Event-based beam report based on machine learning prediction
A machine learning-based event-triggered beam reporting system in wireless communication optimizes reporting by predicting beam conditions, reducing overhead and maintaining connectivity through proactive reporting.
Patent Information
- Application Number
- PCT/CN2024/086257
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-04-05
- Publication Date
- 2025-10-09
AI Technical Summary
Existing wireless communication systems face inefficiencies in beam reporting, leading to increased signaling overhead and power consumption due to periodic or semi-persistent reporting, which can lead to beam failure in certain scenarios.
Implementing a machine learning-based approach for event-triggered beam reporting, where a user equipment (UE) uses machine learning models to predict beam characteristics and generate reports only when specific conditions are met, reducing unnecessary reporting and optimizing connectivity.
The solution reduces signaling overhead and power consumption while maintaining network connectivity by allowing the UE to proactively generate beam reports based on predicted metrics, thereby avoiding potential beam failures.
Smart Images

Figure CN2024086257_09102025_PF_FP_ABST
Abstract
Description
EVENT-BASED BEAM REPORT BASED ON MACHINE LEARNING PREDICTIONTECHNICAL FIELD
[0001] This disclosure relates generally to wireless communication and some aspects relate to an event-based beam report based on machine learning prediction.BACKGROUND
[0002] This background description is provided for the purpose of generally presenting the context of the disclosure. Work of the presently named inventors, to the extent it is described in this background section, as well as aspects of the description that may not otherwise qualify as prior art at the time of filing, are neither expressly nor impliedly admitted as prior art against the present disclosure.
[0003] Beamforming is a technique that can enhance the signal quality between a network entity and a user equipment (UE) thereby improving data rates, reducing latency, and increasing overall network performance. In beamforming, the transmitter (e.g., the network entity) directs radio frequency (RF) transmission towards a specific direction (e.g., towards an intended receiver, such as the UE) , creating a "beam" of focused energy, rather than radiating the signal in all directions equally. The UE and the network entity measure various characteristics of reference signals and communicate with one another to determine an optimal beam for communications. The network entity can configure a report configuration with triggering conditions to cause the UE to send an event-based beam report (also referred to as an “event-triggered beam report” or “UE-initiated beam report” ) when the UE measures channel metrics that satisfy the triggering conditions or detects an occurrence of an event that satisfies the triggering condition.
[0004] BRIEF SUMMARY
[0005] The systems, methods, and apparatuses of this disclosure each have several innovative aspects, no single one of which is solely responsible for the desirable attributes disclosed herein.
[0006] One innovative aspect of the subject matter described in this disclosure can be implemented as a method for wireless communication by a user equipment (UE) . The method includes receiving, from a network entity, a configuration that configures an event-based beam report based on a machine learning model, at least one event triggering the event-based beam report, and one or more downlink reference signals. The method also includes receiving, from the network entity, the one or more downlink reference signals. The method also includes detecting at least one event based on an output of the machine learning model, an input of the machine learning model including measurements of the one or more downlink reference signals, the output of the machine learning model including one or more predicted metrics or the at least one event. And, the method also includes transmitting, to the network entity, the event-based beam report based on the at least one event.
[0007] Another innovative aspect of the subject matter described in this disclosure can be implemented as a method for wireless communication by a network entity. The method includes transmitting, to a UE, a configuration that configures an event-based beam report based on a machine learning model, at least one event triggering the event-based beam report, and one or more downlink reference signals. The method also includes transmitting, to the UE, the one or more downlink reference signals. And, the method also includes receiving, from the UE, the event-based beam report based on one or more of at least one event predicted by the machine learning model or one or more predicted metrics associated with one or more predicted beams.
[0008] Another innovative aspect of the subject matter described in this disclosure can be implemented as an apparatus that includes a communication unit and a processing system configured to control the communication unit to implement any one of the above-referenced methods.
[0009] Details of one or more implementations of the subject matter described in this disclosure are set forth in the accompanying drawings and the description below. Other features, aspects, and advantages will become apparent from the description, the drawings, and the claims.BRIEF DESCRIPTION OF THE DRAWINGS
[0010] Like reference numbers and designations in the various drawings indicate like elements. Note that the relative dimensions of the figures may not be drawn to scale. To easily identify the discussion of any particular element or act, the most significant digit or digits in a reference number refer to the figure number in which that element is first introduced.
[0011] FIG. 1 is a diagram illustrating an example wireless system including a user equipment (UE) communicating with a network entity.
[0012] FIG. 2A is a sequence diagram illustrating operations of a first example, communications process for machine learning-based event triggered beam report.
[0013] FIG. 2B is a sequence diagram illustrating operations of a second example, communications process for machine learning-based event triggered beam report.
[0014] FIG. 2C is a sequence diagram illustrating operations of a third example, communications process for machine learning-based event triggered beam report.
[0015] FIG. 3 is a timing diagram illustrating an example machine learning-based event trigger and beam report.
[0016] FIG. 4 is a block diagram illustrating an example channel prediction module.
[0017] FIG. 5 is a flow chart diagram illustrating first example UE operations for a machine learning-based event trigger and beam report.
[0018] FIG. 6 is a flow chart diagram illustrating example network entity operations for a machine learning-based event trigger and beam report.
[0019] FIG. 7 is a flow chart diagram illustrating second example UE operations for a machine learning-based event trigger and beam report.
[0020] FIG. 8 is a block diagram illustrating example configurations of a network entity and a user equipment.DETAILED DESCRIPTION
[0021] The following description is directed to certain implementations for the purpose of describing innovative aspects of this disclosure. However, a person having ordinary skill in the art will readily recognize that the teachings herein can be applied in a multitude of different ways. Some of the examples in this disclosure are based on wireless communication according to the 3rd Generation Partnership Project (3GPP) wireless standards, such as ambient internet-of-things (A-IoT) , the 4th generation (4G) Long Term Evolution (LTE) and 5th generation (5G) New Radio (NR) standards. However, the described implementations can be implemented in any device, system, or network that is capable of transmitting and receiving radio frequency signals according to any of the wireless communication standards, including any of the Institute of Electrical and Electronics Engineers (IEEE) 802.11 or 802.16 wireless standards, or other known signals that are used to communicate within a wireless, cellular, or IoT network, such as a system utilizing 4G, 5G, 6G, ZigBee, Bluetooth, WiFi, or future radio technology.
[0022] This disclosure provides systems, methods and apparatuses where, according to aspects of the disclosure, a UE uses machine learning (ML) techniques for temporal domain prediction, spatial domain prediction, or other prediction of a beam characteristic that can trigger an event-based beam report. For example, the UE can predict future qualities of a beam based on measurements of the beam in the past (temporal domain prediction) or predict a beam that has the possibility to be the best beam based on current measurements of another beam (spatial domain prediction) .
[0023] The network entity can transmit downlink reference signals (RSs) associated with candidate beams. In some implementations, the RSs can include channel state information RSs (CSI-RSs) or synchronization signal blocks (SSBs) . The UE provides measurements of the RSs to a machine learning model. The machine learning model can use the current measurements and past measurements of the RSs to predict future channel metrics and / or beam metrics (collectively referred to as “predicted metrics” ) or to predict current channel metrics for a different beam. The UE can determine whether the predicted metrics satisfy a condition for triggering the UE to generate and provide an event-based beam report to the network. In some aspects, the UE proactively generates an event-based beam report before the triggering condition is actually met, such as based on a prediction from the machine learning (or a separate model trained for generating reports) . In some aspects, the UE might modify the contents of the event-based beam report and / or the uplink (UL) resources used for the event-based beam report based on the ML prediction.
[0024] In some aspects, the UE uses machine learning techniques applied to past measurements of beam characteristics for temporal based event detection. In this case, the event may be related to predicted future characteristics of beams associated with the RSs. In some aspects, the UE performs machine learning techniques applied to current (and / or past) measurements of beam characteristics for spatial-domain based event detection. In this case, the event may be related to current characteristics of a first set of one or more beams. The UE may utilize the machine learning model to predict current characteristics of a second set of one or more beams. Further, the UE may utilize machine learning techniques to determine a confidence of the prediction. The UE may determine to utilize actual measurements of beam characteristics rather than predicted characteristics when the confidence of the prediction is low (e.g., below a threshold) . When the confidence of the prediction is high (e.g., above the threshold) , the UE can skip making actual measurements, thereby reducing overhead on the UE.
[0025] Particular implementations of the subject matter described in this disclosure can be implemented to realize one or more of the following potential advantages. One potential technical advantage of the techniques of this disclosure is that through the use of machine learning techniques, the UE may be able to generate and send beam reports on an as needed basis rather than using periodic or semi-persistent beam reporting, thereby reducing overhead related to beam reports. Therefore, the techniques of this disclosure can reduce signaling overhead and power consumption. A potential technical advantage of using predicted channel metrics for event-based beam reporting is that the UE can maintain connectivity to the network entity in scenarios where beam failure might otherwise occur.
[0026] FIG. 1 is a diagram illustrating an example wireless system 100 including a user equipment (UE) 130 communicating with a network entity 120. Although illustrated as a smartphone in Figure 1, the UE 130 may be implemented as any suitable computing or electronic device, such as a mobile communication device, a modem, cellular phone, gaming device, navigation device, media device, laptop computer, desktop computer, tablet computer, smart appliance, vehicle-based communication system, an Internet-of-things (IoT) device (e.g., sensor node, controller / actuator node, combination thereof) , and the like. The UE 130 may communicate with network entity 120 using wireless links (not shown in Figure 1) , which may be implemented as any suitable type of wireless link. The wireless links may include one or more wireless links (e.g., radio links) or bearers implemented using any suitable communication protocol or standard, or combination of communication protocols or standards, such as 3GPP LTE, 5G NR, and so forth. Multiple wireless links may be aggregated in a carrier aggregation to provide a higher data rate for communication between the UE 130 and the network entity 120.
[0027] As an example, the network entity 120 may be a base station, an Evolved Universal Terrestrial Radio Access Network Node B (E-UTRAN Node B) , evolved Node B (eNodeB or eNB) , Next Generation Node B (gNodeB or gNB) , Next Generation E-UTRAN Node Be (ng-eNB) , access point, radio head or the like. The network entity 120 may be implemented in a macrocell, microcell, small cell, picocell, or the like, or any combination thereof. The network entity 120 may be configured to use multiple-input-multiple-output (MIMO) communication to exchange wireless signals with the UE 130.
[0028] The network entity 120 supports wireless communication with one or more UEs, such as the UE 130, via radio frequency (RF) signaling using one or more applicable radio access technologies (RATs) as specified by one or more communications protocols or standards. The network entity 120 may employ any of a variety of RATs, such as operating as a NodeB (or base transceiver station (BTS) ) for a Universal Mobile Telecommunications System (UMTS) RAT (also known as “3G” ) , operating as an eNB for a 3GPP LTE RAT, operating as a gNB for a 3GPP 5G NR RAT, and the like.
[0029] The network entity 120 may be part of a radio access network (RAN) , for example, an Evolved Universal Terrestrial Radio Access Network, E-UTRAN, 5G NR RAN, or NR RAN. The network entity 120 may be connected to a core network 150. For example, the network entity 120 may connect to the core network 150 through an NG2 interface for control-plane signaling and using an NG3 interface for user-plane data communications when connecting to a 5G core network or using an Si interface for control-plane signaling and user-plane data communications when connecting to an Evolved Packet Core (EPC) network. The network entity 120 may communicate using an Xn Application Protocol (XnAP) through an Xn interface or using an X2 Application Protocol (X2AP) through an X2 interface to exchange user-plane and control-plane data. A UE (e.g., UE 130) may connect, via the core network 150, to one or more wide area networks (WANs, e.g., WAN 160) or other packet data networks (PDNs) , such as the Internet.
[0030] In some aspects, the functionality, and thus the hardware components, of a network entity such as network entity 120 may be distributed across multiple network nodes or devices and may be distributed in a manner to perform the functions described herein. As one example, the functionality of a network entity (e.g., network entity 120) may be distributed across a radio unit (RU) , a distributed unit (DU) , or a central unit (CU) .
[0031] Communications between a network entity and a UE utilize an uplink (UL) transmission path for transmission path for RF transmissions from the UE to the network entity and a downlink (DL) transmission path for RF transmissions from the network entity to the UE. For example, as shown in Figure 1, the UE 130 utilizes UL transmission path 116 for RF transmissions from the UE 130 to the network entity 120 and DL transmission path 118 for RF transmissions from the network entity 120 to the UE 130. In the context of the UL transmission path 116, the UE 130 serves as the data sending device and the network entity 120 serves as the data receiving device, whereas in the context of the DL transmission path 118, the network entity 120 serves as the data sending device and the UE 130 serves as the data receiving device. UL transmission path 116 and DL transmission path 118 may utilize multiple communication channels for signal transmission. The multiple channels may each have different purposes.
[0032] UL transmission path 116 may include a physical uplink shared channel (PUSCH) , a physical uplink control channel (PUCCH) , and a physical random access channel (PRACH) . The PUSCH is used for the transmission of user data, such as voice data, video data, or text message data from the UE 130 to the network entity 120. Additionally, the PUSCH may be used to transmit control information (e.g., uplink control information (UCI) ) . The PUSCH may be shared by multiple UEs. The PUCCH is used for transmitting control information (e.g., UCI) from the UE to the network, such as channel quality feedback, scheduling requests, and acknowledgments. The PRACH is used for random access in the uplink direction, enabling the UE to access the system.
[0033] DL transmission path 118 may include one or more of a physical downlink shared channel (PDSCH) , a physical downlink control channel (PDCCH) , a physical broadcast channel (PBCH) , or a paging channel. The PDSCH is used for transmission of user data from the network entity 120 to the UE 130. The PDSCH may be shared by multiple UEs. As with the PUSCH, the data may be any type of information, such as voice data, video data, or text message data. The paging channel is used to notify a UE that there is incoming traffic for it from a network entity.
[0034] The network entity 120 and the UE 130 may be configured to use MIMO communication in which multiple beams 124 are used to exchange wireless communication signals with UE 130. The UE 130 and may send an event-based beam reports based on a machine learning model to the network entity to optimize the quality of communications between the UE 130 and network entity 120. According to aspects of the disclosure, the UE 130 may provide the network entity 120 with UE capability information 104 that indicates whether the UE 130 supports event-based beam reporting based on a machine learning model. The network entity 120 may, depending on the UE capability information 104, transmit configuration information 106 to the UE 130 that configures the UE 130 for event-based beam reporting based on a machine learning model.
[0035] The network entity 120 may transmit downlink reference signals (DL-RSs) 110 to the UE 130. The UE 130 may measure characteristics of the DL RS (s) 110 to produce one or more channel metrics and / or beam metrics. The UE 130 may provide the channel metrics and / or beam metrics as input to a machine learning model that has been trained to provide predicted metrics as output.
[0036] In some aspects, the UE 130 may detect an event based on the predicted metrics. For example, the UE 130 may detect an event based on thresholds and conditions associated with the predicted metrics. In some aspects, the UE 130 may detect an event based on an output of the machine learning model that is indicative of the event.
[0037] When an event is detected, the UE 130 may provide a beam report 128 to the network entity 120. The beam report may include an identifier of the event or events triggering the report, one or more predicted beam indexes such as a DL RS indexes or beam identifiers, one or more confidence levels for the predicted metrics or predicted beams and the like.
[0038] Further details of various techniques and aspects of disclosure are provided below with respect to FIGs. 2A, 2B, 2C, and 3-8.
[0039] FIG. 2A -FIG. 2C are sequence diagrams illustrating aspects and example operations of communications processes for a machine learning-based event triggered beam report. In the examples shown in FIG. 2A -FIG. 2C that follow, the operations may be described as utilizing radio resource control (RRC) signaling to configure the CSI report based on different types of CSI associated with multiple codebook configurations. The RRC signaling may indicate a RRC reconfiguration message from the network entity 120 to the UE 130, or a system information block (SIB) . The SIB can be an existing SIB (e.g., SIB1) or a new SIB (e.g., SIB J, where J is an integer above 21) transmitted by the network entity. Although not illustrated for the sake of illustration clarity, various acknowledgements for messages illustrated in FIG. 2A -FIG. 2C may be implemented to ensure reliable operations for measuring reference signals and providing machine-learning based event triggered beam reports.
[0040] FIG. 2A is a sequence diagram illustrating operations of a first example, communications process for a machine learning-based event triggered beam report. At operation 204, the UE 130 may optionally transmit or report to network entity 120 UE capability information regarding the UE’s capability or support for a machine learning-based event trigger and beam report. In some aspects, UE 130 may communicate UE capability information to the network entity 120 during an initial communication session setup process between the UE 130 and the network entity 120. The UE capability information may include supported frequency bands, radio access technologies, maximum transmission power, maximum data rates, and network protocols. In some aspects, the UE 130 may report UE capability information that includes supported configurations for machine learning-based event triggering and beam reporting. In some aspects, the configurations may include one or more of the following parameters: a minimum, maximum and / or supported number of DL RSs for event detection and beam reporting; a minimum, maximum and / or supported predicted duration for machine learning-based event triggering and beam reporting; a minimum, maximum and / or supported number of predicted beams for machine learning-based event triggering and beam reporting. In some aspects, the configurations may include indicators of the types of triggering events supported by the UE and / or the types of machine learning models supported by the UE.
[0041] In the example of FIG. 2A, the UE 130 transmits UE capability information to the network entity 120. In some implementations, the network entity 120 may receive the UE capability information from a core network (e.g., from an access and mobility management function (AMF) of the core network 150 of FIG. 1) . In some implementations, the network entity 120 may receive the UE capability information from another network entity (e.g., a gNB or eNB) .
[0042] At operation 206, the network entity 120 may, depending on the UE capability information received at operation 204, transmit to the UE configuration information that configures at least one event-based beam report based on a machine learning model, at least one event triggering the event-based beam report, and one or more DL reference signal (DL-RS) resources. The DL-RS resources may be SSB or CSI-RS resources for use in machine learning-based event detection and beam report generation. In some aspects, the configuration information may include triggering conditions that trigger the UE to generate a beam report. In some aspects, the configuration information may include one or more thresholds associated with one or more of the triggering conditions or events.
[0043] In some aspects, the configuration information includes a configuration of the beam report content. For example, the network entity 120 may configure the UE 130 to report one or more of a predicted beam index, a predicted metric, a predicted beam characteristic, or one or more predicted confidence levels associated with elements of the predicted beam report. In some aspects, the configuration information may include one or more uplink resources for the predicted beam report. For example, the configuration information may include one or more of a PUCCH, PUSCH, or PRACH for transmitting the predicted beam report to the network entity 120.
[0044] In some aspects, the configuration information may include one or more indicators of one or more machine learning models that the UE may use to detect events and / or generate predicted beam reports. For example, the configuration information may include a first indication indicating a machine learning model that the UE may use to detect events, and a second machine learning model that the UE used to generate report content. In some aspects, the configuration information may indicate a single ML model that the UE may use to both detect events and generate predicted beam report content. In some aspects, the configuration may include confidence levels or thresholds with respect to events and predicted metrics. In some aspects, the confidence levels may specify an error range. For example, the confidence level may specify a standard deviation of the prediction error or the probability that the predicted value is reliable within the error range.
[0045] In some aspects, the network entity 120 may transmit the configuration via radio resource control (RRC) signaling, e.g., RRCReconfiguration.
[0046] At operation 210, the network entity 120 may transmit the one or more DL references signals (DL-RSs) to the UE 130. In some aspects, the network entity 120 may transmit the DL-RS resources periodically (P) , semi-persistently (SP) , or aperiodically (AP) . In some aspects, one or more of the DL-RS resources may be quasi-co-located (QCLed) with, or configured as, a QCL source reference signal in a TCI state for a DL or UL channel.
[0047] At operation 212, the UE 130 may measure or determine metrics of the one or more DL-RSs received at operation 210. For example, the UE 130 may measure channel coefficients, channel quality metrics (e.g., precoding matrix indicator (PMI) , rank indicator (RI) , channel quality indicator (CQI) , layer indicator (LI) , reference signal received power (RSRP) , reference signal received quality (RSRQ) , received signal strength indicator (RSSI) , or signal-to-interference-plus-noise ratio (SINR) ) , and / or beam related metrics (e.g. beam index, DL-RS index, and RSRP) .
[0048] At operation 216, the UE 130 may predict channel metrics or beam metrics based on the measurements obtained at operation 212. For example, the UE 130 UE may execute a machine learning module that uses machine learning techniques to predict a value of a channel metric or a beam metric at a future time (referred to as a “predicted metric” ) . Like the metrics measured at operation 212, the predicted metrics can be channel coefficients, channel quality metrics (e.g., PMI, RI, CQI, LI, RSRP, RSSI, SINR) , and beam related metrics (e.g. beam index, DL-RS index, and RSRP) . In some aspects, the predicted metrics may correspond to a channel quality or a beam quality at a future time (referred to as a time domain prediction) . As an example of time domain prediction, the UE 130 may measure metrics for a beam or channel and use machine learning techniques to predict values for the same beam or channel at a point in the future. In some aspects, the predicted metrics may correspond to a channel quality or beam quality at a current time for a channel or beam where the UE 130 has not been performing measurements (referred to as a spatial domain prediction) . The predicted metrics may be a combination of temporal domain predictions and spatial domain predictions. As one example of spatial domain prediction, the UE 130 may measure the RSRP in beamforming direction A, and use the ML module to predict the RSRP in another beamforming direction B.
[0049] In some aspects, the ML module may generate a prediction of a future channel metric and an indication of a confidence level of the prediction. In some aspects, the confidence level can be derived from output of the ML module. In some aspects, the confidence level can be derived from assistant information associated with the ML module. For example, the confidence level can be derived from an empirical error level based on history data for the metric. As an example, the history data may be maintained by a network entity 120 or a vendor of the UE 130 and provided to the UE 130.
[0050] At operation 218, the UE 130 may detect whether one or more trigger conditions have been met. In some aspects, the one or more trigger conditions may include one or more of:
[0051] ● A predicted metric of one or more current beams, e.g., a metric predicted from measurements of a DL-RS for a beam in an activated unified TCI state or an indicated TCI state, is worse than a first threshold. For example, the triggering condition is met when the predicted metric of a current beam is less the first threshold.
[0052] ● A predicted metric of at least one predicted beam, such as a predicted layer 1 RSRP (L1-RSRP) , becomes a second threshold value better than the same metric of one or more current beams. For example, the triggering condition is met when the L1-RSRP of a predicted beam is greater than the L1-RSRP of a current beam by the second threshold.
[0053] ● A predicted metric of a predicted beam is better than a third threshold. For example, the triggering condition is met when the predicted metric of the predicted beam is greater than the third threshold.
[0054] ● A predicted metric of a current beam is worse than a fourth threshold, and a predicted metric of at least one new beam is better than a fifth threshold. For example, the triggering condition is met when the predicted metric of the current beam is less than the fourth threshold and the predicted metric of a new beam is greater than the fifth threshold.
[0055] ● A confidence level of one or more predicted beams is worse or better than a sixth threshold. For example ( “worse” case) , the triggering condition is met when the confidence level of a predicted beam is less than the sixth threshold. In another example ( “better” case) , the triggering condition is met when the confidence level of the predicted beam is greater than the sixth threshold.
[0056] ● A predicted metric of a beam is worse or better than the same metric corresponding to a current or latest measurement by more than a seventh threshold. For example ( “worse” case) , the triggering condition is met when the predicted metric of a beam is less than the current / latest measurement of the same beam by the seventh threshold. In another example ( “better” case) , the triggering condition is met when the predicted metric of a beam is greater than the current / latest measurement of the same beam by the seventh threshold.
[0057] ● A probability level of one or more predicted beams is worse or better than an eighth threshold. For example ( “worse” case) , the triggering condition is met when the probability level of a predicted beam to be the best beam is less than the eighth threshold. In another example (better) , the triggering condition is met when the probability level of a predicted beam to be the best beam is greater than the eighth threshold
[0058] In some aspects, any of the first through eighth thresholds described above may be predefined. In some aspects, the network entity 120 may configure any of the first through eighth thresholds, for example, by including a value for the threshold in the configuration information transmitted to the UE 130 at operation 206. In some aspects, the network entity 120 or the UE 130 may derive any of the first through eighth thresholds based on the current and / or past measurements of the corresponding metrics.
[0059] In some aspects, thresholds associated with a current beam state may be configured with common values for a current beam in an activated TCI state and a current beam in an indicated TCI state, regardless of whether the thresholds are predefined, configured by the network entity 120, derived by the network entity 120, or derived by the UE 130. In some aspects, one or more of the thresholds associated with a current beam state may be configured with separate values for a current beam in an activated TCI state and a current beam in an indicated TCI state.
[0060] In some aspects, a metric (e.g., layer 3 RSRP (L3 RSRP) ) may be averaged in a time domain or spatial domain. The network entity 120 may configure the filter related parameters. In some aspects, the network entity may include a “forgetting factor” in the configuration information transmitted to the UE 130 at operation 206, e.g., a forgetting factor A or (1-A) . The forgetting factor A may be used in a moving average (also “sliding average” or “rolling average” ) calculation. As an example, a filtered RSRP value may be calculated as:
[0061] filtered RSRP in slot t = L1-RSRP in slot t * (1-A) + A *filtered RSRP before slot t.
[0062] In some aspects, the ML module may output an indication of a trigger condition. For example, an ML model may be trained to provide an indication of a trigger condition as an output. The machine learning model may output trigger condition with the predicted metrics or separately from the predicted metrics.
[0063] At operation 220, if at least one trigger condition has been met, the UE 130 generates report content for an event-triggered beam report. In some aspects, the UE 130 may generate report content that includes one or more of:
[0064] ● Detected event (s) , e.g., event ID, that triggered the report.
[0065] ● One or more predicted beam indexes, e.g., DL-RS indexes or beam IDs.
[0066] ● One or more predicted metrics for the predicted beam (s) .
[0067] ● One or more confidence levels for the predicted beam (s) .
[0068] ● One or more probability levels for the predicted beam (s) .
[0069] ● A serving cell index or serving cell list index for the one or more predicted beams.
[0070] ● Timing information for the one or more predicted beams, e.g., timestamp (s) for the one or more predicted beam (s) indicating a future time for the predicted metrics.
[0071] In some aspects, a probability level for a predicted beam indicates a probability that the predicted beam is the best beam e.g., the beam having highest quality. In some aspects, the probability level indicates a probability that the predicted beam is one of the top K beams, where K may be predefined, configured by the network entity, or determined and reported by the UE.
[0072] In some aspects, the UE 130 may generate different report content based on one or more of the detected events. For example, different detected events may cause the UE 130 to generate different report content.
[0073] The UE 130 may derive the content of a beam report based at least in part on output of the ML model. For example, the report content may depend on a confidence level of one or more predicted metrics. In some aspects, when the confidence level indicates a low level of confidence in a metric, (e.g., a confidence level that is below or above a threshold value) , the UE 130 may include a measured value for the metric rather than a predicted value. The UE 130 may generate a beam report that includes a mix of measured values and predicted values for different metrics. As an example, the UE may report a measured value for a metric associated with a current serving beam (e.g., a beam associated with an indicated unified TCI or activated unified TCI state) and may report a predicted value for metrics associated with other beams.
[0074] The UE 130 may change the content of a beam report from one instance of a beam report to another. For example, the UE 130 may change the content based on a prediction confidence level, or when a beam switch command occurs. In some aspects, the UE 130 may change beam report content by switching between a measured value and a predicted value for a metric. In some aspects, the UE 130 may change the report quantity. For example, the UE 130 may change the report quantity from RSRP to RSRP+SINR and PMI.
[0075] In some aspects, the UE 130 may indicate the content change by transmitting UL signaling that indicates the change. For example, an SR may be dedicated for indicating a change in a beam report. In some aspects, the UE 130 may indicate the content change via a bitmap in the report, for example, a bitmap in a header of the report. In some aspects, bits in the bitmap may correspond to metrics in the report. The value of a bit may be set to a value (e.g., “1” or “0” ) to indicate whether the corresponding metric has a measured value or a predicted value.
[0076] In some aspects, the UE 130 may indicate that the change is to take effect after a time period has elapsed. The time period may be a predefined time period or a configured time period (e.g., configured by the network entity 120) , among other examples. Alternatively, the time period may be determined by the UE 130 and reported by the UE 130 to the network entity 120.
[0077] At operation 222A, the UE may optionally request resources from the network entity 120 for an uplink transmission of the beam report generated at operation 220. In some aspects, the UE 130 may indicate in the request that the UE 130 will transmit the beam report to the network entity 120 at the current time (e.g., when the network entity grants the UL resources) . In some aspects, the UE 130 may indicate in the request that the UE 130 will transmit the beam report to the network entity 120 at a future time. The UE 130 may determine to transmit the beam report at a future time based on triggering conditions and / or the detected event. As one example, the UE 130 may indicate in the request that a beam report will be transmitted at a future time when a predicted metric (e.g., RSRPs of a beam) at the future time meet satisfies a predefined or configurable criteria. As another example, the UE 130 may indicate in the request that a beam report will be transmitted at a future time when the confidence level of the prediction of the metric at the future time is lower than a threshold.
[0078] In some implementations, the UE 130 may add a timestamp to the request that indicates the future time. In some aspects, the timestamp can be specified as X milliseconds (ms) , Y report occasions, or Z slots. The values of X, Y, and / or Z may be configured by the network entity 120 or determined by the UE 130 and reported to the network entity 120. In some aspects, the values of X, Y, and / or Z may be based on output of the machine learning model. In some aspects, the values of X, Y, and / or Z may be based on the machine learning model used for generating the predicted metrics being reported.
[0079] In some aspects, the starting point associated with the timestamp may be based on a first or a last slot of the report. In some aspects, the starting point may be a most recent transmission occasion of the DL resource used for measuring the current metrics occurring before a reference slot. The reference slot may be pre-defined, configured by the network entity 120, or determined and reported by the UE 130.
[0080] In some implementations, the UE 130 may indicate the future time by the occasion of the request. As an example, the UE 130 may use an SR dedicated to indicating that the UE 130 will transmit the beam report at the future time. In some aspects, the dedicated SR may indicate that the UE 130 will transmit the beam report using preconfigured PUCCH resources in X ms, Y PUCCH occasions associated with the beam report, or Z slots after the SR.
[0081] In some aspects, the UE 130 may transmit the beam report for W consecutive occasions, and then autonomously stop transmitting the beam report. The value of W may be pre-defined, configured by the network entity 120, or determined and reported by the UE 130.
[0082] At operation 224A, the network entity 120 may optionally transmit, to the UE 130, a grant of uplink resources for an uplink transmission of the beam report. In some aspects, the network entity 104 may transmit the grant of uplink resources in downlink control information (DCI) on a PDCCH.
[0083] At operation 230A, the UE 130 may transmit the beam report to the network entity 120. In some aspect, the UE 130 may transmit the beam report via one or more of uplink channels specified in the configuration information received at operation 206. As described above, the UE 130 may perform operation 230A at a future time.
[0084] In some aspects, the UE 130 may transmit the beam report in a single stage, for example, via multiple uplink channels. In some aspects, the UE 130 may transmit the beam report in multiple stages. For example, the UE 130 may transmit a first portion of the beam report via a first uplink channel, for example, a first PUCCH. The UE 130 may transmit a second portion of the beam report via a second uplink channel, for example, a PUSCH or a second PUCCH.
[0085] A UL resource may be associated with multiple beam reports, i.e., the multiple beam reports may share the UL resource. As an example, the beam reports may correspond to different trigger conditions. If multiple beam reports that share a UL resource are triggered, the UL resource may not be able to carry all of the triggered reports. For example, the UL resource may be pre-configured and have a fixed size, and the reports may be configured to be sent via UCI. In some aspects, the UE 130 may use a priority associated with the beam reports to determine which beam reports are transmitted via the UL resource. The UE 130 may also use priority to determine when beam reports are transmitted when multiple beam reports on a UL resource is not configured.
[0086] In some aspects, the priority associated with a beam report can be based on at least one of:
[0087] ● Whether the report is based, at least in part, on a ML based prediction. Either triggered conditions or the beam report content may be based on the ML prediction.
[0088] ● A timestamp associated with the prediction. For example, a beam report with an earlier timestamp may be transmitted before or instead of a beam report with a later timestamp.
[0089] ● An ML model (also referred to as an ML prediction function) that generated prediction, for example, a function ID, model ID, or priority associated with the ML model or ML function.
[0090] ● Whether the metric associated with the report is an L1 metric or a time average (e.g. L3 metric) .
[0091] ● A report configuration ID, e.g., lower ID may indicate a higher priority than a higher ID.
[0092] ● A serving cell index for the beam report, e.g., a lower serving cell index may indicate a higher priority than a higher service cell index.
[0093] ● A triggered event, e.g., different triggering events may correspond to different priorities. If multiple events are detected, the event with a highest or lowest priority is used to determine the priority of the beam report.
[0094] In some aspects, an event-triggered beam report may share UL resources with other reports, for example, periodic, semi-periodic, and / or aperiodic reports. In such cases, the UE 130 may determine a priority based on the time domain behavior of the other reports. As an example, an aperiodic report may have a higher priority than an event-triggered beam report, which may in turn have a higher priority than a semi-periodic report, which may in turn have a higher priority than a periodic report. Different implementations may use different priority orders for the reports.
[0095] In some aspects, the UE 130 may indicate to the network entity 120 which beam reports were triggered and / or which beam reports are being reported via the UL resources. As an example, the UE 130 may indicate the triggering events and / or beam reports using a bitmap, where a bit in the bitmap corresponds to a specific triggering event or beam report. In some aspects, the bitmap may be appended to the beam report or be provided in a header of the beam report.
[0096] In some aspects, the UE 130 may indicate that at least one beam report of the beam reports that share UL resources was triggered using the same request (e.g., an SR) at operation 222A.
[0097] In some aspects, the UE 130 may defer, for a future report occasion, the transmission of beam reports that cannot be fitted into the UL resources and thus not transmitted. As an example, the UE 130 may multiplex transmission of the beam reports in an order based on the priority associated with the beam report. In some aspects, the UE 130 may discard (e.g., drop or refrain from transmitting) beam reports that are not transmitted at operation 230A.
[0098] In some aspects, the UE 130 may transmit the beam report when a single occurrence of an event occurs. In some aspects, the UE 130 may count the occurrences of a triggering event and defer transmission of the beam report until the quantity of occurrences of triggering events meets a threshold. In some aspects, the count may be associated with triggering events in general. In some aspects, a different count may be associated with different triggering events.
[0099] FIG. 2B is a sequence diagram illustrating operations of a second example, communications process for a machine learning-based event triggered beam report. Operations 204-220 shown in the example of FIG. 2B have been described above with respect to FIG. 2A.
[0100] At operation 222B, the UE 130 may optionally transmit an SR to network entity 120 to request UL resources for transmitting the beam report.
[0101] At operation 224B, if the UE 130 transmits an SR at operation 222B, the network entity 120 may respond to the SR by transmitting a UL PUSCH grant to the UE 130. The UL PUSCH grant may be transmitted in DCI on a PDCCH.
[0102] At operation 230B, the UE 130 may transmit the beam report via a MAC CE in a PUSCH transmission.
[0103] FIG. 2C is a sequence diagram illustrating operations of a third example, communications process for machine learning-based event triggered beam report. Operations 204 and 206 of FIG. 2C have been described above with respect to FIG. 2A.
[0104] At operation 208, the network entity 120 may transmit a configuration of pre-configured PUSCH and / or PUCCH resources for use by the UE 130 to transmit beam reports. In some aspects, the UE 130 does not need to request resources for the beam reports, and instead, can use the pre-configured resources to transmit the beam reports.
[0105] At operation 210A, the network entity transmits a first instance of one or more DL-RSs. This first instance of DL-RSs may correspond to the DL-RSs described above with respect to FIG. 2A, operation 210.
[0106] At operation 212A, and as described above with respect to FIG. 2A, operation 212, the UE 130 measures the characteristics of the first instance of DL-RSs.
[0107] Operations 218 and 220 have been described above with respect to FIG. 2A.
[0108] At operation 222C, the UE 130 may optionally transmit an SR indicating that triggering conditions have been met. In some aspects, the network entity 120 may pre-configure periodic or semi-persistent resources that the UE 130 may use to send a beam report when an event is triggered. In some aspects, the pre-configured resources may be dedicated to indicating the triggering event. In some aspects, if the triggering conditions are met and a triggering event occurs, the UE 130 may transmit UL signaling, for example, one or more bits in the SR, to indicate the triggering event to the network entity 120. The UE 130 may use subsequent pre-configured resources to send the triggered beam report. If the network entity 120 does not receive an SR indicating a triggering event has occurred, the network entity 120 may not expect the UE 130 to transmit a beam report driven by the triggering condition in the corresponding resource.
[0109] FIG. 3 is a timing diagram illustrating an example machine learning-based event trigger and beam report. In the example of FIG. 3, the network entity 120 has configured the UE 130 with three DL resources 310A, 310B, and 310C for use in detecting an event and generating an event-based beam report based on machine learning prediction.
[0110] In the example of FIG. 3, at time t1, the UE 130 receives DL RS 310A from network entity 120. At time t2, the UE 130 receives DL RS 310B from network entity 120. At time time t3, the UE 130 receives DL RS 310C from network entity 120.
[0111] The UE 130 may obtain, through measurements of DL RS 310A-310C values of one or more metrics associated with the DL RSs. The UE 130 may provide these metrics as input to a machine learning module 338.
[0112] The machine learning module may use machine learning techniques to generate predicted metrics as output of the machine learning module 338. The UE 130 may detect a beam reporting event based on the predicted metrics. At time t4, the UE 130 transmits an indication of the beam reporting event to the network entity 120. As described above, the indication of the beam reporting event may be provided in an SR.
[0113] The UE 130 generates an event-based beam report based on machine learning, and at time t5, the UE 130 transmits the event-based beam report based on machine learning prediction to the network entity 120.
[0114] FIG. 4 is a block diagram illustrating an example machine learning module of a UE (e.g., UE 130 of FIG. 1) . In the example shown in FIG. 4 machine learning module may include one or more machine learning models 436. In some aspects, the one or more machine learning models 436 may be obtained from a network entity (e.g., network entity 120 of FIG. 1) . In some aspects, the one or more machine learning models 436 may be obtained from a vendor of the UE. In some aspects, the one or more machine learning models may be obtained from a third party service. The one or more machine learning models 436 may be trained to predict values of channel metrics and / or beam metrics. Additionally, or alternatively, the machine learning models may be trained to generate a predicted event 418.
[0115] The one or more machine learning models 436 may be created using different machine learning techniques and / or have coefficients and parameters that are determined via supervised or unsupervised learning. In some aspects, these machine learning techniques may include one or more of logistics regression, support vector machines, Bayes algorithms, decision trees, linear regression, k nearest neighbors (kNN) , random forest, boosting algorithms (e.g., gradient boosting machine) and hierarchical clustering, among others.
[0116] The UE performs channel and / or beam measurement operations 414 on DL RSs 310A-310C as they are received to generate current metrics. In some aspects, the metrics obtained from the DL RSs 310A-310C may be organized into a multi-dimensional vector, where each dimension corresponds to a DL RS. In the example shown in FIG. 4, vector X 412A corresponds to DL RS 310A, vector Y 412B corresponds to DL RS 310B, and vector Z 412C corresponds to DL RS 310C. The values in each dimension may be a time series of the measurements of the DL RSs 310A-310C, where different elements in the same time sequence correspond to different measurement times.
[0117] For the purposes of the example shown in FIG. 4, the current time is N. The input vectors X, Y and Z represent the time sequence of K metrics at the current time (time = N) and past measurements associated with different RSs, e.g., DL RSs 310A-310C. In some aspects, some values may be missing in the time series. In the example shown in FIG. 4, entries 442A-442C in vectors X 412A, Y 412B, and Z 412C, respectively, may be missing. The output vectors Y 416A, T 416B, and B 416C correspond to the predicted channel and / or beam metrics of different RSs based on the input vectors 412A-412C.
[0118] In some aspects, the predicted metrics in the output and the measurements in the input may or may not correspond to the same DL RS or the same channel metric.
[0119] In some aspects, the ML module 338 may also provide a confidence level of the predictions. For example, the confidence level may be expressed as the standard deviation of the prediction error or a probability of the predicted value to be true or reliable (perhaps within a certain error range) .
[0120] In some aspects, the UE may report the prediction output to the network entity, for example, in beam report. In some aspects, the UE may use the prediction output locally, for example, to detect whether the condition of the event triggered event has been met.
[0121] FIG. 5 is a flow chart diagram illustrating example UE operations of a method 500 for machine learning-based event trigger and beam report. The example operations of method 500 may be performed, for example, by UE 130 of FIG. 1, FIG. 2A, FIG. 2B, and FIG. 2C.
[0122] At block 502, the UE may receive one or more configurations for one or more machine learning models. In some aspects, the machine learning models may be pre-loaded on the UE, and the UE may receive an indicator indicating the machine learning model or models to use. In some aspects, the UE may receive the actual machine learning models. As described above, the UE may receive the machine learning models from the network entity, a vendor of the UE, and / or a third party service.
[0123] At block 504, and as described above with respect to FIG. 2A, operation 204, the UE may optionally transmit or report to network entity UE capability information regarding the UE’s capability or support for a machine learning-based event trigger and beam report. In some aspects, the UE 130 may report UE capability information that includes supported configurations for machine learning-based event triggering and beam reporting. In some aspects, the configurations may include one or more of the following parameters: a minimum, maximum and / or supported number of DL RSs for event detection and beam reporting; a minimum, maximum and / or supported predicted duration for machine learning-based event triggering and beam reporting; a minimum, maximum and / or supported number of predicted beams for machine learning-based event triggering and beam reporting.
[0124] At block 506, and as described above with respect to FIG. 2A, operation 206, the UE may, depending on the UE capability information transmitted at block 504, receive, from the network entity, configuration information that configures at least one event-based beam report based on a machine learning model, at least one event triggering the event-based beam report, and one or more DL reference signal (DL-RS) resources. In some aspects, the configuration information may include one or more thresholds associated with one or more of the triggering conditions or events. In some aspects, the configuration information includes a configuration of the beam report content. For example, the network entity may configure the UE to report one or more of a predicted beam index, a predicted metric, a predicted beam characteristic, one or more predicted confidence levels, or one or more predicted probability levels associated with elements of the predicted beam report.
[0125] At block 510, and as described above with respect to FIG. 2A, operation 210, the UE may receive one or more DL-RSs from the network entity.
[0126] At block 512, and as described above with respect to FIG. 2A, operation 212, the UE may measure or determine metrics of the one or more DL-RSs received at operation 210. For example, the UE may measure channel coefficients, channel quality metrics (e.g., PMI, RI, CQI, LI, RSRP, RSSI, SINR) , and / or beam related metrics (e.g., beam index, DL-RS index, and RSRP) in FR2.
[0127] At block 514, the UE may provide the measurements obtained at block 512 to a machine learning model.
[0128] At block 516, and as described above with respect to FIG. 2A, operation 216, the UE may predict channel metrics or beam metrics based on the measurements obtained at operation 212. For example, the UE may execute a machine learning module that uses the machine learning model to predict a value of a channel metric or a beam metric at a future time (referred to as a “predicted metric” ) . The predicted metrics can be channel coefficients, channel quality metrics (e.g., PMI, RI, CQI, LI, RSRP, RSSI, SINR) , and beam related metrics (e.g., beam index, DL-RS index, and RSRP) in FR2. In some aspects the UE may perform time domain analysis to obtain predicted metrics at a future point in time. In some aspects, the UE may perform spatial domain analysis on measurements of a current beam to obtain predicted metrics for a different beam.
[0129] At block 518, and as described above with respect to FIG. 2A, operation 218, the UE may detect whether one or more trigger conditions have been met based, at least in part, on the predicted metrics obtained at block 516. In some aspects, the UE may compare the predicted metrics with thresholds to detect whether a trigger condition has been met.
[0130] At block 520, and as described above with respect to FIG. 2A, operation 220, if at least one trigger condition has been met, the UE generates report content for an event-triggered beam report. The content may include one or more of the predicted metrics, may identify the event that triggered the report, beams or channels corresponding to the predicted metrics, and the like.
[0131] At block 522, and as described above with respect to FIG. 2A, operation 222A, FIG. 2B, operation 222B, FIG. 2C operation 222C, the UE may optionally request resources from the network entity for an uplink transmission of the beam report generated at block 520. In some aspects, the UE may indicate in the request that the UE will transmit the beam report to the network entity at the current time. In some aspects, the UE may indicate, via the request, that the UE will transmit the beam report to the network entity 120 at a future time.
[0132] At block 524, and as described above with respect to FIG. 2A, operation 224A and FIG. 2B, operation 224B, the UE may receive a grant of uplink resources for an uplink transmission of the beam report.
[0133] At block 526, and as included in the discussion of FIG. 2A, operation 222, if there are more beam reports than the UE can fit into the resources configured for the beam report, the UE may derive priorities for the beam reports to determine which beam reports are transmitted to the network entity.
[0134] At block 530, and as described above with respect to FIG. 2A, operation 230A, FIG. 2B, operation 230B, and FIG. 2C, operation 230C, the UE may transmit the beam report to the network entity.
[0135] FIG. 6 is a flow chart diagram illustrating example network entity operations of a method 600 for machine learning-based event trigger and beam report. The example operations of method 600 may be performed, for example, by network entity 120 of FIG. 1.
[0136] At block 602, the network entity may transmit one or more configurations for one or more machine learning models to the UE. In some aspects, the machine learning models may be pre-loaded on the UE, and the network entity may transmit an indicator indicating the machine learning model or models to use. In some aspects, the network entity may transmit the actual machine learning models.
[0137] At block 604, and as described above with respect to FIG. 2A, operation 204, the network entity may optionally receive, from the UE, UE capability information regarding the UE’s capability or support for a machine learning-based event trigger and beam report. In some aspects, the network entity may receive UE capability information that includes supported configurations for machine learning-based event triggering and beam reporting. In some aspects, the configurations may include one or more of the following parameters: a minimum, maximum and / or supported number of DL RSs for event detection and beam reporting; a minimum, maximum and / or supported predicted duration for machine learning-based event triggering and beam reporting; a minimum, maximum and / or supported number of predicted beams for machine learning-based event triggering and beam reporting.
[0138] At block 606, and as described above with respect to FIG. 2A, operation 206, depending on the UE capability information received at block 604, the network entity may transmit configuration information that configures at least one event-based beam report based on a machine learning model, at least one event triggering the event-based beam report, and one or more DL reference signal (DL-RS) resources. In some aspects, the configuration information may include one or more thresholds associated with one or more of the triggering conditions or events. In some aspects, the configuration information includes a configuration of the beam report content. For example, the network entity may configure the UE to report one or more of a predicted beam index, a predicted metric, a predicted beam characteristic, or one or more predicted confidence levels associated with elements of the predicted beam report.
[0139] At block 608, and as described above with respect to FIG. 2C, operation 208, the network entity may transmit a configuration of pre-configured PUSCH and / or PUCCH resources for use by the UE 130 to transmit beam reports. In some aspects, the UE 130 does not need to request resources for the beam reports, and instead, can use the pre-configured resources to transmit the beam reports.
[0140] At block 610, and as described above with respect to FIG. 2A, operation 210, the network entity may transmit the one or more DL-RSs to the UE.
[0141] At block 622 and as described above with respect to FIG. 2A, operation 222, the network entity may receive a request for resources from the UE. In some aspects, the request for resources may be an SR.
[0142] At block 624, and as described above with respect to FIG. 2A, operation 224A and FIG. 2B, operation 224B, the network entity may transmit a response to the request received at block 622. In some aspects, the response may be an UL grant of resources.
[0143] At block 628, the network entity may optionally determine a time for receiving the beam report. As described above, the UE may indicate that the beam report may be transmitted at a future time. The network entity may determine, based on the indicated future time, when to expect the beam report.
[0144] At block 630, and as described above with respect to FIG. 2A, operation 230A, FIG. 2B, operation 230B, and FIG. 2C, operation 230C, the network entity may receive the beam report.
[0145] FIG. 7 is a flow chart diagram illustrating example UE operations for machine learning-based event trigger and beam report. In block 706, routine 700 receives, from a network entity, a configuration for an event-based beam report that configures the UE to provide the event-based beam report based on a machine learning model, at least one event triggering the event-based beam report, and one or more downlink reference signals. In block 710, routine 700 receives, from the network entity, the one or more downlink reference signals. In block 718, routine 700 detects at least one event based on an output of the machine learning model, wherein measurements of the one or more downlink reference signals are input to the machine learning model and one or more predicted metrics or the at least one event are output of the machine learning model. In block 730, routine 700 transmits the event-based beam report to the network entity based on the at least one event.
[0146] FIG. 8 shows a block diagram of an example device 810 and an example network entity 804. Note that the depicted hardware configurations represent the processing components (e.g., a processing system) and communication components (e.g., a communication unit) of a network entity 804 (such as the network entity 120 described herein) and a device 810 (such as the wireless device UE 130 described herein) . The depicted hardware configurations may omit certain components well-understood to be frequently implemented in such electronic devices, such as displays, peripherals, power supplies, and the like.
[0147] The device 810 includes antennas 803A, a radio frequency front end (RF front end) 803B, and radio-frequency transceivers (e.g., an LTE transceiver 803D and a 5G NR transceiver 803C) for communicating with the network entity 804. The RF front end 803B includes one or more modems configured for the corresponding RAT (s) employed (for example, Third Generation Partnership Project (3GPP) Fifth Generation New Radio (5G NR) ) , one or more analog-to-digital converters (ADCs) , one or more digital-to-analog converters (DACs) , signal processors, and the like. In the example illustrated in FIG. 8, the RF front end 803B of the device 810 may couple or connect the 5G NR transceiver 803C to the antennas 803A to facilitate various types of wireless communication. The RF front end 803B operates, in effect, as a physical (PHY) transceiver interface to conduct and process signaling between the one or more processor (s) 803E and antennas 803A so as to facilitate various types of wireless communication.
[0148] The antennas 803A of the device 810 include an array of multiple antennas that may be tuned to one or more frequency bands associated with a corresponding RAT. The antennas 803A and the RF front end 803B are tuned to, and / or be tunable to, one or more frequency bands defined by the 3GPP 5G NR communication standards and implemented by the 5G NR transceiver 803C. Additionally, the antennas 803A, the RF front end 803B, and / or the 5G NR transceiver 803C can be configured to support beamforming for the transmission and reception of communications with the network entity 804. By way of example and not limitation, the antennas 803A and the RF front end 803B may be implemented for operation in sub-gigahertz bands, sub-6 GHz bands, and / or above 6 GHz bands that are defined by the 3GPP LTE and 5G NR communication standards.
[0149] The device 810 also includes processor (s) 803E and computer-readable storage media (CRM) 803F. The processor (s) 803E may include, for example, one or more central processing units, graphics processing units (GPUs) , or other application-specific integrated circuits (ASIC) , and the like. To illustrate, the processor (s) 803E may include an application processor (AP) utilized by the device 810 to execute controller functions, an operating system, or various applications, as well as one or more processors utilized by modems or a baseband processor of the RF front end 803B. The CRM 803F may include any suitable memory or storage device such as random-access memory (RAM) , static RAM (SRAM) , dynamic RAM (DRAM) , non-volatile RAM (NVRAM) , read-only memory (ROM) , Flash memory, solid-state drive (SSD) or other mass-storage devices, and the like useable to store one or more sets of executable software instructions and associated data that manipulate the one or more processor (s) 803E and other components of the device 810 to perform the various functions described herein and attributed to the device 810. The sets of executable software instructions include, for example, an operating system (OS) and various drivers (not shown) , and various software applications (not shown) , which are executable by processor (s) 803E to enable user-plane communication, control-plane signaling, and user interaction with the device 810.
[0150] Turning to the hardware of the network entity 804, it is noted that although FIG. 8 illustrates an implementation of the network entity 804 as a single network node (for example, a 5G NR Node B, or “gNB” ) , the functionality, and thus the hardware components, of the network entity 804 instead may be distributed across multiple network nodes or devices and may be distributed in a manner to perform the functions described herein. As one example, the functionality of network entity 804 may be distributed across a radio unit (RU) , distributed unit (DU) , or central unit (CU) .
[0151] The network entity 804 includes antennas 805A, a radio frequency front end (RF front end) 805B, and one or more 5G NR transceivers 805C for communicating with the device 810. The RF front end 805B of the network entity 804 may couple or connect the 5G NR transceivers 805C to the antennas 805A to facilitate various types of wireless communication. Similar to RF front end 803B, the RF front end 805B includes one or more modems, one or more ADCs, one or more DACs, and the like. RF front end 805B receives the one or more RF signals, for example, RF signals from device 810, and pre-processes the one or more RF signals to generate data from the RF signals that is provided as input to processes and / or applications executing on network entity 804. This pre-processing may include, for example, power amplification, conversion of band-pass signaling to baseband signaling, initial analog-to-digital conversion, and the like.
[0152] The antennas 805A of the network entity 804 may be configured individually and / or as one or more arrays of multiple antennas. The antennas 805A and the RF front end 805B may be tuned to, and / or be tunable to, one or more frequency band defined by the 3GPP 5G NR communication standards, and implemented by the 5G NR transceivers 805C. Additionally, the antennas 805A, the RF front end 805B, and the 5G NR transceivers 805C may be configured to support beamforming, such as Massive-MIMO, for the transmission and reception of communications with the device 810.
[0153] The network entity 804 also includes processor (s) 805D and computer-readable storage media (CRM) 805E. The processor (s) 805D may include, for example, one or more central processing units, graphics processing units (GPUs) , or other application-specific integrated circuits (ASIC) , and the like. To illustrate, the processor (s) 805D may include an application processor (AP) utilized by the network entity 804 to execute an operating system and various user-level software applications, as well as one or more processors utilized by modems or a baseband processor of the RF front end 805B to enable communication with the device 810. In at least some aspects, the processor (s) 805D configures the 5G NR transceiver (s) 805C for communication with the device 810, transmission and reception points (TRPs) , and radio units via fronthaul interface 807A, as well as communication with a core network. In some aspects, the network entity 804 includes an inter-network entity interface 807B, such as an Xn and / or X2 interface, which the processor (s) 805D configures to exchange user-plane and control-plane data with another network entity, to manage the communication of the network entity 804 with the device 810. The network entity 804 includes a core network interface 807C that the processor (s) 805D configures to exchange user-plane and control-plane data with core network functions and entities.
[0154] FIG. 1 through FIG. 8 and the operations described herein are examples meant to aid in understanding example implementations and should not be used to limit the potential implementations or limit the scope of the claims. some implementations may perform additional operations, fewer operations, operations in parallel or in a different order, and some operations differently.
[0155] The following additional considerations may apply to the foregoing and the following discussions.
[0156] Unless defined otherwise, technical and scientific terms used herein have the same meaning as is commonly understood by one of ordinary skill in the art to which this specification belongs. The terms “first, ” “second, ” and the like, as used herein do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The use of terms “including, ” “comprising” or “having” and variations thereof herein are meant to encompass the items listed thereafter and equivalents thereof as well as additional items. The terms “connected” and “coupled” are not restricted to physical or mechanical connections or couplings and can include electrical connections or couplings, whether direct or indirect. Furthermore, terms “circuit” and “circuitry” and “control unit” may include either a single component or a plurality of components, which are either active and / or passive and are connected or otherwise coupled together to provide the described function. In addition, the term operationally coupled as used herein includes wired coupling, wireless coupling, electrical coupling, magnetic coupling, radio communication, software based communication, or combinations thereof.
[0157] Some or all of the foregoing or the following implementations can be jointly combined or formed to be a new or another one implementation. The foregoing or the following techniques can be used to solve at least (but not limited to) the issue (s) or scenario (s) mentioned in this disclosure. Any two or more than two of the foregoing or the following paragraphs, (sub) -bullets, points, actions, or claims described in each method / technique / implementation may be combined logically, reasonably, and properly to form a specific method. Any sentence, paragraph, (sub) -bullet, point, action, or claim described in each of the foregoing or the following technique (s) / implementation (s) / concept (s) may be implemented independently and separately to form a specific method. Dependency, such as “based on, ” “more specifically, ” “where” or etc., in technique (s) / implementation (s) / concept (s) mentioned in this disclosure is just one possible implementation which would not restrict the specific method.
[0158] Generally speaking, description for one of the above figures can apply to another of the above figures. Examples, implementations and methods described above can be combined, if there is no conflict. An event or block described above can be optional or omitted. For example, an event or block with dashed lines in the figures can be optional. In some implementations, “message” is used and can be replaced by “information element (IE) , ” and vice versa. In some implementations, “IE” is used and can be replaced by “field, ” and vice versa. In some implementations, “configuration” can be replaced by “configurations” or “configuration parameters, ” and vice versa. In some implementations, “some” means “one or more. ” In some implementations, “at least one” means “one or more. ”
[0159] As used herein, the terms “wireless device” , “user device” , “user equipment” , “wireless communication device” , “mobile communication device” , “communication device” , or “mobile device” refer to any one or all of cellular telephones, smartphones, portable computing devices, personal or mobile multi-media players, laptop computers, tablet computers, smartbooks, Internet-of-Things (IoT) devices, palm-top computers, wireless electronic mail receivers, multimedia Internet enabled cellular telephones, wireless gaming controllers, display sub-systems, driver assistance systems, vehicle controllers, vehicle system controllers, vehicle communication system, infotainment systems, vehicle telematics systems or subsystems, vehicle display systems or subsystems, vehicle data controllers, point-of-sale (POS) terminals, health monitoring devices, drones, cameras, media-streaming dongles or another personal media devices, wearable devices such as smartwatches, wireless hotspots, femtocells, broadband routers or other types of routers, and similar electronic devices which include a programmable processor and memory and circuitry configured to perform operations as described herein. Further, the user device may be embedded in an electronic system such as the head unit of a vehicle or an advanced driver assistance system (ADAS) . Still further, the user device can operate as an internet-of-things (IoT) device or a mobile-internet device (MID) . Depending on the type, the user device can include one or more general-purpose processors, a computer-readable memory, a user interface, one or more network interfaces, one or more sensors, etc.
[0160] Certain techniques are described in this disclosure as including logic or a number of components or modules. Modules can be software modules (e.g., code, or machine-readable instructions stored on non-transitory machine-readable medium) or hardware modules. A hardware module is a tangible unit capable of performing certain operations and may be configured or arranged in a certain manner. A hardware module can comprise dedicated circuitry or logic that is permanently configured (e.g., as a special-purpose processor, such as a field programmable gate array (FPGA) or an application-specific integrated circuit (ASIC) , a digital signal processor (DSP) , etc. ) to perform certain operations. A hardware module may also comprise programmable logic or circuitry (e.g., as encompassed within a general-purpose processor or other programmable processor) that is temporarily configured by software to perform certain operations. The decision to implement a hardware module in dedicated and permanently configured circuitry, or in temporarily configured circuitry (e.g., configured by software) may be driven by cost and time considerations.
[0161] When implemented in software, the techniques can be provided as part of the operating system, a library used by multiple applications, a particular software application, etc. The software can be executed by one or more general-purpose processors or one or more special-purpose processors.
[0162] As used herein, the terms “component” and “module” are intended to be broadly construed as hardware, firmware, or a combination of hardware and software. As used herein, a processor is implemented in hardware, firmware, or a combination of hardware and software. As used herein, the phrase “based on” is intended to be broadly construed to mean “based at least in part on. ”
[0163] As used herein, a phrase referring to a list of items separated by “or” refers to any combination of those items, including single members. For example, “a, b, or c” is intended to cover the possibilities of: a only, b only, c only, a combination of a and b, a combination of a and c, a combination of b and c, and a combination of a and b and c.
[0164] In this disclosure, an expression of “X / Y” may include meaning of any of the following: “X or Y” or “X and Y” or “X and / or Y. " An expression of “ (A) B” or “B (A) ” may include concept of “only B. ” An expression of “ (A) B” or “B (A) ” may include the concept of “A+B” or “B+A. ”
[0165] In this disclosure, the term "can" indicates a capability, or alternatively indicates a possible implementation option. The term "may" indicates a permission or a possible implementation option.
[0166] Some aspects are described herein in connection with thresholds. As used herein, satisfying a threshold may refer to a value being greater than the threshold, greater than or equal to the threshold, less than the threshold, less than or equal to the threshold, equal to the threshold, not equal to the threshold, or the like.
[0167] The various illustrative components, logic, logical blocks, modules, circuits, operations and algorithm processes described in connection with the implementations disclosed herein may be implemented as electronic hardware, firmware, software, or combinations of hardware, firmware or software, including the structures disclosed in this specification and the structural equivalents thereof. The interchangeability of hardware, firmware and software has been described generally, in terms of functionality, and illustrated in the various illustrative components, blocks, modules, circuits and processes described above. Whether such functionality is implemented in hardware, firmware or software depends upon the particular application and design constraints imposed on the overall system.
[0168] As described above, some aspects of the subject matter described in this specification can be implemented as software. For example, various functions of components disclosed herein, or various blocks or steps of a method, operation, process or algorithm disclosed herein can be implemented as one or more modules of one or more computer programs. Such computer programs can include non-transitory processor-executable or computer-executable instructions encoded on one or more tangible processor-readable or computer-readable storage media for execution by, or to control the operation of, a data processing apparatus including the components of the devices described herein. By way of example, and not limitation, such storage media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that may be used to store program code in the form of instructions or data structures. Combinations of the above should also be included within the scope of storage media.
[0169] Various modifications to the implementations described in this disclosure may be readily apparent to persons having ordinary skill in the art, and the generic principles defined herein may be applied to other implementations without departing from the scope of this disclosure. Thus, the claims are not intended to be limited to the implementations shown herein but are to be accorded the widest scope consistent with this disclosure, the principles and the novel features disclosed herein.
[0170] Additionally, various features that are described in this specification in the context of separate implementations also can be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation also can be implemented in multiple implementations separately or in any suitable subcombination. As such, although features may be described above as acting in particular combinations, and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.
[0171] The drawings may schematically depict one or more example processes in the form of a flowchart or flow diagram. However, other operations that are not depicted can be incorporated in the example processes that are schematically illustrated. For example, one or more additional operations can be performed before, after, simultaneously, or between any of the illustrated operations. In some circumstances, multitasking and parallel processing may be advantageous. Moreover, the separation of various system components in the implementations described above should not be understood as requiring such separation in all implementations, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products. Additionally, other implementations are within the scope of the following claims. In some implementations, the actions recited in the claims can be performed in a different order and still achieve desirable results.
[0172] The foregoing disclosure provides illustration and description but is not intended to be exhaustive or to limit the aspects to the precise form disclosed. Modifications and variations may be made in light of the above disclosure or may be acquired from practice of the aspects. While the aspects of the disclosure have been described in terms of various examples, any combination of aspects from any of the examples is also within the scope of the disclosure. The examples in this disclosure are provided for pedagogical purposes.
Claims
1.A method for wireless communication by a user equipment (UE) (130) , the method comprising:receiving (206, 506, 706) , from a network entity (120) , a configuration that configures an event-based beam report based on a machine learning model (436) , at least one event triggering the event-based beam report, and one or more downlink reference signals;receiving (210, 510, 710) , from the network entity, the one or more downlink reference signals;detecting (218, 518, 718) at least one event based on an output of the machine learning model, an input of the machine learning model including measurements of the one or more downlink reference signals, the output of the machine learning model including one or more predicted metrics or the at least one event; andtransmitting (230A, 230B, 230C, 330, 530, 730) , to the network entity, the event-based beam report (128, 330) based on the at least one event.2.The method of claim 1, further comprising receiving the machine learning model from at least one of:the network entity;a vendor of the UE; ora third-party service.3.The method of claim 1 or 2, further comprising generating (220, 520) content for the event-based beam report based on at least one of:the output of the machine learning model; orthe event.4.The method of claim 3, wherein generating the content for the event-based beam report includes generating one or more of:at least one detected event identifier (ID) corresponding to the at least one event;one or more beam indexes identifying one or more predicted beams associated with the one or more predicted metrics;one or more confidence indicators associated with the one or more predicted metrics;one or more beam probability indicators associated with the one or more predicted beams;a serving cell index or a serving cell list index for the one or more predicted beams; ortiming information corresponding to the one or more predicted beams.5.The method of claims 3 or 4, wherein the generating the content for the event-based beam report includes one or more of:generating the content for the event-based beam report based on at least one of the measurements of the one or more downlink reference signals when the event is a first event;generating the content for the event-based beam report based on the output of the machine learning model when the event is a second event;generating the content for the event-based beam report based on at least one of the measurements of the one or more downlink reference signals when a confidence value corresponding to the output of the machine learning model is below a first threshold; andgenerating the content for the event-based beam report based on the one or more predicted metrics when the confidence value is above a second threshold.6.The method of any one of claims 1 to 5, further comprising transmitting, to the network entity, an indication of a future time associated with the event-based beam report, the indication of the future time including one or more of:a timestamp indicating the future time; ora scheduling request dedicated for indicating the future time;wherein the transmitting the event-based beam report comprises transmitting the event-based beam report at the future time.7.The method of any one of claims 1 to 6, further comprising receiving, from the network entity, one or more of:a first indicator enabling machine learning based event detection;at least one second indicator indicating the at least one event is to be detected;a first configuration of one or more uplink resources for transmitting the event-based beam report;a second configuration of the one or more downlink reference signals;one or more first threshold values corresponding to the at least one event;one or more second threshold values associated with the one or more predicted metrics;a third configuration of triggering conditions for the at least one event; ora fourth configuration of content for the event-based beam report.8.The method of any one of claims 1 to 7, wherein a plurality of event-based beam reports including the event-based beam report are configured to share an uplink resource.9.The method of any one of claims 1 to 8, wherein the transmitting the event-based beam report comprises transmitting the event-based beam report based on a priority corresponding to the event-based beam report, wherein the priority is based on one or more of:whether the at least one event is associated with a machine learning based prediction;whether the content of the event-based beam report is generated by the machine learning model;a timestamp associated with the output of the machine learning model;a machine learning model corresponding to the output;whether a predicted metric associated with the event-based beam report is associated with a layer 1 (L1) metric or a layer 3 (L3) metric;an event-based beam report configuration identifier;a serving cell index for the event-based beam report; ora priority corresponding to the at least one event.10.The method of any one of claims 1 to 9, wherein the machine learning model is configured to perform one or more of:a temporal domain prediction based on the one or more downlink reference signals; ora spatial domain prediction based on the one or more downlink reference signals.11.The method of any one of claims 1 to 10, further comprising:counting a quantity of occurrences of the at least one event; andwherein the transmitting the event-based beam report includes transmitting the event-based beam report based on the quantity of the occurrences of the event exceeding a threshold.12.The method of any one of claims 1 to 11, further comprising transmitting an indication of the at least one event, wherein the transmitting the indication of the at least one event comprises one of:transmitting the indication in a scheduling request (222B) for the event-based beam report;transmitting the indication in a medium access control-control element (MAC-CE) ; ortransmitting the indication in uplink control information (UCI) .13.The method of any one of claims 1 to 12, wherein the detecting the at least one event comprises detecting one or more of:at least one of the one or more predicted metrics is below a first threshold;at least one of the one or more predicted metrics is higher than at least one metric of a current beam by more than a second threshold;at least one of the one or more predicted metrics is higher than a third threshold;at least one of the one or more predicted metrics associated with at least one current beam is lower than a fourth threshold, and a fifth predicted metric of at least another beam is higher than a fifth threshold;a confidence level corresponding to at least one of the one or more predicted metrics is less than a sixth threshold or higher than a seventh threshold; orat least one of the one or more predicted metrics is different from a most recent actual metric corresponding to the at least one of the one or more predicted metrics by more than an eighth threshold.14.A method for wireless communication by a network entity (120) , the method comprising:transmitting (206, 606) , to a user equipment (UE) (130) , a configuration that configures an event-based beam report based on a machine learning model, at least one event triggering the event-based beam report, and one or more downlink reference signals;transmitting (210, 610) , to the UE, the one or more downlink reference signals; andreceiving (230A, 230B, 230C, 630) , from the UE, the event-based beam report (128, 330) based on one or more of at least one event predicted by the machine learning model or one or more predicted metrics associated with one or more predicted beams.15.The method of claim 14, wherein the configuration includes one or more of:a first indicator enabling machine learning based event detection;at least one second indicator indicating the one or more machine learning based events to be detected; orone or more threshold values associated with the one or more predicted metrics.16.The method of claim 14 or 15, wherein the event-based beam report includes one or more of:at least one detected event identifier (ID) corresponding to the at least one event;one or more beam indexes identifying one or more predicted beams associated with the one or more predicted metrics;one or more confidence indicators associated with the one or more predicted metrics;one or more beam probability indicators associated with the one or more predicted beams;a serving cell index or a serving cell list index for the one or more predicted beams; ortiming information corresponding to the one or more predicted beams.17.The method of any one of claims 1 to 16, wherein the one or more predicted metrics comprise at least one channel metric or beam metric.18.An apparatus, comprising:a communication unit; anda processing system configured to control the communication unit to implement any one of the methods of any one of claims 1 to 17.
Citation Information
Patent Citations
Event-based reporting of beam-related prediction
US20230354077A1