus, the UE 102 may refrain from receiving other downlink signals. In one implementation, the UE 102 may refrain from receiving other downlink signals in the same serving cell. In one implementation, the UE 102 may refrain from receiving other downlink signals from a serving cell in a list of serving cells containing the serving cell with the downlink reference signal for data collection. The serving cell lists may be configured by the network entity104, reported by the UE 102, or may be predefined, e.g., serving cells within a frequency band.

FIGs. 9-10 show methods for implementing one or more aspects of FIGs. 2-8. In particular, FIG. 9 shows an implementation by the UE 102 of the one or more aspects of FIGs. 2-8. FIG. 10 shows an implementation by the network entity 104 of the one or more aspects of FIGs. 2-8.

FIG. 9 is a flowchart of a method 900 of wireless communication at a UE for receiving configuration information and downlink reference signals to collect data to support UE-side machine learning based beam prediction according to an embodiment. With reference to FIGs. 1, 4, and 11, the method may be performed by the UE 102, the UE apparatus 1102, etc., which may include the memory 1126', 1106', 1116, and which may correspond to the entire UE 102 or the entire UE apparatus 1102, or a component of the UE 102 or the UE apparatus 1102, such as the wireless baseband processor 1126 and/or the application processor 1106.

The UE transmits 902, to a network entity, UE capability information on supported configuration for data collection associated with machine learning based beam prediction. For example, referring to FIG. 4, the UE 102 transmits 402, to the network entity 104, information on the UE’s capability (also referred to as assistance information) pertaining to supported, recommended, or preferred configuration for data collection for machine learning based beam prediction. In one implementation, the capability information may include at least one of: a preferred periodicity for the data collection; a minimum periodicity for the data collection; a maximum periodicity for the data collection; a preferred number of instances of the downlink reference signals for the data collection; a minimum number of instances of the downlink reference signals for the data collection; a maximum number of instances of the downlink reference signals for the data collection; a preferred interval between two consecutive instances of the downlink reference signals for the data collection; a minimum interval between two consecutive instances of the downlink reference signals for the data collection; a maximum interval between two consecutive instances of the downlink reference signals for the data collection; a preferred time-domain behavior of the downlink reference signals for the data collection, etc.

The UE receives 904, from the network entity, a signaling to configure a codebook for beams of a plurality of downlink reference signals configured for data collection associated with machine learning based beam prediction and feature parameters associated with the downlink reference signals. For example, referring to FIG. 4, the UE 102 receives 404, from the network entity 104, control signaling to configure beam measurements of the downlink reference signals for data collection. The controlling signaling may configure a list of candidate downlink reference signals for data collection and a beam codebook for the beams that may be configured for the candidate downlink reference signals. The controlling signaling may configure a candidate network beam by the beam codebook for a candidate downlink reference signal. The beam codebook may configure at least one of: an AoD and ZoD corresponding to the beams; an angular span of the AoD and ZoD for the beams (e.g., a minimum and maximum AoD, a minimum and maximum ZoD) ; a number of the beams in a horizontal direction; a number of the beams in a vertical direction; a number of horizontal antenna ports; a number of vertical antenna ports; an oversampling factor for a number of the beams in a horizontal direction; an oversampling factor for a number of the beams in a vertical direction.

The UE transmits 906, to the network entity, a request for the downlink reference signals. For example, referring to FIG. 4, the UE 102 transmits 406, to the network entity 104, a request for the configured downlink reference signals to trigger the data collection. In one implementation, the UE 102 may transmit at least one of the following information: a serving cell index associated with the downlink reference signals for data collection; a bandwidth part index associated with the downlink reference signals for data collection; beams or beam groups corresponding to the downlink reference signals (e.g., the beam index of the candidate network beam from the beam codebook corresponding to the downlink reference signals) ; a number of repetitions for the downlink reference signals for data collection; an interval between two consecutive repetitions of the downlink reference signals for data collection, etc.

The UE receives 908, from the network entity, a response to the request. For example, referring to FIG. 4, the UE 102 receives 408, from the network entity 104, a response to the request for data collection such as a trigger for the downlink reference signals. In one implementation, the response may be received via a PDCCH. For example, for semi-persistent or aperiodic downlink reference signals, such as semi-persistent or aperiodic CSI-RS, UE 102 may receive a MAC CE or DCI to trigger the downlink reference signals. In one implementation, the response may be received via MAC CE in PDSCH to activate or trigger the downlink reference signals for data collection.

The UE receives 910, from the network entity, the downlink reference signals based on the signaling. For example, referring to FIG. 4, the UE 102 receives 410, from the network entity 104, the downlink reference signals for the UE 102 to perform the data collection. The downlink reference signals may be SSB and/or CSI-RS.

The UE generates 912 beam quality data based on the received downlink reference signals. The beam quality data is associated with the data collection. For example, referring to FIG. 4, the UE 102 generates 412 beam quality data for the data collection based on the downlink reference signals. The beam quality data may include a L1-RSRP for the downlink reference signals; a L1-SINR for the downlink reference signals; or index (es) of the best beam (s) (e.g., SSBRI or CRI) .

FIG. 9 describes a method from a UE-side of a wireless communication link, whereas FIG. 10 describes a method from a network-side of the wireless communication link.

FIG. 10 is a flowchart of a method 1000 of wireless communication at a network entity for transmitting configuration information and downlink reference signals to support UE-side machine learning based beam management according to an embodiment. With reference to FIGs. 1, 4, and 12, the method may be performed by one or more network entities 104, which may correspond to a base station or a unit of the base station, such as the RU 106, the DU 108, the CU 110, an RU processor 1206, a DU processor 1226, a CU processor 1246, etc. The one or more network entities 104 may include memory 1206’/1226’/1246’ , which may correspond to an entirety of the one or more network entities 104, or a component of the one or more network entities 104, such as the RU processor 1206, the DU processor 1226, or the CU processor 1246.

The network entity receives 1002, from a UE, UE capability information on supported configuration for data collection associated with machine learning based beam prediction. For example, referring to FIG. 4, the network entity 104 receives 402, from the UE 102, information on the UE’s capability (also referred to as assistance information) pertaining to supported, recommended, or preferred configuration for data collection for machine learning based beam prediction. In one implementation, the capability information may include at least one of: a preferred periodicity for the data collection; a minimum periodicity for the data collection; a maximum periodicity for the data collection; a preferred number of instances of the downlink reference signals for the data collection; a minimum number of instances of the downlink reference signals for the data collection; a maximum number of instances of the downlink reference signals for the data collection; a preferred interval between two consecutive instances of the downlink reference signals for the data collection; a minimum interval between two consecutive instances of the downlink reference signals for the data collection; a maximum interval between two consecutive instances of the downlink reference signals for the data collection; a preferred time-domain behavior of the downlink reference signals for the data collection, etc.

The network entity transmits 1004, to the UE, a signaling to configure a codebook for beams of a plurality of downlink reference signals configured for data collection associated with machine learning based beam prediction and feature parameters associated with the downlink reference signals. For example, referring to FIG. 4, the network entity 104 transmits 404, to the UE 102, control signaling to configure beam measurements of the downlink reference signals for data collection. The controlling signaling may configure a list of candidate downlink reference signals for data collection and a beam codebook for the beams that may be configured for the candidate downlink reference signals. The controlling signaling may configure a candidate network beam by the beam codebook for a candidate downlink reference signal. The beam codebook may configure at least one of: an AoD and ZoD corresponding to the beams; an angular span of the AoD and ZoD for the beams (e.g., a minimum and maximum AoD, a minimum and maximum ZoD) ; a number of the beams in a horizontal direction; a number of the beams in a vertical direction; a number of horizontal antenna ports; a number of vertical antenna ports; an oversampling factor for a number of the beams in a horizontal direction; an oversampling factor for a number of the beams in a vertical direction.

The network entity receives 1006, from the UE, a request for the downlink reference signals. For example, referring to FIG. 4, the network entity 104 receives 406, from the UE 102, a request for the configured downlink reference signals to trigger the data collection. In one implementation, the request may include at least one of the following information: a serving cell index associated with the downlink reference signals for data collection; a bandwidth part index associated with the downlink reference signals for data collection; beams or beam groups corresponding to the downlink reference signals (e.g., the beam index of the candidate network beam from the beam codebook corresponding to the downlink reference signals) ; a number of repetitions for the downlink reference signals for data collection; an interval between two consecutive repetitions of the downlink reference signals for data collection, etc.

The network entity transmits 1008, to the UE, a response to the request. For example, referring to FIG. 4, the network entity 104 transmits 408, to the UE 102, a response to the request for data collection such as a trigger for the downlink reference signals. In one implementation, the network entity 104 may transmit the response via a PDCCH. For example, for semi-persistent or aperiodic downlink reference signals, such as semi-persistent or aperiodic CSI-RS, the network entity 104 may transmit a MAC CE or DCI (e.g., in PDCCH) to trigger the downlink reference signals. In one implementation, the network entity 104 may transmit the response via MAC CE in PDSCH to activate or trigger the downlink reference signals for data collection.

The network entity transmits 1010, to the UE, the downlink reference signals based on the signaling. For example, referring to FIG. 4, the network entity 104 transmits 410, to the UE 102, the downlink reference signals for the UE 102 to perform the data collection. The downlink reference signals may be SSB and/or CSI-RS.

A UE apparatus 1102, as described in FIG. 11, may perform the method of flowchart 900 of FIG. 9. The one or more network entities 104, as described in FIG. 12, may perform the method of flowchart 1000 of FIG. 10.

FIG. 11 is a diagram 1100 illustrating a hardware implementation for an example UE apparatus 1102 according to some embodiments. The UE apparatus 1102 may be the UE 102, a component of the UE 102, or may implement UE functionality. The UE apparatus 1102 may include an application processor 1106, which may have on-chip memory 1106’ . In examples, the application processor 1106 may be coupled to a secure digital (SD) card 1108 and/or a display 1110. The application processor 1106 may also be coupled to a sensor (s) module 1112, a power supply 1114, an additional module of memory 1116, a camera 1118, and/or other related components. For example, the sensor (s) module 1112 may control a barometric pressure sensor/altimeter, a motion sensor such as an inertial management unit (IMU) , a gyroscope, accelerometer (s) , a light detection and ranging (LIDAR) device, a radio-assisted detection and ranging (RADAR) device, a sound navigation and ranging (SONAR) device, a magnetometer, an audio device, and/or other technologies used for positioning.

The UE apparatus 1102 may further include a wireless baseband processor 1126, which may be referred to as a modem. The wireless baseband processor 1126 may have on-chip memory 1126'. Along with, and similar to, the application processor 1106, the wireless baseband processor 1126 may also be coupled to the sensor (s) module 1112, the power supply 1114, the additional module of memory 1116, the camera 1118, and/or other related components. The wireless baseband processor 1126 may be additionally coupled to one or more subscriber identity module (SIM) card (s) 1120 and/or one or more transceivers 1130 (e.g., wireless RF transceivers) .

Within the one or more transceivers 1130, the UE apparatus 1102 may include a Bluetooth module 1132, a WLAN module 1134, an SPS module 1136 (e.g., GNSS module) , and/or a cellular module 1138. The Bluetooth module 1132, the WLAN module 1134, the SPS module 1136, and the cellular module 1138 may each include an on-chip transceiver (TRX) , or in some cases, just a transmitter (TX) or just a receiver (RX) . The Bluetooth module 1132, the WLAN module 1134, the SPS module 1136, and the cellular module 1138 may each include dedicated antennas and/or utilize antennas 1140 for communication with one or more other nodes. For example, the UE apparatus 1102 can communicate through the transceiver (s) 1130 via the antennas 1140 with another UE (e.g., sidelink communication) and/or with a network entity 104 (e.g., uplink/downlink communication) , where the network entity 104 may correspond to a base station or a unit of the base station, such as the RU 106, the DU 108, or the CU 110.

The wireless baseband processor 1126 and the application processor 1106 may each include a computer-readable medium/memory 1126', 1106', respectively. The additional module of memory 1116 may also be considered a computer-readable medium/memory. Each computer-readable medium/memory 1126', 1106', 1116 may be non-transitory. The wireless baseband processor 1126 and the application processor 1106 may each be responsible for general processing, including execution of software stored on the computer-readable medium/memory 1126', 1106', 1116. The software, when executed by the wireless baseband processor 1126/application processor 1106, causes the wireless baseband processor 1126/application processor 1106 to perform the various functions described herein. The computer-readable medium/memory may also be used for storing data that is manipulated by the wireless baseband processor 1126/application processor 1106 when executing the software. The wireless baseband processor 1126/application processor 1106 may be a component of the UE 102. The UE apparatus 1102 may be a processor chip (e.g., modem and/or application) and include just the wireless baseband processor 1126 and/or the application processor 1106. In other examples, the UE apparatus 1102 may be the entire UE 102 and include the additional modules of the apparatus 1102.

As discussed in FIG. 1 and implemented with respect to FIG. 11, a data collection for UE-side machine learning based beam prediction component 140 (also referred to as ML data collection component 140) is configured to collect data to support training, refinement, or monitoring of a UE-side machine learning model for downlink beam prediction. The ML data collection component 140 may receive from the base station/network entity 104 a control signaling to configure a codebook for beams of downlink reference signals configured for data collection associated with machine learning based beam prediction. The control signaling may also configure feature parameters associated with the downlink reference signals. The ML data collection component 140 may receive from the base station/network entity 104 the downlink reference signals based on the control signaling. The ML data collection component 140 may generate beam quality data based on the downlink reference signals. The beam quality data is associated with the data collection.

The ML data collection component 140 may be within the application processor 1106 (e.g., at 140a) , the wireless baseband processor 1126 (e.g., at 140b) , or both the application processor 1106 and the wireless baseband processor 1126. The ML data collection component 140a-140b may be one or more hardware components specifically configured to carry out the stated processes/algorithm, implemented by one or more processors configured to perform the stated processes/algorithm, stored within a computer-readable medium for implementation by the one or more processors, or a combination thereof.

FIG. 12 is a diagram 1200 illustrating a hardware implementation for one or more example network entities 104 according to some embodiments. The one or more network entities 104 may be a base station, a component of a base station, or may implement base station functionality. The one or more network entities 104 may include, or may correspond to, at least one of the RU 106, the DU, 108, or the CU 110. The CU 110 may include a CU processor 1246, which may have on-chip memory 1246'. In some aspects, the CU 110 may further include an additional module of memory 1256 and/or a communications interface 1248, both of which may be coupled to the CU processor 1246. The CU 110 can communicate with the DU 108 through a midhaul link 162, such as an F1 interface between the communications interface 1248 of the CU 110 and a communications interface 1228 of the DU 108.

The DU 108 may include a DU processor 1226, which may have on-chip memory 1226'. In some aspects, the DU 108 may further include an additional module of memory 1236 and/or the communications interface 1228, both of which may be coupled to the DU processor 1226. The DU 108 can communicate with the RU 106 through a fronthaul link 160 between the communications interface 1228 of the DU 108 and a communications interface 1208 of the RU 106.

The RU 106 may include an RU processor 1206, which may have on-chip memory 1206'. In some aspects, the RU 106 may further include an additional module of memory 1216, the communications interface 1208, and one or more transceivers 1230, all of which may be coupled to the RU processor 1206. The RU 106 may further include antennas 1240, which may be coupled to the one or more transceivers 1230, such that the RU 106 can communicate through the one or more transceivers 1230 via the antennas 1240 with the UE 102.

The on-chip memory 1206', 1226', 1246'a nd the additional modules of memory 1216, 1236, 1256 may each be considered a computer-readable medium/memory. Each computer-readable medium/memory may be non-transitory. Each of the processors 1206, 1226, 1246 is responsible for general processing, including execution of software stored on the computer-readable medium/memory. The software, when executed by the corresponding processor (s) 1206, 1226, 1246 causes the processor (s) 1206, 1226, 1246 to perform the various functions described herein. The computer-readable medium/memory may also be used for storing data that is manipulated by the processor (s) 1206, 1226, 1246 when executing the software. In examples, the UE-side machine learning based beam prediction configuration component 150 may sit at any of the one or more network entities 104, such as at the CU 110; both the CU 110 and the DU 108; each of the CU 110, the DU 108, and the RU 106; the DU 108; both the DU 108 and the RU 106; or the RU 106.

As discussed in FIG. 1 and implemented with respect to FIG. 12, the UE-side machine learning based beam prediction configuration component 150 (also referred to as ML data collection configuration component 150) is configured to control UE data collection to support training, refinement, or monitoring of a UE-side machine learning model for downlink beam prediction. The ML data collection configuration component 150 may transmit to any of the UEs 102 a control signaling to configure a codebook for beams of downlink reference signals. The configured downlink reference signals are measured for data collection by the UEs 102 associated with machine learning based beam prediction on the UE side. The control signaling may also configure feature parameters associated with the downlink reference signals. The ML data collection configuration component 150 may transmit to the UEs 102 the downlink reference signals based on the control signaling.

The ML data collection configuration component 150 may be within one or more processors of the one or more network entities 104, such as the RU processor 1206 (e.g., at 150a) , the DU processor 1226 (e.g., at 150b) , and/or the CU processor 1246 (e.g., at 150c) . The ML data collection configuration component 150a-150c may be one or more hardware components specifically configured to carry out the stated processes/algorithm, implemented by one or more processors 1206, 1226, 1246 configured to perform the stated processes/algorithm, stored within a computer-readable medium for implementation by the one or more processors 1206, 1226, 1246, or a combination thereof.

The specific order or hierarchy of blocks in the processes and flowcharts disclosed herein is an illustration of example approaches. Hence, the specific order or hierarchy of blocks in the processes and flowcharts may be rearranged. Some blocks may also be combined or deleted. Dashed lines may indicate optional elements of the diagrams. The accompanying method claims present elements of the various blocks in an example order, and are not limited to the specific order or hierarchy presented in the claims, processes, and flowcharts.

The detailed description set forth herein describes various configurations in connection with the drawings and does not represent the only configurations in which the concepts described herein may be practiced. The detailed description includes specific details for the purpose of providing a thorough explanation of various concepts. However, these concepts may be practiced without these specific details. In some instances, well known structures and components are shown in block diagram form in order to avoid obscuring such concepts.

Aspects of wireless communication systems, such as telecommunication systems, are presented with reference to various apparatuses and methods. These apparatuses and methods are described in the following detailed description and are illustrated in the accompanying drawings by various blocks, components, circuits, processes, call flows, systems, algorithms, etc. (collectively referred to as “elements” ) . These elements may be implemented using electronic hardware, computer software, or combinations thereof. Whether such elements are implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system.

An element, or any portion of an element, or any combination of elements may be implemented as a “processing system” that 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 (SoC) , baseband processors, field programmable gate arrays (FPGAs) , programmable logic devices (PLDs) , state machines, gated logic, discrete hardware circuits, and other similar hardware configured to perform the various functionality described throughout this disclosure. One or more processors in the processing system may execute software, which may be referred to as software, firmware, middleware, microcode, hardware description language, or otherwise. Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software components, applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, functions, or any combination thereof.

If the functionality described herein is implemented in software, the functions may be stored on, or encoded as, one or more instructions or code on a computer-readable medium, such as a non-transitory computer-readable storage medium. Computer-readable media includes computer storage media and can include a random-access memory (RAM) , a read-only memory (ROM) , an 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. Storage media may be any available media that can be accessed by a computer.

Aspects, implementations, and/or use cases described herein may be implemented across many differing platform types, devices, systems, shapes, sizes, and packaging arrangements. For example, the aspects, implementations, and/or use cases may come about via integrated chip implementations and other non-module-component based devices, such as end-user devices, vehicles, communication devices, computing devices, industrial equipment, retail/purchasing devices, medical devices, artificial intelligence (AI) -enabled devices, machine learning (ML) -enabled devices, etc. The aspects, implementations, and/or use cases may range from chip-level or modular components to non-modular or non-chip-level implementations, and further to aggregate, distributed, or original equipment manufacturer (OEM) devices or systems incorporating one or more techniques described herein.

Devices incorporating the aspects and features described herein may also include additional components and features for the implementation and practice of the claimed and described aspects and features. For example, transmission and reception of wireless signals necessarily includes a number of components for analog and digital purposes, such as hardware components, antennas, RF-chains, power amplifiers, modulators, buffers, processor (s) , interleavers, adders/summers, etc. Techniques described herein may be practiced in a wide variety of devices, chip-level components, systems, distributed arrangements, aggregated or disaggregated components, end-user devices, etc., of varying configurations.

The description herein is provided to enable a person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects. Thus, the claims are not limited to the aspects described herein, but are to be interpreted in view of the full scope of the present disclosure consistent with the language of the claims.

Reference to an element in the singular does not mean “one and only one” unless specifically stated, but rather “one or more. ” Terms such as “if, ” “when, ” and “while” do not imply an immediate temporal relationship or reaction. That is, these phrases, e.g., “when, ” do not imply an immediate action in response to or during the occurrence of an action, but simply imply that if a condition is met then an action will occur, but without requiring a specific or immediate time constraint for the action to occur. The terms “may” , “might” , and “can” , as used in this disclosure, often carry certain connotations. For example, “may” refers to a permissible feature that may or may not occur, “might” refers to a feature that probably occurs, and “can” refers to a capability (e.g., capable of) . The phrase “For example” often carries a similar connotation to “may” and, therefore, “may” is sometimes excluded from sentences that include “for example” or other similar phrases.

Unless specifically stated otherwise, the term “some” refers to one or more. Combinations such as “at least one of A, B, or C” or “one or more of A, B, or C” include any combination of A, B, and/or C, such as A and B, A and C, B and C, or A and B and C, and may include multiples of A, multiples of B, and/or multiples of C, or may include A only, B only, or C only. Sets should be interpreted as a set of elements where the elements number one or more.

Unless otherwise specifically indicated, ordinal terms such as “first” and “second” do not necessarily imply an order in time, sequence, numerical value, etc., but are used to distinguish between different instances of a term or phrase that follows each ordinal term. Reference numbers, as used in the specification and figures, are sometimes cross-referenced among drawings to denote same or similar features. A feature that is exactly the same in multiple drawings may be labeled with the same reference number in the multiple drawings. A feature that is similar among the multiple drawings, but not exactly the same, may be labeled with reference numbers that have different leading numbers, but have one or more of the same trailing numbers (e.g., 206, 306, 406, etc., may refer to similar features in the drawings) . Sometimes an “X” is used to universally denote multiple variations of a feature. For instance, “X06” can universally refer to all reference numbers that end in “06” (e.g., 206, 306, 406, etc. ) .

Structural and functional equivalents to elements of the various aspects described throughout this disclosure that are known or later come to be known to those of ordinary skill in the art are expressly incorporated herein by reference and are encompassed by the claims. The words “module, ” “mechanism, ” “element, ” “device, ” and the like may not be a substitute for the word “means. ” As such, no claim element is to be construed as a means plus function unless the element is expressly recited using the phrase “means for. ” As used herein, the phrase “based on” shall not be construed as a reference to a closed set of information, one or more conditions, one or more factors, or the like. In other words, the phrase “based on A” , where “A” may be information, a condition, a factor, or the like, shall be construed as “based at least on A” unless specifically recited differently.

The following examples are illustrative only and may be combined with other examples or teachings described herein, without limitation.

Example 1 is a method of wireless communication at a UE, including: receiving, from a network entity, a signaling to configure a codebook for beams of a plurality of downlink reference signals configured for data collection associated with machine learning based beam prediction, and feature parameters associated with the downlink reference signals; receiving, from the network entity, the downlink reference signals based on the signaling; and generating beam quality data based on the downlink reference signals, the beam quality data being associated with the data collection.

Example 2 may be combined with Example 1 and includes that the codebook includes at least one of: an azimuth angle of departure (AoD) and a zenith angle of departure (ZoD) corresponding to the beams; an angular span of the AoD for the beams; an angular span of the ZoD for the beams; a number of the beams in a horizontal direction; a number of the beams in a vertical direction; a number of horizontal antenna ports; a number of vertical antenna ports; an oversampling factor for a number of the beams in a horizontal direction; or an oversampling factor for a number of the beams in a vertical direction.

Example 3 may be combined with any one of Examples 1 or 2, and includes that the feature parameters includes at least one of: a beam pattern corresponding to the beams of the downlink reference signals; a time resource corresponding to the downlink reference signals; a frequency resource corresponding to the downlink reference signals; a transmission power corresponding to the downlink reference signals; a time-domain behavior of the downlink reference signals; a serving cell index associated with the downlink reference signals; a bandwidth part index associated with the downlink reference signals; or a physical cell identifier associated with the downlink reference signals.

Example 4 may be combined with Example 3, and includes that the time-domain behavior includes at least one of: a periodicity of the downlink reference signals; a number of repetitions of the downlink reference signals; or an interval between two consecutive repetitions of the downlink reference signals.

Example 5 may be combined with any one of Examples 1-4, and includes that the downlink reference signals includes at least one of: a synchronization signal block (SSB) ; or a channel state information reference signal (CSI-RS) .

Example 6 may be combined with any one of Examples 1-5, and further includes transmitting, to the network entity, a request for the downlink reference signals.

Example 7 may be combined with Example 6, and includes that the signaling received further configures at least one of: an uplink resource for the UE to transmit the request; a monitoring window for the UE to monitor a response to the request; a maximum number of retransmissions of the request; a retransmission interval between retransmissions of the request; or a downlink resource for the UE to receive a response to the request.

Example 8 may be combined with Example 7, and includes that the signaling received further configures at least one of: transmitting the request when a timer counting down a wait interval from a trigger event expires and a beam quality associated with a previous instance of one of the downlink reference signals is above a threshold; or retransmitting the request when a timer counting down the retransmission interval from a previous transmission of the request expires before receiving the downlink reference signals.

Example 9 may be combined with Example 6, and includes that the request for the downlink reference signals includes at least one of: a serving cell index associated with the downlink reference signals; a bandwidth part index associated with the downlink reference signals; a beam corresponding to the downlink reference signals; a number of repetitions for the downlink reference signals; or an interval between two consecutive repetitions of the downlink reference signals.

Example 10 may be combined with Example 6, and further includes monitoring a response to the request after a delay from transmitting the request; and receiving, from the network entity, the response.

Example 11 may be combined with any one of Examples 1-10, and further includes receiving, from the network entity, a configuration indicating a measurement gap for the data collection associated with the machine learning based beam prediction.

Example 12 may be combined with Example 11, and includes that the downlink reference signals are also received for a secondary beam operation different from the data collection associated with the machine learning based beam prediction.

Example 13 may be combined with Example 12, and includes that receiving the downlink reference signals includes: receiving a first subset of the downlink reference signals within the measurement gap for the data collection associated with the machine learning based beam prediction; and receiving a second subset of the downlink reference signals outside the measurement gap for the secondary beam operation.

Example 14 may be combined with any one of Examples 1-13, and further includes: transmitting, to the network entity, information on capability of the UE to support the data collection associated with the machine learning based beam prediction. The information includes at least one of: a preferred periodicity for the data collection; a minimum periodicity for the data collection; a maximum periodicity for the data collection; a preferred number of instances of the downlink reference signals for the data collection; a minimum number of instances of the downlink reference signals for the data collection; a maximum number of instances of the downlink reference signals for the data collection; a preferred interval between two consecutive instances of the downlink reference signals for the data collection; a minimum interval between two consecutive instances of the downlink reference signals for the data collection; a maximum interval between two consecutive instances of the downlink reference signals for the data collection; or a preferred time-domain behavior of the downlink reference signals for the data collection.

Example 15 may be combined with any one of Examples 1-14, and includes that receiving the downlink reference signals includes performing a receive beam sweeping to identify a best receive beam to receive the downlink reference signals.

Example 16 is a method of wireless communication at a network entity, including: transmitting, to a user equipment, a signaling to configure a codebook for beams of a plurality of downlink reference signals for data collection associated with machine learning based beam prediction, and feature parameters associated with the downlink reference signals; and transmitting, to the UE, the downlink reference signals based on the signaling.

Example 17 may be combined with Example 16, and includes that the codebook includes at least one of: an azimuth angle of departure (AoD) and a zenith angle of departure (ZoD) corresponding to the beams; an angular span of the AoD for the beams; an angular span of the ZoD for the beams; a number of the beams in a horizontal direction; a number of the beams in a vertical direction; a number of horizontal antenna ports; a number of vertical antenna ports; an oversampling factor for a number of the beams in a horizontal direction; or an oversampling factor for a number of the beams in a vertical direction.

Example 18 may be combined with any one of Examples 16-17, and includes that the feature parameters includes at least one of: a beam pattern corresponding to the beams of the downlink reference signals; a time resource corresponding to the downlink reference signals; a frequency resource corresponding to the downlink reference signals; a transmission power corresponding to the downlink reference signals; a time-domain behavior of the downlink reference signals; a serving cell index associated with the downlink reference signals; a bandwidth part index associated with the downlink reference signals; or a physical cell identifier associated with the downlink reference signals..

Example 19 may be combined with any one of Examples 16-18, and further includes receiving, from the UE, a request for the downlink reference signals. The request for the downlink reference signals includes at least one of: a serving cell index associated with the downlink reference signals; a bandwidth part index associated with the downlink reference signals; a beam corresponding to the downlink reference signals; a number of repetitions for the downlink reference signals; or an interval between two consecutive repetitions of the downlink reference signals.

Example 20 may be combined with any one of Examples 16-19, and further includes transmitting, to the network entity, a configuration indicating a measurement gap for the data collection associated with the machine learning based beam prediction.

Example 21 may be combined with any one of Examples 16-20, and further includes receiving, from the UE, UE assistance information for the data collection associated with the machine learning based beam prediction. The UE assistance information includes at least one of: a preferred periodicity for the data collection; a minimum periodicity for the data collection; a maximum periodicity for the data collection; a preferred number of instances of the downlink reference signals for the data collection; a minimum number of instances of the downlink reference signals for the data collection; a maximum number of instances of the downlink reference signals for the data collection; a preferred interval between two consecutive instances of the downlink reference signals for the data collection; a minimum interval between two consecutive instances of the downlink reference signals for the data collection; a maximum interval between two consecutive instances of the downlink reference signals for the data collection; or a preferred time-domain behavior of the downlink reference signals for the data collection.

Example 22 is an apparatus for wireless communication, including a memory, a transceiver, and a processor coupled to the memory and the transceiver, the apparatus being configured to implement a method as in any of Examples 1-21.

Example 23 may be combined with Example 8, and includes that the signaling received from the network entity further configures the threshold.

Example 24 may be combined with Example 8, and includes that counting down the wait interval or the retransmission interval for retransmitting the request includes restarting or stopping the timer in response to at least one of: the UE receiving the downlink reference signals; the UE receiving a trigger for the downlink reference signals; the UE switching to a different physical cell; the UE activating a secondary cell (SCell) ; or the UE adding a primary secondary serving cell (PSCell) .

Example 25 may be combined with Example 7, and includes that the uplink resource used to transmit the request for the downlink reference signals includes at least one of: a physical uplink control channel (PUCCH) ; a physical uplink shared channel (PUSCH) ; or a physical random access channel (PRACH) .

Example 26 may be combined with Example 10, and includes that the signaling received from the network entity further configures the delay.

Example 27 may be combined with Example 10, and includes that the response includes a triggering signal activating the plurality of downlink reference signals.

Example 28 may be combined with Example 1, and further includes receiving, from the network entity, a triggering signal activating the UE to receive the plurality of downlink reference signals.

Example 29 may be combined with Example 18, and includes that the time-domain behavior includes at least one of: a periodicity of the downlink reference signals; a number of repetitions of the downlink reference signals; or an interval between two consecutive repetitions of the downlink reference signals.

Example 30 may be combined with Example 16, and includes that the downlink reference signals includes at least one of: a synchronization signal block (SSB) ; or a channel state information reference signal (CSI-RS) .

Example 31 may be combined with Example 16, and further includes receiving, from the UE, a request for the downlink reference signals.

Example 32 may be combined with Example 31, and includes that the signaling transmitted to the UE further configures at least one of: an uplink resource for the UE to transmit the request; a monitoring window for the UE to monitor a response to the request; a maximum number of retransmissions of the request; a retransmission interval between retransmissions of the request; or a downlink resource for a response to the request.

Example 33 may be combined with Example 32, and includes that the uplink resource for the request includes at least one of: a physical uplink control channel (PUCCH) ; a physical uplink shared channel (PUSCH) ; or a physical random access channel (PRACH) .

Example 34 may be combined with Example 31, and includes that the request is received when a beam quality associated with a previous instance of one of the downlink reference signals is above a threshold.

Example 35 may be combined with Example 34, and includes that the signaling transmitted to the UE further configures the threshold.

Example 36 may be combined with Example 31, and further includes transmitting, to the UE, a response to the request.

Example 37 may be combined with Example 36, and includes that the response includes a triggering signal activating the plurality of downlink reference signals.

Example 38 may be combined with Example 16, and includes transmitting, to the UE, a triggering signal activating the plurality of downlink reference signals.

Claims

A method of wireless communication at a user equipment (UE) (102) , comprising:

receiving (904) , from a network entity (104) , a signaling to configure:

a codebook for beams of a plurality of downlink reference signals configured for data collection associated with machine learning based beam prediction, and

feature parameters associated with the downlink reference signals;

receiving (910) , from the network entity (104) , the downlink reference signals based on the signaling; and

generating (912) beam quality data based on the downlink reference signals, the beam quality data being associated with the data collection.
The method of claim 1, wherein the codebook comprises at least one of:

an azimuth angle of departure (AoD) and a zenith angle of departure (ZoD) corresponding to the beams;

an angular span of the AoD for the beams;

an angular span of the ZoD for the beams.

a number of the beams in a horizontal direction;

a number of the beams in a vertical direction;

a number of horizontal antenna ports;

a number of vertical antenna ports;

an oversampling factor for a number of the beams in a horizontal direction; or

an oversampling factor for a number of the beams in a vertical direction.
The method of one of claims 1-2, wherein the feature parameters comprise at least one of:

a beam pattern corresponding to the beams of the downlink reference signals;

a time resource corresponding to the downlink reference signals;

a frequency resource corresponding to the downlink reference signals;

a transmission power corresponding to the downlink reference signals;

a time-domain behavior of the downlink reference signals;

a serving cell index associated with the downlink reference signals;

a bandwidth part index associated with the downlink reference signals; or

a physical cell identifier associated with the downlink reference signals.
The method of claim 3, wherein the time-domain behavior comprises at least one of:

a periodicity of the downlink reference signals;

a number of repetitions of the downlink reference signals; or

an interval between two consecutive repetitions of the downlink reference signals.
The method of any one of claims 1-4, wherein the downlink reference signals comprise at least one of:

a synchronization signal block (SSB) ; or

a channel state information reference signal (CSI-RS) .
The method of any one of claims 1-5, further comprising:

transmitting (906) , to the network entity (104) , a request for the downlink reference signals.
The method of claim 6, wherein the signaling received further configures at least one of:

an uplink resource for the UE (102) to transmit the request;

a monitoring window for the UE (102) to monitor a response to the request;

a maximum number of retransmissions of the request;

a retransmission interval between retransmissions of the request; or

a downlink resource for the UE (102) to receive a response to the request.
The method of claim 7, wherein transmitting the request for the downlink reference signals comprises at least one of:

transmitting the request when a timer counting down a wait interval from a trigger event expires and a beam quality associated with a previous instance of one of the downlink reference signals is above a threshold; or

retransmitting the request when a timer counting down the retransmission interval from a previous transmission of the request expires before receiving the downlink reference signals.
The method of claim 6, wherein the request for the downlink reference signals comprises at least one of:

a serving cell index associated with the downlink reference signals;

a bandwidth part index associated with the downlink reference signals;

a beam corresponding to the downlink reference signals;

a number of repetitions for the downlink reference signals; or

an interval between two consecutive repetitions of the downlink reference signals.
The method of claim 6, further comprising:

monitoring a response to the request after a delay from transmitting the request; and

receiving (908) , from the network entity (104) , the response.
The method of any one of claims 1-10, further comprising:

receiving, from the network entity (104) , a configuration indicating a measurement gap for the data collection associated with the machine learning based beam prediction.
The method of claim 11, wherein the downlink reference signals are also received for a secondary beam operation different from the data collection associated with the machine learning based beam prediction.
The method of claim 12, wherein receiving the downlink reference signals comprises:

receiving a first subset of the downlink reference signals within the measurement gap for the data collection associated with the machine learning based beam prediction; and

receiving a second subset of the downlink reference signals outside the measurement gap for the secondary beam operation.
The method of any one of claims 1-13, further comprising:

transmitting (902) , to the network entity (104) , information on capability of the UE (102) to support the data collection associated with the machine learning based beam prediction, wherein the information comprises at least one of:

a preferred periodicity for the data collection;

a minimum periodicity for the data collection;

a maximum periodicity for the data collection;

a preferred number of instances of the downlink reference signals for the data collection;

a minimum number of instances of the downlink reference signals for the data collection;

a maximum number of instances of the downlink reference signals for the data collection;

a preferred interval between two consecutive instances of the downlink reference signals for the data collection;

a minimum interval between two consecutive instances of the downlink reference signals for the data collection;

a maximum interval between two consecutive instances of the downlink reference signals for the data collection; or

a preferred time-domain behavior of the downlink reference signals for the data collection.
The method of any one of claims 1-14, wherein receiving the downlink reference signals comprises:

performing a receive beam sweeping to identify a best receive beam to receive the downlink reference signals.
A method of wireless communication at a network entity (104) , comprising:

transmitting (1004) , to a user equipment (UE) (102) , a signaling to configure:

a codebook for beams of a plurality of downlink reference signals for data collection associated with machine learning based beam prediction, and

feature parameters associated with the downlink reference signals; and

transmitting (1010) , to the UE (102) , the downlink reference signals based on the signaling.
The method of claim 16, wherein the codebook comprises at least one of:

an azimuth angle of departure (AoD) and a zenith angle of departure (ZoD) corresponding to the beams;

an angular span of the AoD for the beams;

an angular span of the ZoD for the beams.

a number of the beams in a horizontal direction;

a number of the beams in a vertical direction;

a number of horizontal antenna ports;

a number of vertical antenna ports;

an oversampling factor for a number of the beams in a horizontal direction; or

an oversampling factor for a number of the beams in a vertical direction.
The method of any one of claims 16-17, wherein the feature parameters comprise at least one of:

a beam pattern corresponding to the beams of the downlink reference signals;

a time resource corresponding to the downlink reference signals;

a frequency resource corresponding to the downlink reference signals;

a transmission power corresponding to the downlink reference signals;

a time-domain behavior of the downlink reference signals;

a serving cell index associated with the downlink reference signals;

a bandwidth part index associated with the downlink reference signals; or

a physical cell identifier associated with the downlink reference signals.
The method of any one of claims 16-18, further comprising receiving (1006) , from the UE (102) , a request for the downlink reference signals, wherein the request for the downlink reference signals comprises at least one of:

a serving cell index associated with the downlink reference signals;

a bandwidth part index associated with the downlink reference signals;

a beam corresponding the downlink reference signals;

a number of repetitions for the downlink reference signals; or

an interval between two consecutive repetitions of the downlink reference signals.
The method of any one of claims 16-19, further comprising:

transmitting, to the network entity (104) , a configuration indicating a measurement gap for the data collection associated with the machine learning based beam prediction.
The method of any one of claims 16-20, further comprising:

receiving (1002) , from the UE (102) , UE assistance information for the data collection associated with the machine learning based beam prediction, wherein the UE assistance information comprises at least one of:

a preferred periodicity for the data collection;

a minimum periodicity for the data collection;

a maximum periodicity for the data collection;

a preferred number of instances of the downlink reference signals for the data collection;

a minimum number of instances of the downlink reference signals for the data collection;

a maximum number of instances of the downlink reference signals for the data collection;

a preferred interval between two consecutive instances of the downlink reference signals for the data collection;

a minimum interval between two consecutive instances of the downlink reference signals for the data collection;

a maximum interval between two consecutive instances of the downlink reference signals for the data collection; or

a preferred time-domain behavior of the downlink reference signals for the data collection.
An apparatus for wireless communication comprising a memory, a transceiver, and a processor coupled to the memory and the transceiver, the apparatus being configured to implement a method as in any of claims 1-21.