EP4728660A1

EP4728660A1 - Method for network data collection for machine learning based beam management

Info

Publication number: EP4728660A1
Application number: EP23755012.4A
Authority: EP
Inventors: Yushu Zhang
Original assignee: Google LLC
Current assignee: Google LLC
Priority date: 2023-07-13
Filing date: 2023-07-13
Publication date: 2026-04-22
Also published as: CN121532959A; WO2025010732A1

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 on the network side. A signaling framework allows a network entity to control the scope of data collected and to configure the content and the time domain behavior of a report. A UE (102) receives (1104), from a network entity (104), a control signaling for configuring one or more sets of channel measurement resources (CMRs) and a report for data collection associated with machine learning based beam management. The UE (102) receives (1110), from the network entity (104), downlink reference signals via the one or more sets of CMRs. The UE (102) transmits (1112), to the network entity (104), the report based on beam measurements corresponding to the downlink reference signals.

Description

METHOD FOR NETWORK 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 network 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 network entity 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 and CSI reporting capabilities. 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. In addition, there may be measurement error when the UE makes beam quality measurements. Measurement error in the data collected by the UE may degrade the performance of machine learning. The UE may consider how to reduce the negative impact of the measurement error when reporting the beam quality measurements.
Aspects of the present disclosure address the above-noted and other deficiencies associated with data collection by a UE to support machine learning based beam prediction performed on the network entity side. In some aspects, a signaling framework is disclosed to allow the network entity to flexibly control the scope of data collected by the UE such as the number, frequency, timing, etc., of beam quality measurements. In some aspects, when the UE performs receive beam sweeping to receive the downlink reference signals, there may be a scheduling restriction to refrain the network entity from transmitting other downlink signals that overlap in time with the downlink reference signals. In some aspects, if there is no such scheduling restriction, the UE may determine the receive beam based on a priority rule to apply the receive beam corresponding to the downlink signal with the highest priority. In some aspects, the network entity may configure the content and the time domain behavior of the CSI report. In some embodiments, the UE may report the L1-RSRP for the configured CMR and the index (es) of the best beam (s) based on the L1-RSRP, L1-SINR and/or the hypothetical measurement error of the configured CMR satisfying one or more criteria.
According to some aspects, a UE receives, from a network entity, a control signaling for configuring one or more sets of channel measurement resources (CMRs) and a report for data collection associated with machine learning based beam management. The UE receives, from the network entity, downlink reference signals via the one or more sets of CMRs. The UE, transmits, to the network entity, the report based on beam measurements corresponding to the downlink reference signals.
According to some aspects, a network entity transmits, to a UE, a control signaling for configuring one or more sets of channel measurement resources (CMRs) and a report for data collection associated with machine learning based beam management on the network entity. The network entity transmits, to the UE, downlink reference signals via the one or more sets of CMRs. The network entity receives, from the UE, the report based on beam measurements corresponding to the downlink reference signals.

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 network-side machine learning based beam management according to an embodiment.
FIG. 5 illustrates an example of a joint input/output beam report for a machine learning model when the beam report includes a subset of beam quality measurements from a set of channel measurement resources (CMRs) and a beam index of the best beam of the CMRs according to an embodiment.
FIG. 6 illustrates an example of a beam report based on beam measurements of the CMRs made at a number of reporting instances before a reference time according to an embodiment.
FIG. 7 illustrates an example of a beam report based on averaging the beam measurements of the CMRs for each of a number of reporting instances before a reference time according to an embodiment.
FIG. 8 illustrates an example of a joint input/output beam report for a machine learning model when the network entity configures two sets of CMRs for beam measurements and the beam report includes a subset of beam quality measurements from a first set of CMRs and a beam index of the best beam from a second set of CMRs according to an embodiment.
FIG. 9 illustrates an example of separate beam reports for the input and output data of a machine learning model when the network entity configures two sets of CMRs for beam measurements and the beam report includes a subset of beam quality measurements from a first set of CMRs and a beam index of the best beam from a second set of CMRs according to an embodiment.
FIG. 10 illustrates an example of beam measurements of CMRs based on a configured measurement window that indicates the time for the UE to measure the CMRs to generate the beam report according to an embodiment.
FIG. 11 is a flowchart of a method of wireless communication at a UE for receiving CMRs and reporting beam measurements of the CMRs in a beam report to support network-side machine learning based beam management according to an embodiment.
FIG. 12 is a flowchart of a method of wireless communication at a network entity for transmitting CMRs and receiving beam measurements of the CMRs in a beam report to support network-side machine learning based beam management according to an embodiment.
FIG. 13 is a diagram illustrating a hardware implementation for an example UE apparatus according to some embodiments.
FIG. 14 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 network-side machine learning based beam management component 140 (also referred to as ML data collection component 140) configured to collect data to support training, refinement, or monitoring of a network-side machine learning model for downlink beam management. The ML data collection component 140 may receive from the base station/network entity 104 a control signaling for configuring one or more sets of channel measurement resources (CMRs) and configuring a report for data collection associated with machine learning based beam management. The ML data collection component 140 may receive from the base station/network entity 104 downlink reference signals via the one or more sets of CMRs. The ML data collection component 140 may transmit to the base station/network entity 104 the report based on beam measurements corresponding to the downlink reference signals.
In certain aspects, any of the base stations 104 or a network entity of the base stations 104 may include a network-side machine learning based beam management 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 network-side machine learning model for downlink beam management. The ML data collection configuration component 150 may transmit to any of the UEs 102 a control signaling for configuring one or more sets of CMRs and configuring a report for data collection associated with machine learning based beam management on the base station/network entity 104. The ML data collection configuration component 150 may transmit to the UEs 102 downlink reference signals via the one or more sets of CMRs. The ML data collection configuration component 150 may receive from the UEs the report based on beam measurements corresponding to the downlink reference signals.
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 CMRs. Training, refinement, or monitoring of the machine learning model relies on data collection of beam measurements performed by a UE 102. For example, a 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 receive the downlink reference signals in a range of azimuth and elevation (may also be referred to as zenith) angles. 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. When the machine learning model resides on the network side, the UE 102 may report the input and output training data for the machine learning model as a beam report to a network entity 104. Once trained, the network entity 104 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 as monitored by the UE 102.
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. The network entity 104 may use a subset of best beams 230 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 reporting instances. Each beam measurement for a time reporting instance may include beam quality measurements of multiple beams received at the time reporting instance. The machine learning model 310 may apply beam quality measurements 320, 330, and 340 from the three time reporting 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 network entity side. In some aspects, a signaling framework is disclosed to allow the network entity to flexibly control the scope of data collected by the UE such as the number, frequency, timing, etc., of beam quality measurements. In some aspects, when the UE performs receive beam sweeping to receive the downlink reference signals, there may be a scheduling restriction to refrain the network entity from transmitting other downlink signals that overlap in time with the downlink reference signals. In some aspects, if there is no such scheduling restriction, the UE may determine the receive beam based on a priority rule to apply the receive beam corresponding to the downlink signal with the highest priority. In some aspects, the network entity may configure the content and the time domain behavior of the CSI report.
In some embodiments, the UE may report the L1-RSRP of the downlink reference signals for the configured CMR and the index (es) of the best beams based on the L1-RSRP, L1-SINR, and/or the hypothetical measurement error of the configured CMR satisfying one or more criteria. 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 network-side machine learning based beam management according to one 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 pertaining to supported configuration for data collection for beam prediction. In one implementation, the capability information may include supported configuration for the beam report, such as the maximum number of the best beams to report, the maximum number of time reporting instances of the downlink reference signals, the maximum number of beam measurements for each time reporting instance, a minimum processing for the beam report, the supported time domain behavior for the beam report, etc. 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 one or more sets of CMRs and a report based on the beam measurements. The report may represent the data collection used for machine learning based beam management. In one implementation, the network entity 104 may configure at least one CSI report configuration for data collection by Radio Resource Control (RRC) signaling, e.g., RRCReconfiguration, where the network entity may configure at least one set of downlink reference signals, e.g., SSB or CSI-RS, as CMR. The network entity may further configure the report quantity for the data collection by RRC signaling. The report quantity may include the content and the time domain behavior of the CSI report such as the number, frequency, timing, etc., of the beam quality measurements. For periodic report, the network entity may further configure the periodicity and the slot offset for the report.
The network entity 104 may transmit 406, to the UE 102, (or the UE 102 may receive 406 from the network entity 104) a trigger signal to trigger the configured set (s) of downlink reference signals and/or the beam report for data collection. For example, for semi-persistent report or aperiodic report, the network entity 104 may transmit a Medium Access Control (MAC) Control Element (CE) or Downlink Control Information (DCI) (e.g., in PDCCH) to trigger the beam report. For semi-persistent downlink reference signal or aperiodic downlink reference signal, the network entity 104 may transmit a MAC CE or DCI to trigger the downlink reference signals.
The UE 102 may determine 408 a receive beam to receive the downlink reference signals. In one implementation, the UE 102 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 102 may determine whether and how to receive the downlink reference signals to identify the best beams. In some aspects, when the UE 102 performs receive beam sweeping to receive the downlink reference signals, there may be a scheduling restriction to refrain the network entity from transmitting other downlink signals that overlap in time with the downlink reference signals. In some aspects, if there is no such scheduling restriction, the UE 102 may determine the receive beam based on a priority rule to apply the receive beam corresponding to the downlink signal with the highest priority.
The network entity 104 may transmit 410 (or the UE 102 may receive 410) the downlink reference signals via the one or more sets of configured CMRs for the UE 102 to perform the beam measurements. The UE 102 may transmit 412, to the network entity 104, (or the network entity 104 may receive 412 from the UE 102) the beam report based on the configured report quantity and the received downlink reference signals. The beam report may provide beam quality data corresponding to the one or more sets of CMRs for supporting machine learning based beam management.
Following is a detailed discussion of how the UE 102 may be configured to measure beams of one or more sets of CMRs to collect data for supporting machine learning based beam prediction on the network side. In one aspect, the network entity 104 may configure the UE 102 to collect both input and output data for the machine learning model in a single beam report based on a single set of CMRs. In one aspect, the network entity 104 may configure the UE 102 to collect model input data and model output data based on separate sets of CMRs in a single beam report. In one aspect, the network 104 may configure the UE 102 to collect model input data and model output data based on separate sets of CMRs in separate beam reports.
FIG. 5 illustrates an example 500 of a joint input/output beam report for a machine learning model when the beam report includes a subset of beam quality measurements from a set of channel measurement resources (CMRs) and a beam index of the best beam of the CMRs according to one embodiment. The network entity 104 may configure the UE 102 to collect beam measurements for both input and output data for a machine learning model based on a single set of CMRs. In one aspect, the network entity 104 may use RRC signaling to configure the UE 102 to generate a beam report, such as a CSI report.
The single set of CMRs may include downlink reference signals transmitted on a spatial array of four beams in the ZoD dimension and 8 beams in the AoD dimension for a total of 32 beams (510) . The UE 102 may perform beam quality measurements for all 32 beams (510) , but the network entity 104 may configure a CMR report subset restriction to request the UE 102 to report the beam quality for a subset of beams of the CMRs.
FIG. 5 shows that the CMR report subset restriction indicates a subset of 4 beams (520) . The network entity may further configure the UE to report the N beam index (es) , e.g., SSB resource indicator (SSBRI) or CSI-RS resource indicator (CRI) , corresponding to the best beam (s) . In one implementation, the value of N may be predefined, e.g., N=1. In another implementation, network entity 104 may configure the value of N by RRC signaling, e.g., an RRC parameter in the CSI report configuration. In one implementation, the UE 102 may report the maximum value of N via the UE capability information. FIG. 5 shows the network entity 104 configuring the UE 102 to report the beam index for the best beam (N=1) . In one implementation, the network entity 104 may further configure the UE 102 to report the beam quality corresponding to the N best beam (s) .
The UE 102 may report the beam quality 530 for the 4 beams (520) indicated by the CMR report subset restriction. The UE 102 may evaluate the beam quality measurements for all 32 beams to determine the beam with the best beam quality. The beam report may further contain the beam index of the best beam 540. The beam quality for the best beam 540 may not be a part of the beam quality 530 for the 4 beams (520) as requested by the CMR report subset restriction. In such case, the UE 102 may report the beam quality of the best beam 540.
The network entity 104 may transmit beams carrying the downlink reference signals of the CMRs over a number of time instances, such as by periodically transmitting the beams. In one implementation, for temporal beam prediction, the network entity 104 may configure the UE 102 to report the N beam index (es) , the beam quality for the N best beam (s) , and/or the beam quality for the CMR subsets configured in the CMR subset restriction corresponding to each of X time reporting instances. For example, the network entity 104 may configure the UE 102 to report the beam quality for the CMR subsets and the beam indexes of the N beam beams for each time reporting instance for X periodic or aperiodic time reporting instances. In one implementation, X may be predefined, e.g., X = 4. In another implementation, the network entity 104 may configure X by RRC signaling, e.g., an RRC parameter in the CSI report configuration. In one implementation, the UE 102 may report the maximum value of X via the UE capability information. In one implementation, the UE 102 may report the maximum value of X*N via the UE capability information.
FIG. 6 illustrates an example 600 of a beam report 660 based on beam measurements of the CMRs made at a number of reporting instances before a reference time 650 according to an embodiment. The CMRs may be periodic and are denoted as CMR instance 1 (610) , CMR instance 2 (620) , CMR instance 3 (630) , and CMR instance 4 (640) . The network entity 104 may configure the UE 102 to collect data for three time reporting instances of the CMRs (e.g., CMR instance 2 (620) , CMR instance 3 (630) , CMR instance 4 (640) ) before the reference time 650. These time reporting instances of the CMRs for which the UE 102 reports beam measurement data may be referred to as the reporting instances.
In one implementation, the reference time 650 may be predefined, e.g., the reference time may occur prior to the latest possible occurrence of the CMRs determined from the minimum processing delay for the beam report for data collection before the first symbol of the beam report. In one implementation, the minimum processing delay may be predefined (e.g., Z1 and Z1’ as defined in section 5.4 in 3GPP TS 38.214) . In one implementation, the network entity 104 may configure the minimum processing time. In one implementation, the UE 102 may report the minimum processing time via UE capability information. In one implementation, the network entity 104 may configure the reference time via RRC signaling, MAC CE, or DCI. In one implementation, the network entity 104 may configure the reference time as an offset before the first symbol of the beam report for data collection, or after the PDCCH or MAC CE triggering the beam report for data collection. In one implementation, the UE 102 may report the reference time in the beam report. In one implementation, the UE 102 may report measurement instances or measured slot index (es) for the reported beams in the beam report.
In one implementation, to improve measurement accuracy, the network entity 104 may configure the number of averaging instances (or number of measurement instances per time reporting instance) Y and the number of time reporting instances X. The UE 102 may determine the beam quality for a time reporting instance based on the measurements of Y instances of the CMRs such as by averaging the beam measurements for the Y measurements instances. In one implementation, the UE 102 may report via the UE capability information the maximum value of Y (e.g., maximum value of the measurement instance for each time reporting instance) , the maximum of X*Y (e.g., maximum value of the total measurement instances for all time reporting instances) , Y*N (e.g., a maximum product of the measurement instances per time reporting instance and the number of best beams to report) , X*N (e.g., a maximum product of the time reporting instances and the number of best beams to report) , and/or X*Y*N (e.g., a maximum product of the total measurement instances for all time reporting instances and the number of best beams to report) .
FIG. 7 illustrates an example 700 of a beam report 790 based on averaging the beam measurements of the CMRs for each of a number of reporting instances before a reference time 780 according to an embodiment. The CMRs may be periodic and are denoted as CMR instance 1 (710) , CMR instance 2 (720) , CMR instance 3 (730) , and CMR instance 4 (740) , CMR instance 5 (750) , CMR instance 6 (760) , CMR instance 7 (770) . The network entity 104 may configure the UE 102 to collect data for three time reporting instances of the CMRs before the reference time 780. The collected data for each time reporting instance may be based on an average window of two measurement instances of the CMRs. For example, the first time reporting instance may be based on an average window 725 of the beam measurements of CMR instance 2 (720) and CMR instance 3 (730) ; the second time reporting instance may be based on an average window 745 of the beam measurements of CMR instance 4 (740) and CMR instance 5 (750) ; the third time reporting instance may be based on an average window 765 of the beam measurements of CMR instance 6 (760) and CMR instance 7 (770) .
In one implementation, the network entity 104 may configure the number of measurement instances Y (e.g., number of averaging instances) in each averaging window. In one implementation, the network entity 104 may configure the total number of measurement instances Z and the number of time reporting instances X. The UE 102 may then derive the number of averaging instances Y = Z/X. In one implementation, the network entity 104 may configure the total number of measurement instances Z and the number of averaging instance Y. Then the UE may derive the number of time reporting instances X = Z/Y.
In one aspect, the network entity 104 may configure the UE 102 to collect model input data and model output data based on separate sets of CMRs in a single beam report. The beams of the separate sets of CMRs may have different beam widths. For example, the SSB configured in a first set of CMRs may have a relative wide beam width and CSI-RS configured in a second set of CMRs may have more directional beams. A machine learning model for beam management may apply the beam quality measurements from the first set of CMRs as input training data, and the beam index (es) of the best beam (s) from the second set of CMRs as output training data, for the machine learning model to predict the best narrower beam (s) based on measurements of the wider beams.
FIG. 8 illustrates an example 800 of a joint input/output beam report for a machine learning model when the network entity configures two sets of CMRs for beam measurements and the beam report includes a subset of beam quality measurements from a first set of CMRs and a beam index of the best beam from a second set of CMRs according to an embodiment. The network entity 104 may configure the UE 102 to collect beam measurements for input data and output data for a machine learning model based on the first set of CMRs and the second set of CMRs, respectively.
The first set of CMRs may include downlink reference signals transmitted on a spatial array of four beams in the ZoD dimension and 8 beams in the AoD dimension for a total of 32 beams. The UE 102 may perform beam quality measurements for all 32 beams, but the network entity 104 may configure a CMR report subset restriction to request the UE 102 to report the beam quality for a subset of 4 beams (810) of the first set of CMRs.
The second set of CMRs may also include downlink reference signals transmitted on a spatial array of four beams in the ZoD dimension and 8 beams in the AoD dimension for a total of 32 beams (820) . In one implementation, the first CMR set and the second CMR set may have different beam patterns (e.g., the two CMR sets have different azimuth/elevation width) . The network entity 104 may also configure the UE 102 to report the N beam index (es) , SSBRI or CRI, for the best beam (s) for the second CMR set. In one implementation, the value of N may be predefined, e.g., N=1. In another implementation, network entity 104 may configure the value of N by RRC signaling, e.g., an RRC parameter in the CSI report configuration. In one implementation, the UE 102 may report the maximum value of N via the UE capability information. FIG. 8 shows the network entity 104 configuring the UE 102 to report the beam index for the best beam (N=1) . In one implementation, the network entity 104 may further configure the UE 102 to report the beam quality corresponding to the N best beam (s) .
The UE 102 may report the beam quality 830 for the 4 beams (810) of the first CMR set indicated by the CMR report subset restriction. The UE 102 may perform beam quality measurements for all 32 beams (820) of the second CMR set. The UE 102 may evaluate the beam quality measurements for all 32 beams (820) of the second CMR set to determine the beam with the best beam quality. The beam report may further contain the beam index of the best beam 840 from the second CMR set. In one implementation, the UE 102 may report the beam quality of the best beam 840.
In one implementation, for temporal beam prediction, the network entity 104 may configure the UE 102 to report the N beam index (es) , the beam quality for the N best beam (s) , and/or the beam quality for the CMR report subset restriction for each of X time reporting instances for the beams in the first CMR set and the second CMR set. The number of time reporting instances X may be common or separate for the two sets of CMRs. In one implementation, X may be predefined, e.g., X = 1 for the first CMR set. In another implementation, the network entity 104 may configure X for the second CMR set by RRC signaling, e.g., an RRC parameter in the CSI report configuration. In one implementation, the UE 102 may report the maximum value of X for the first CMR set and/or the second CMR set via the UE capability information. In one implementation, the UE 102 may report the maximum value of X*N via the UE capability information.
The UE 102 may measure and report the beam quality for the X time reporting instances of the first CMR set or the second CMR set before a reference time. the reference time 650 may be predefined, e.g., the reference time may occur prior to the latest possible occurrence of the CMRs determined from the minimum processing delay for the beam report for data collection before the first symbol of the beam report. In one implementation, the minimum processing delay may be predefined. In one implementation, the network entity 104 may configure the minimum processing time. In one implementation, the UE 102 may report the minimum processing time via UE capability information. In one implementation, the network entity 104 may configure the reference time via RRC signaling, MAC CE, or DCI. In one implementation, the network entity 104 may configure the reference time as an offset before the first symbol of the beam report for data collection, or after the PDCCH or MAC CE triggering the beam report for data collection. In one implementation, the UE 102 may report the reference time in the beam report. In one implementation, the UE 102 may report measurement instances or measured slot index (es) for the reported beams in the beam report.
In one aspect, the network 104 may configure the UE 102 to collect model input data and model output data based on separate sets of CMRs in separate beam reports. The network entity 104 may configure separate CSI report configurations to collect the beam quality data for the model input and output for a machine learning model by RRC signaling. The network entity 104 may configure one set of CMRs for each CSI report configuration.
FIG. 9 illustrates an example 900 of separate beam reports for the input and output data of a machine learning model when the network entity configures two sets of CMRs for beam measurements and the beam report includes a subset of beam quality measurements from a first set of CMRs and a beam index of the best beam from a second set of CMRs according to an embodiment. The network entity 104 may configure separate CSI report configuration for the two sets of CMRs.
In one implementation, for the first CSI report configuration, the network entity 104 may configure a CMR report subset restriction to request the UE 102 to report the beam quality for a subset of 4 beams (910) of the first set of CMRs. The first set of CMRs may include downlink reference signals transmitted on a spatial array of four beams in the ZoD dimension and 8 beams in the AoD dimension for a total of 32 beams.
For the second CSI report configuration, the network entity 104 may configure the UE 102 to report the N beam index (es) , SSBRI or CRI, for the best beam (s) for the second set of CMRs. The second set of CMRs may also include downlink reference signals transmitted on a spatial array of four beams in the ZoD dimension and 8 beams in the AoD dimension for a total of 32 beams (920) . In one implementation, the first CMR set and the second CMR set may have different beam patterns (e.g., the two CMR sets have different azimuth/elevation width) . In one implementation, the value of N may be predefined, e.g., N=1. In another implementation, network entity 104 may configure the value of N by RRC signaling, e.g., an RRC parameter in the CSI report configuration. In one implementation, the UE 102 may report the maximum value of N via the UE capability information. FIG. 8 shows the network entity 104 configuring the UE 102 to report the beam index for the best beam (N=1) . In one implementation, the network entity 104 may further configure the UE 102 to report the beam quality corresponding to the N best beam (s) .
The UE 102 may report the beam quality 930 for the 4 beams (910) of the first CMR set indicated by the CMR report subset restriction configured by the first CSI report configuration. The UE 102 may perform beam quality measurements for all 32 beams (920) of the second CMR set configured by the second CSI configuration. The UE 102 may evaluate the beam quality measurements for all 32 beams (920) of the second CMR set to determine the beam with the best beam quality. The beam report may further contain the beam index of the best beam 940 from the second CMR set. In one implementation, the UE 102 may report the beam quality of the best beam 940.
In one implementation, for temporal beam prediction, the network entity 104 may configure the UE 102 to report the N beam index (es) , the beam quality for the N best beam (s) , and/or the beam quality for the CMR report subset restriction for each of X time reporting instances for the beams in the first CMR set configured by the first CSI report configuration and the beams in the second CMR set configured by the second CSI configuration. The UE may measure and report the beam quality for the X time reporting instances of the first CMR set or the second CMR set before a reference time. The UE 102 may determine the number of time reporting instances X and the reference time as discussed for FIG. 8, the details of which will not be repeated for sake of brevity.
In one aspect, when the UE 102 performs receive beam sweeping to receive the downlink reference signals configured by the CMRs for data collection, there may be a scheduling restriction to refrain the network entity 104 from transmitting other downlink signals that overlap in time with the downlink reference signals. For example, when a UE receive beam is applicable (e.g., quasi-co-location (QCL) TypeD, which indicates the spatial receive parameters, is applicable) , the network entity 104 may refrain from transmitting other downlink reference signal overlapping with the downlink reference signal for data collection in time domain in the same component carrier (CC) or different CCs within a frequency band or band combination because UE 102 needs to conduct beam sweeping.
In one implementation, the network entity 104 may refrain from transmitting the downlink reference signals with a different QCL-TypeD property as the downlink reference signal overlapping with the downlink reference signal for data collection in the same component carrier (CC) or different CCs within a frequency band or band combination.
In one implementation, the network entity 104 may configure a measurement window to indicate when the UE 102 may perform the measurement of the downlink reference signals for data collection by RRC signaling, MAC CE, or DCI. In one implementation, the network entity 104 may configure the periodicity, slot offset and duration for the measurement window. Then the aforementioned scheduling restriction is only applicable when the UE needs to measure the downlink reference signals for data collection.
FIG. 10 illustrates an example 1000 of beam measurements of CMRs based on a configured measurement window that indicates the time for the UE to measure the CMRs to generate the beam report according to an embodiment. The CMRs may be periodic and are denoted as CMR instance 1 (1011) , CMR instance 2 (1012) , CMR instance 3 (1023) , and CMR instance 4 (1024) , CMR instance 5 (1015) , CMR instance 6 (1016) , CMR instance 7 (1027) , and CMR instance 8 (1028) .
The network entity 104 may configure measurement window 1030 to be on for the UE 102 to measure CMR instance 1 (1011) and CMR instance 2 (1012) ; similarly, the network entity 104 may configure measurement window 1050 to be on for the UE 102 to measure CMR instance 5 (1015) and CMR instance 6 (1016) . During the time when the measurement windows 1030 and 1050 are on, the network entity 1014 may implement a scheduling restriction 1010 to refrain from transmitting other downlink reference signals.
In contrast, the network entity 104 may configure measurement window 1040 to be off during CMR instance 3 (1023) and CMR instance 4 (1024) ; similarly, the network entity 104 may configure measurement window 1060 to be off during CMR instance 7 (1027) and CMR instance 8 (1028) . During the time when the measurement windows 1040 and 1060 are off, the network entity 1014 may transmit the CMR instances without any scheduling restriction 1020.
In one aspect, when a UE receive beam is applicable (e.g., QCL-TypeD is applicable) , if there is another downlink reference signal overlapping with the downlink reference signal for data collection in time domain in the same component carrier (CC) or different CCs within a frequency band or band combination, the UE 102 may determine the receive beam based on a priority rule. Thus, the UE 102 may apply the receive beam (s) corresponding to the downlink signal with the highest priority.
In one implementation, the network entity 104 may configure the priority for the downlink signals via RRC signaling, MAC CE, or DCI. In one implementation, the priority for the downlink signals may be predefined. The priority may be determined based on the type of the channel, the configuration of the channel (e.g., the search space type of the channel, the time domain behavior of the channel, the triggering behavior of the channel) , etc. In one implementation, the priority from the highest downward may be defined as PDCCH in common search space > PDSCH scheduled by PDCCH in common search space > PDCCH in UE dedicated search space >PDSCH scheduled by UE dedicated search space > downlink reference signal for data collection > aperiodic CSI-RS > semi-persistent CSI-RS. In other implementations, the network entity 104 and UE 102 may determine different priority orders for the downlink signals. For example, the UE 102 may not measure the downlink reference signal to report the beam quality measurements for data collection if there is an overlapping downlink signal (e.g., PDSCH) with a higher priority.
In one implementation, the UE 102 may refrain from receiving the downlink signal with a different QCL-TypeD property from the determined QCL-TypeD for the downlink signal with the highest priority. In one implementation, the UE 102 may receive all the downlink signals based on the determined QCL-TypeD for the downlink signal with the highest priority.
In one aspect, the time domain behavior of the beam report providing the collected data may include: aperiodic report, semi-persistent report or periodic report. The network entity 104 may configure the time domain behavior for the beam report. In one implementation, the network entity 104 may refrain from configuring one or more than one time domain behavior for the report, e.g., aperiodic report. In one implementation, the UE 102 may report the UE capability indicating the supported time domain behaviors for the beam report for data collection.
In one implementation, the UE 102 may transmit the beam report for data collection by at least one PUCCH resource configured by the network entity 104 via RRC signaling, MAC CE, or DCI. In one implementation, the UE 102 may transmit the beam report for data collection by PUSCH configured by the network entity 104 via RRC signaling, MAC CE, or DCI. In one implementation, the UE 102 may transmit the beam report for data collection as uplink control information multiplexed on the PUSCH. In one implementation, the UE 102 may transmit the beam report by MAC CE.
In one aspect, for the content of the beam report providing the collected data, the network entity 104 may configure the UE 102 to report the L1-RSRP for each beam. In one implementation, the UE 102 may report the absolute L1-RSRP for each beam. If the UE 102 is configured to report the L1-RSRP for a configured CMR subset or for one or more sets of CMRs, the UE 102 may report the L1-RSRP based on the order of the beam index within the CMR subset or CMR set. Table 1 illustrates one example for the absolute L1-RSRP report for all the configured CMRs in a subset or set.
Table 1: An example for the absolute L1-RSRP report for all the configured K CMRs in a subset or set
In one implementation, the UE 102 may report the absolute L1-RSRP for the best beam and differential L1-RSRP for the remaining beams. If the UE 102 is configured to report the L1-RSRP for a configured CMR subset or for one or more sets of CMRs,the UE 102 may report a beam index indicating the beam index with the strongest L1-RSRP as well as the strongest L1-RSRP and may report the differential L1-RSRP based on the order of the remaining beam index within the CMR subset or CMR set. Table 2 illustrates one example for the absolute plus differential based L1-RSRP report for all the configured CMRs in a subset or set.
Table 2: An example for the absolute plus differential based L1-RSRP report for all the configured K CMRs in a subset or set
In one implementation, the UE 102 may determine to report the L1-RSRP for one or more CMRs if certain criteria for the CMR are met. The criteria may include at least one of the following: the measured L1-RSRP for the one or more CMRs is above a first threshold; the measured L1-SINR for the one or more CMRs is above a second threshold; or the hypothetical measurement error for the one or more CMRs is below a third threshold. In one implementation, the first, second, and third thresholds may be predefined. In one implementation, the network entity 104 may configure the first, second, and third thresholds by RRC signaling, MAC CE, or DCI. In one implementation, the UE 102 may determine the hypothetical measurement error based on the measured L1-SINR and its receiving algorithm. In one implementation, the UE 102 may report an indicator to indicate the number of reported L1-RSRPs that are above the first threshold.
In one implementation, the UE 102 may determine to report the L1-RSRP for all the configured CMRs if certain criteria are met. The criteria may include at least one of the following: the measured L1-RSRP for one or more CMR is above a first threshold; the measured L1-SINR for the CMR is above a second threshold; or the hypothetical measurement error for the CMR is below a third threshold.
In one implementation, for the beam report providing the beam quality, the network entity 104 may configure the UE 102 to report the L1-RSRP and L1-SINR for each beam. Then the network entity 104 may determine whether to use the reported L1-RSRP for model training, refinement, monitoring, and other purposes based on the received L1-SINR.
In one implementation, the UE 102 may report the absolute L1-RSRP and the absolute L1-SINR for each beam. If the UE is configured to report the L1-RSRP for a configured CMR subset or for one or more sets of CMRs, the UE 102 may report the L1-RSRP and the associated L1-SINR based on the order of the beam index within the CMR subset or CMR set.
In one implementation, the UE 102 may report the absolute L1-RSRP for the best beam and differential L1-RSRP for the remaining beams. The UE may report the absolute L1-SINR for each beam. If the UE is configured to report the L1-RSRP for a configured CMR subset or for one or more sets of CMRs, the UE 102 may report a beam index indicating the beam index with the strongest L1-RSRP as well as the strongest L1-RSRP and may report the differential L1-RSRP based on the order of the remaining beam index within the CMR subset or CMR set.
In one implementation, the UE 102 may report absolute the L1-RSRP and L1-SINR for the best beam and differential L1-RSRP and L1-SINR for the remaining beams. If the UE is configured to report the L1-RSRP for a configured CMR subset or for one or more sets of CMRs, the UE may report a beam index indicating the beam index with the strongest L1-RSRP as well as the L1-RSRP and the associated L1-SINR and may report the differential L1-RSRP and L1-SINR based on the order of the remaining beam index within the CMR subset or CMR set.
In one implementation, for each CMR, the UE 102 may report the absolute and/or differential L1-RSRP and an indicator indicating whether the L1-SINR is above a threshold. In one implementation, the threshold may be predefined, e.g., 3dB, or configured by the network entity 104 via RRC signaling.
In one implementation, for the beam report providing the beam quality, the network entity 104 may configure the UE 102 to report L1-RSRP and hypothetical measurement error for each beam. Then the network entity 104 may determine whether to use the reported L1-RSRP for model training, refinement, monitoring, and other purposes based on the received hypothetical measurement error.
In one implementation, the UE 102 may report the absolute L1-RSRP and the absolute hypothetical measurement error for each beam. If the UE is configured to report the L1-RSRP for a configured CMR subset or for one or more sets of CMRs, the UE 102 may report the L1-RSRP and the hypothetical measurement error based on the order of the beam index within the CMR subset or CMR set.
In one implementation, the UE 102 may report the absolute L1-RSRP for the best beam and differential L1-RSRP for the remaining beams. The UE 102 may report the absolute hypothetical measurement error for each beam. If the UE is configured to report the L1-RSRP a configured CMR subset or for one or more sets of CMRs, the UE 102 may report a beam index indicating the beam index with the strongest L1-RSRP as well as the L1-RSRP and may report the differential L1-RSRP based on the order of the remaining beam index within the CMR subset or CMR set.
In one implementation, for each CMR, the UE 102 may report the absolute and/or differential L1-RSRP and an indicator indicating whether the hypothetical measurement error is below a threshold. In one implementation, the threshold may be predefined, e.g., 3dB, or configured by the network entity 104 via RRC signaling.
FIGs. 11-12 show methods for implementing one or more aspects of FIGs. 2-10. In particular, FIG. 11 shows an implementation by the UE 102 of the one or more aspects of FIGs. 2-10. FIG. 12 shows an implementation by the network entity 104 of the one or more aspects of FIGs. 2-10.
FIG. 11 is a flowchart 1100 of a method of wireless communication at a UE for receiving CMRs and reporting beam measurements of the CMRs in a beam report to support network-side machine learning based beam management according to an embodiment. With reference to FIGs. 1, 4, and 13, the method may be performed by the UE 102, the UE apparatus 1302, etc., which may include the memory 1326', 1306', 1316, and which may correspond to the entire UE 102 or the entire UE apparatus 1302, or a component of the UE 102 or the UE apparatus 1302, such as the wireless baseband processor 1326 and/or the application processor 1306.
The UE transmits 1102, to a network entity, UE capability information on supported configuration for a beam report for data collection associated with machine learning based beam management. For example, referring to FIG. 4, the UE 102 transmits 402, to the network entity 104, UE capability on supported configuration for a beam report for data collection. In one implementation, the capability information may include supported configuration for the beam report, such as the maximum number of the best beams to report, the maximum number of time reporting instances of the downlink reference signals, the maximum number of beam measurements for each time reporting instance, a minimum processing for the beam report, the supported time domain behavior for the beam report, etc. The network entity 104 may configure the data collection based on the UE’s capability information.
The UE receives 1104, from the network entity, a control signaling for configuring a set of channel measurement resources (CMRs) and a report for data collection associated with machine learning based beam management. For example, referring to FIG. 4, the UE 102 receives 404, from the network entity 104, control signaling configuring beam measurements of one or more sets of channel measurement resources CMRs and a beam report based on the beam measurements. In one implementation, the report may represent the data collection used for machine learning based beam management. In one implementation, the network entity 104 may configure at least one CSI report configuration for data collection by RRC signaling, e.g., RRCReconfiguration, where the network entity may configure at least one set of downlink reference signals, e.g., SSB or CSI-RS, as CMR. The network entity may further configure the report quantity for the data collection by RRC signaling. The report quantity may include the content and the time domain behavior of the CSI report such as the number, frequency, timing, etc., of the beam quality measurements. For periodic report, the network entity may further configure the periodicity and the slot offset for the report.
The UE receives 1106, from the network entity, a trigger to receive the set of CMRs or to transmit the report. For example, referring to FIG. 4, the UE 102 receives 406, from the network entity 104, a trigger signaling to receive the one or more sets of CMRs or to transmit the beam report. In one implementation, for semi-persistent report or aperiodic report, the network entity 104 may transmit a MAC CE or DCI to trigger the beam report. For semi-persistent downlink reference signal or aperiodic downlink reference signal, the network entity 104 may transmit a MAC CE or DCI to trigger the downlink reference signals.
The UE receives 1110, from the network entity, downlink reference signals via the set of CMRs. For example, referring to FIG. 4, the UE 102 receives 410, from the network entity 104, one or more sets of CMRs for the beam measurements. The CMRs may contain downlink reference signals such as SSB and/or CSI-RS.
The UE transmits 1112, to the network entity, the report based on beam measurements corresponding to the downlink reference signals. For example, referring to FIG. 4, the UE transmits 412, to the network entity 104, the beam report based on the beam measurements to provide beam quality data corresponding to the one or more sets of CMRs for supporting machine learning based beam management. In one implementation, the beam report may be based on the configured report quantity and the received downlink reference signals.
FIG. 11 describes a method from a UE-side of a wireless communication link, whereas FIG. 12 describes a method from a network-side of the wireless communication link.
FIG. 12 is a flowchart 1200 of a method of wireless communication at a network entity for transmitting CMRs and receiving beam measurements of the CMRs in a beam report to support network-side machine learning based beam management according to an embodiment. With reference to FIGs. 1, 4, and 14, 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 1406, a DU processor 1426, a CU processor 1446, etc. The one or more network entities 104 may include memory 1406’ /1426’ /1446’ , 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 1406, the DU processor 1426, or the CU processor 1446.
The network entity receives 1202, from a UE, UE capability information on supported configuration for a beam report for data collection associated with machine learning based beam management. For example, referring to FIG. 4, the network entity 104 receives 402, from the UE 102, UE capability on supported configuration for a beam report for data collection. In one implementation, the capability information may include supported configuration for the beam report, such as the maximum number of the best beams to report, the maximum number of time reporting instances of the downlink reference signals, the maximum number of beam measurements for each time reporting instance, a minimum processing for the beam report, the supported time domain behavior for the beam report, etc. The network entity 104 may configure the data collection based on the UE’s capability information.
The network entity transmits 1204, to the UE, a control signaling for configuring a set of channel measurement resources (CMRs) and a report for data collection associated with machine learning based beam management. For example, referring to FIG. 4, the network entity 104 transmits 404, to the UE 102, control signaling configuring beam measurements of one or more sets of channel measurement resources CMRs and a beam report based on the beam measurements. In one implementation, the report may represent the data collection used for machine learning based beam management. In one implementation, the network entity 104 may configure at least one CSI report configuration for data collection by RRC signaling, e.g., RRCReconfiguration, where the network entity may configure at least one set of downlink reference signals, e.g., SSB or CSI-RS, as CMR. The network entity may further configure the report quantity for the data collection by RRC signaling. The report quantity may include the content and the time domain behavior of the CSI report such as the number, frequency, timing, etc., of the beam quality measurements. For periodic report, the network entity may further configure the periodicity and the slot offset for the report.
The network entity transmits 1206, to the UE, a trigger to receive the set of CMRs or to transmit the report. For example, referring to FIG. 4, the network entity 104 transmits 406, to the UE 102, a trigger signaling to receive the one or more sets of CMRs or to transmit the beam report. In one implementation, for semi-persistent report or aperiodic report, the network entity 104 may transmit a MAC CE or DCI to trigger the beam report. For semi-persistent downlink reference signal or aperiodic downlink reference signal, the network entity 104 may transmit a MAC CE or DCI to trigger the downlink reference signals.
The network entity transmits 1210, to the UE, downlink reference signals via the set of CMRs. For example, referring to FIG. 4, the network entity 104 transmits 410, to the UE 102, one or more sets of CMRs for the beam measurements. The CMRs may contain downlink reference signals such as SSB and/or CSI-RS.
The network entity receives 1212, from the UE, the report based on beam measurements corresponding to the downlink reference signals. For example, referring to FIG. 4, the network entity 104 receives 412, from the UE 102, the beam report based on the beam measurements to provide beam quality data corresponding to the one or more sets of CMRs for supporting machine learning based beam management. In one implementation, the beam report may be based on the configured report quantity and the received downlink reference signals.
A UE apparatus 1302, as described in FIG. 13, may perform the method of flowchart 1100. The one or more network entities 104, as described in FIG. 14, may perform the method of flowchart 1200.
FIG. 13 is a diagram 1300 illustrating a hardware implementation for an example UE apparatus 1302 according to some embodiments. The UE apparatus 1302 may be the UE 102, a component of the UE 102, or may implement UE functionality. The UE apparatus 1302 may include an application processor 1306, which may have on-chip memory 1306’ . In examples, the application processor 1306 may be coupled to a secure digital (SD) card 1308 and/or a display 1310. The application processor 1306 may also be coupled to a sensor (s) module 1312, a power supply 1314, an additional module of memory 1316, a camera 1318, and/or other related components. For example, the sensor (s) module 1312 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 1302 may further include a wireless baseband processor 1326, which may be referred to as a modem. The wireless baseband processor 1326 may have on-chip memory 1326'. Along with, and similar to, the application processor 1306, the wireless baseband processor 1326 may also be coupled to the sensor (s) module 1312, the power supply 1314, the additional module of memory 1316, the camera 1318, and/or other related components. The wireless baseband processor 1326 may be additionally coupled to one or more subscriber identity module (SIM) card (s) 1320 and/or one or more transceivers 1330 (e.g., wireless RF transceivers) .
Within the one or more transceivers 1330, the UE apparatus 1302 may include a Bluetooth module 1332, a WLAN module 1334, an SPS module 1336 (e.g., GNSS module) , and/or a cellular module 1338. The Bluetooth module 1332, the WLAN module 1334, the SPS module 1336, and the cellular module 1338 may each include an on-chip transceiver (TRX) , or in some cases, just a transmitter (TX) or just a receiver (RX) . The Bluetooth module 1332, the WLAN module 1334, the SPS module 1336, and the cellular module 1338 may each include dedicated antennas and/or utilize antennas 1340 for communication with one or more other nodes. For example, the UE apparatus 1302 can communicate through the transceiver (s) 1330 via the antennas 1340 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 1326 and the application processor 1306 may each include a computer-readable medium /memory 1326', 1306', respectively. The additional module of memory 1316 may also be considered a computer-readable medium /memory. Each computer-readable medium /memory 1326', 1306', 1316 may be non-transitory. The wireless baseband processor 1326 and the application processor 1306 may each be responsible for general processing, including execution of software stored on the computer-readable medium /memory 1326', 1306', 1316. The software, when executed by the wireless baseband processor 1326 /application processor 1306, causes the wireless baseband processor 1326 /application processor 1306 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 1326 /application processor 1306 when executing the software. The wireless baseband processor 1326 /application processor 1306 may be a component of the UE 102. The UE apparatus 1302 may be a processor chip (e.g., modem and/or application) and include just the wireless baseband processor 1326 and/or the application processor 1306. In other examples, the UE apparatus 1302 may be the entire UE 102 and include the additional modules of the apparatus 1302.
As discussed in FIG. 1 and implemented with respect to FIG. 11, the data collection for network-side machine learning based beam management component 140 (also referred to as ML data collection component 140) is configured to receive, from a network entity, a signaling for configuring a set of channel measurement resources (CMRs) and a report for data collection associated with machine learning based beam management; receive, from the network entity, downlink reference signals via the set of CMRs; and transmit, to the network entity, the report based on beam measurements corresponding to the downlink reference signals.
The ML data collection component 140 may be within the application processor 1306 (e.g., at 140a) , the wireless baseband processor 1326 (e.g., at 140b) , or both the application processor 1306 and the wireless baseband processor 1326. 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. 14 is a diagram 1400 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 1446, which may have on-chip memory 1446'. In some aspects, the CU 110 may further include an additional module of memory 1456 and/or a communications interface 1448, both of which may be coupled to the CU processor 1446. The CU 110 can communicate with the DU 108 through a midhaul link 162, such as an F1 interface between the communications interface 1448 of the CU 110 and a communications interface 1428 of the DU 108.
The DU 108 may include a DU processor 1426, which may have on-chip memory 1426'. In some aspects, the DU 108 may further include an additional module of memory 1436 and/or the communications interface 1428, both of which may be coupled to the DU processor 1426. The DU 108 can communicate with the RU 106 through a fronthaul link 160 between the communications interface 1428 of the DU 108 and a communications interface 1408 of the RU 106.
The RU 106 may include an RU processor 1406, which may have on-chip memory 1406'. In some aspects, the RU 106 may further include an additional module of memory 1416, the communications interface 1408, and one or more transceivers 1430, all of which may be coupled to the RU processor 1406. The RU 106 may further include antennas 1440, which may be coupled to the one or more transceivers 1430, such that the RU 106 can communicate through the one or more transceivers 1430 via the antennas 1440 with the UE 102.
The on-chip memory 1406', 1426', 1446'a nd the additional modules of memory 1416, 1436, 1456 may each be considered a computer-readable medium/memory. Each computer-readable medium/memory may be non-transitory. Each of the processors 1406, 1426, 1446 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) 1406, 1426, 1446 causes the processor (s) 1406, 1426, 1446 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) 1406, 1426, 1446 when executing the software. In examples, the network-side machine learning based beam management 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 network-side machine learning based beam management configuration component 150 (also referred to as ML data collection configuration component 150) is configured to transmit, to a UE, a signaling for configuring a set of channel measurement resources (CMRs) and a report for data collection associated with machine learning based beam management; transmit, to the UE, downlink reference signals via the set of CMRs; and receive, from the UE, the report based on beam measurements corresponding to the downlink reference signals.
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 1406 (e.g., at 150a) , the DU processor 1426 (e.g., at 150b) , and/or the CU processor 1446 (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 1406, 1426, 1446 configured to perform the stated processes/algorithm, stored within a computer-readable medium for implementation by the one or more processors 1406, 1426, 1446, 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 for configuring a set of channel measurement resources (CMRs) and a report for data collection associated with machine learning based beam management; receiving, from the network entity, downlink reference signals via the set of CMRs; and transmitting, to the network entity, the report based on beam measurements corresponding to the downlink reference signals.
Example 2 may be combined with Example 1 and includes that the report includes beam quality data for all or a subset of the downlink reference signals from a first set of CMRs or a second set of CMRs.
Example 3 may be combined with Example 2 and includes that the report further includes a beam index identifying one of the downlink reference signals having best beam quality data among the downlink reference signals from the first set of CMRs or the second set of CMRs.
Example 4 may be combined with Examples 2 or 3, and includes that the report further includes multiple reports. Each report includes the beam quality data or the beam indexes corresponding to a respective one of the first set of CMRs or the second set of CMRs.
Example 5 may be combined with Examples 2 or 3, and includes that the report further includes the beam quality data corresponding to the beam indexes identifying the downlink reference signals having the best beam quality data from the first set of CMRs or the second set of CMRs.
Example 6 may be combined with any one of Examples 1-5, and includes that the signaling further configures at least one of: multiple time reporting instances before a reference time for reporting beam quality data in the report; multiple measurement instances before the reference time for measuring the downlink reference signals for each of the time reporting instances; or a total number of measurement instances before the reference time for measuring the downlink reference signals for the time reporting instances.
Example 7 may be combined with Example 6, and includes transmitting, to the network entity, capability of the UE on supported configuration for the data collection associated with machine learning based beam management. The capability includes at least one of: a maximum value of the time reporting instances; a maximum value of the measurement instances for each of the time reporting instance; a maximum value of the total measurement instances for all of the time reporting instances; a maximum number of the downlink reference signals having best beam quality data to report; a maximum product of the time reporting instances and the number of the downlink reference signals having best beam quality data; a maximum product of the measurement instances for each of the time reporting instance and the number of the downlink reference signals having best beam quality data; a maximum product of the total measurement instances for all of the time reporting instances and the number of the downlink reference signals having best beam quality data; or a minimum processing time for the report.
Example 8 may be combined with any one of Examples 1-7, and includes that the signaling further includes a measurement window for measuring the downlink reference signals to generate beam quality data.
Example 9 may be combined with Example 8, and includes that the measurement window includes periodic measurement windows for measuring the downlink reference signals at multiple measurement instances. The signaling further includes a periodicity of the periodic measurement windows; a slot offset for a start of each of the periodic measurement windows; and a duration of each of the periodic measurement windows.
Example 10 may be combined with any one of Examples 1-9, and includes that receiving the downlink reference signals via the set of CMRs includes receiving the downlink reference signals using a UE receive beam configured by a first spatial receiving parameter associated with the set of CMRs.
Example 11 may be combined with Example 10, and includes when the set of CMRs overlaps in time with a second downlink signal associated with a second spatial receiving parameter different from the first spatial receiving parameter, the UE receive beam is configured based on a priority rule between the first spatial receiving parameter and the second spatial receiving parameter.
Example 12 may be combined with Example 11, and includes refraining from receiving the downlink reference signals using the receiving beam that is configured by the second spatial receiving parameter based on the priority rule.
Example 13 may be combined with any one of Examples 1-12, and includes receiving, from the network entity (104) , a trigger to receive the set of CMRs or to transmit the report.
Example 14 may be combined with any one of Examples 2-13, and includes that the beam quality data corresponding to the downlink reference signals in the report includes at least one of: a layer-1 reference signal received power (L1-RSRP) for one of the downlink reference signals; a layer-1 signal-to-interference-plus-noise ratio (L1-SINR) for one of the downlink reference signals; or a hypothetical measurement error for one of the downlink reference signals.
Example 15 may be combined with Example 14, and includes that the beam quality data for one of the downlink reference signals is reported in the report when one of the L1-RSRP or the L1-SINR or the hypothetical measurement error for the downlink reference signals meets reporting criteria.
Example 16 may be combined with Example 15, and includes that the reporting criteria include at least one of: the L1-RSRP for the downlink reference signal is above a first threshold; the L1-SINR for the downlink reference signal is above a second threshold; or a hypothetical measurement error for the downlink reference signal is below a third threshold.
Example 17 is a method of wireless communication at a network entity, including: transmitting, to a user equipment, a signaling for configuring a set of channel measurement resources (CMRs) and a report for data collection associated with machine learning based beam management at the network entity; transmitting, to the UE, downlink reference signals via the set of CMRs; and receiving, from the UE, the report based on beam measurements corresponding to the downlink reference signals.
Example 18 may be combined with Example 17, and includes that the report includes beam quality data for all or a subset of the downlink reference signals from a first set of CMRs or a second set of CMRs.
Example 19 may be combined with Example 18, and includes that the report further includes beam indexes identifying one of the downlink reference signals having best beam quality data among the downlink reference signals from the first set of CMRs or the second set of CMRs.
Example 20 may be combined with Examples 18 or 19, and includes that the report includes multiple reports. Each report includes the beam quality data or the beam indexes corresponding to a respective one of the first set of CMRs or the second set of CMRS.
Example 21 may be combined with any one of Examples 17-20, and includes that the signaling further includes at least one of: multiple time reporting instances before a reference time for reporting beam quality data in the report; multiple measurement instances before the reference time for measuring the downlink reference signals for each of the time reporting instances; or a total number of measurement instances before the reference time for measuring the downlink reference signals for the time reporting instances.
Example 22 may be combined with any one of Examples 18-21, and includes that the beam quality data corresponding to the downlink reference signals in the report includes at least one of: a layer-1 reference signal received power (L1-RSRP) for one of the downlink reference signals; a layer-1 signal-to-interference-plus-noise ratio (L1-SINR) for one of the downlink reference signals; or a hypothetical measurement error for one of the downlink reference signals.
Example 23 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 1-22.
Example 24 may be combined with Examples 2 or 3, and includes that the first set of CMRs and the second set of CMRs are carried on beams having the same beam characteristics or different beam characteristics.
Example 25 may be combined with Example 6, and includes that the signaling configures the multiple measurement instances. The beam quality data for each of the time reporting instances includes an average of the beam measurements made at the measurement instances.
Example 26 may be combined with Example 6, and includes that the reference time is determined based on: a first symbol of the beam report and a minimum processing time for the beam report; or configuration information from the network entity.
Example 27 may be combined with Example 11, and includes that the signaling from the network entity further configures the priority rule.
Example 28 may be combined with Example 11, and includes receiving the one or more sets of CMRs using the receiving beam that is configured by the second receiving parameters based on the priority rule.
Example 29 may be combined with Example 15, and includes that the signaling further configures the reporting criteria.
Example 30 may be combined with Examples 18 or 19, and includes that the first set of CMRs and the second set of CMRs are carried on beams having the same beam characteristics or different beam characteristics.
Example 31 may be combined with Examples 18 or 19, and includes that the beam report further includes the beam quality data corresponding to the beam indexes identifying the downlink reference signals having the best beam quality data from the first set of CMRs or the second set of CMRs.
Example 32 may be combined with Example 21, and includes that the signaling configures the multiple measurement instances. The beam quality data for each of the time reporting instances includes an average of the beam measurements made at the measurement instances.
Example 33 may be combined with Example 21, and includes that the signaling further configures the reference time.
Example 34 may be combined with Example 21, and includes receiving, from the UE, capability of the UE on supported configuration for the data collection associated with machine learning based beam management. The capability includes at least one of: a maximum value of the time reporting instances; a maximum value of the measurement instances for each of the time reporting instance; a maximum value of the total measurement instances for all of the time reporting instances; a maximum number of the downlink reference signals having best beam quality data to report; a maximum product of the time reporting instances and the number of the downlink reference signals having best beam quality data; a maximum product of the measurement instances for each of the time reporting instance and the number of the downlink reference signals having best beam quality data; a maximum product of the total measurement instances for all of the time reporting instances and the number of the downlink reference signals having best beam quality data; or a minimum processing time for the report.
Example 35 may be combined with Example 17, and includes that the signaling further configures a measurement window for the UE to measure downlink reference signals to generate beam quality data.
Example 36 may be combined with Example 35, and includes that the measurement window includes periodic measurement windows for the UE to measure the downlink reference signals at multiple measurement instances. The signaling further includes a periodicity of the periodic measurement windows; a slot offset for a start of each of the periodic measurement windows; and a duration of each of the periodic measurement windows.
Example 37 may be combined with Example 17, and includes that when the set of CMRs overlaps in time with a second downlink signal associated with a second spatial receiving parameter that is from a first spatial receiving parameter used by the UE to configure a receive beam to receive the downlink reference signals, the receive beam is configured based on a priority rule between the first spatial receiving parameter and the second spatial receiving parameter.
Example 38 may be combined with Example 17, and includes that the network entity refrains from transmitting the set of CMRs that overlap in time a second downlink signal associated with a different spatial receiving parameter configuration used by the UE to configure receive beams.
Example 39 may be combined with Example 17, and includes transmitting, to the UE, a trigger to receive the set of CMRs or to transmit the report.
Example 40 may be combined with Example 22, and includes that the beam quality data for one or more of the downlink reference signals is contained in the beam report when one or more of the L1-RSRP or the L1-SINR or the hypothetical measurement error for the downlink reference signals meet reporting criteria.
Example 41 may be combined with Example 40, and includes that the reporting criteria include at least one of: the L1-RSRP for the downlink reference signal is above a first threshold; the L1-SINR for the downlink reference signal is above a second threshold; or a hypothetical measurement error for the downlink reference signal is below a third threshold.
Example 42 may be combined with Example 40, and includes that the signaling further configures the reporting criteria.
Example 43 may be combined with Example 4, and includes that the beam quality data in a first report are applied as input data to a machine learning model for beam management and the beam indexes in a second report are applied as output data to the machine learning model.
Example 44 may be combined with Example 20, and includes that the beam quality data in a first report are applied as input data to a machine learning model for beam management and the beam indexes in a second report are applied as output data to the machine learning model.

Claims

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

receiving (1104) , from a network entity (104) , a signaling for configuring:

a set of channel measurement resources (CMRs) ; and

a report for data collection associated with machine learning based beam management;

receiving (1110) , from the network entity (104) , downlink reference signals via the set of CMRs; and

transmitting (1112) , to the network entity (104) , the report based on beam measurements corresponding to the downlink reference signals.
The method of claim 1, wherein the report comprises beam quality data for all or a subset of the downlink reference signals from a first set of CMRs or a second set of CMRs.
The method of claim 2, wherein the report further comprises a beam index identifying one of the downlink reference signals having best beam quality data among the downlink reference signals from the first set of CMRs or the second set of CMRs.
The method of any of claims 2 or 3, wherein the report comprises multiple reports each including the beam quality data or the beam indexes corresponding to a respective one of the first set of CMRs or the second set of CMRs.
The method of any of claim 2 or 3, wherein the report further comprises the beam quality data corresponding to the beam indexes identifying the downlink reference signals having the best beam quality data from the first set of CMRs or the second set of CMRs.
The method of any one of claims 1-5, wherein the signaling further configures at least one of:

a plurality of time reporting instances before a reference time for reporting beam quality data in the report;

a plurality of measurement instances before the reference time for measuring the downlink reference signals for each of the time reporting instances; or

a total number of measurement instances before the reference time for measuring the downlink reference signals for the time reporting instances.
The method of claim 6, further comprising:

transmitting (1102) , to the network entity (104) , capability of the UE (102) on supported configuration for the data collection associated with machine learning based beam management comprising at least one of:

a maximum value of the time reporting instances;

a maximum value of the measurement instances for each of the time reporting instance;

a maximum value of the total measurement instances for all of the time reporting instances;

a maximum number of the downlink reference signals having best beam quality data to report;

a maximum product of the time reporting instances and the number of the downlink reference signals having best beam quality data;

a maximum product of the measurement instances for each of the time reporting instance and the number of the downlink reference signals having best beam quality data;

a maximum product of the total measurement instances for all of the time reporting instances and the number of the downlink reference signals having best beam quality data; or

a minimum processing time for the report.
The method of any one of claims 1-7, wherein the signaling further configures a measurement window for measuring the downlink reference signals to generate beam quality data.
The method of claim 8, wherein the measurement window comprises periodic measurement windows for measuring the downlink reference signals at a plurality of measurement instances, and wherein the signaling further configures:

a periodicity of the periodic measurement windows;

a slot offset for a start of each of the periodic measurement windows; and

a duration of each of the periodic measurement windows.
The method of any one of claims 1-9, wherein receiving the downlink reference signals via the set of CMRs comprises:

receiving the downlink reference signals using a UE receive beam configured by a first spatial receiving parameter associated with the set of CMRs.
The method of claim 10, wherein when the set of CMRs overlaps in time with a second downlink signal associated with a second spatial receiving parameter different from the first spatial receiving parameter, the UE receive beam is configured based on a priority rule between the first spatial receiving parameter and the second spatial receiving parameter.
The method of claim 11, further comprising:

refraining from receiving the downlink reference signals using the receiving beam that is configured by the second spatial receiving parameter based on the priority rule.
The method of any one of claims 1-12, further comprising:

receiving (1108) , from the network entity (104) , a trigger to receive the set of CMRs or to transmit the report.
The method of any one of claims 2-13, wherein the beam quality data corresponding to the downlink reference signals in the report comprise at least one of:

a layer-1 reference signal received power (L1-RSRP) for one of the downlink reference signals;

a layer-1 signal-to-interference-plus-noise ratio (L1-SINR) for one of the downlink reference signals; or

a hypothetical measurement error for one of the downlink reference signals.
The method of claim 14, wherein the beam quality data for one of the downlink reference signals is reported in the report when one of the L1-RSRP or the L1-SINR or the hypothetical measurement error for the downlink reference signals meets reporting criteria.
The method of claim 15, wherein the reporting criteria comprise at least one of:

the L1-RSRP for the downlink reference signal is above a first threshold;

the L1-SINR for the downlink reference signal is above a second threshold; or

a hypothetical measurement error for the downlink reference signal is below a third threshold.
A method of wireless communication at a network entity (104) , comprising:

transmitting (1204) , to a user equipment (UE) (102) , a signaling for configuring:

a set of channel measurement resources (CMRs) ; and

a report for data collection associated with machine learning based beam management on the network entity (104) ;

transmitting (1210) , to the UE (102) , downlink reference signals via the sets of CMRs; and

receiving (1212) , from the UE (102) , the report based on beam measurements corresponding to the downlink reference signals.
The method of claim 17, wherein the report comprises beam quality data for all or a subset of the downlink reference signals from a first set of CMRs or a second set of CMRs.
The method of claim 18, wherein the report further comprises beam indexes identifying one of the downlink reference signals having best beam quality data among the downlink reference signals from the first set of CMRs or the second set of CMRs.
The method of any of claims 18 or 19, wherein the report comprises multiple reports each including the beam quality data or the beam indexes corresponding to a respective one of the first set of CMRs or the second set of CMRs.
The method of any one of claims 17-20, wherein the signaling further configures at least one of:

a plurality of time reporting instances before a reference time for reporting beam quality data in the report;

a plurality of measurement instances before the reference time for measuring the downlink reference signals for each of the time reporting instances; or

a total number of measurement instances before the reference time for measuring the downlink reference signals for the time reporting instances.
The method of any one of claims 18-21, wherein the beam quality data corresponding to the downlink reference signals in the report comprise at least one of:

a layer-1 reference signal received power (L1-RSRP) for one of the downlink reference signals;

a layer-1 signal-to-interference-plus-noise ratio (L1-SINR) for one of the downlink reference signals; or

a hypothetical measurement error for one of the downlink reference signals.
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 1-22.