Candidate beam identification based on beam prediction

Abstract

A method includes receiving information of a set of candidate beams; obtaining from a machine learning (ML) information indicating a set of predicted top beams; transmitting a report of the set of predicted top beams, the report comprising a beam identity for each predicted top beam of the set of predicted top beams; determining and transmitting an event associated with the set of candidate beams based on a beam quality of at least one of the candidate beams; determining a proposed set of candidate beams based on the set of predicted top beams; transmitting the proposed set of candidate beams; receiving an updated information of the set of candidate beams; and performing a beam failure recovery procedure based on the updated set of candidate beams.

Description

CANDIDATE BEAM IDENTIFICATION BASED ON BEAM PREDICTIONTECHNICAL FIELD

[0001] This description relates to wireless communications.BACKGROUND

[0002] A communication system may be a facility that enables communication between two or more nodes or devices, such as fixed or mobile communication devices. Signals can be carried on wired or wireless carriers.

[0003] An example of a cellular communication system is an architecture that is being standardized by the 3rdGeneration Partnership Project (3GPP). 5G New Radio (NR) development is part of a continued mobile broadband evolution process to meet the requirements of 5G, similar to earlier evolution of 3G and 4G wireless networks. In addition, 5G is also targeted at the new emerging use cases in addition to mobile broadband. A goal of 5G is to provide significant improvement in wireless performance, which may include new levels of data rate, latency, reliability, and security. 5G NR may also scale to efficiently connect the massive Internet of Things (loT) and may offer new types of mission-critical services. For example, ultrareliable and low-latency communications (URLLC) devices may require high reliability and very low latency. Also, non-terrestrial networks are being developed in which signals between base stations (or gNBs) and UEs may be relayed through a satellite.

[0004] Another example is 6G that is designed to continue the ongoing shift to hosting of network functions in cloud platforms. Deployments will move from specialized telco cloud platforms to generic public, private, or hybrid clouds that can be located on-premises, in the (far) edge or in a central site. 6G will provide a uniform orchestration interface for service management of distributed clouds, complemented with segment specific abstractions, e.g., for the 6G RAN. Artificial intelligence and machine learning technology is expected to be an integral part of the 6G architecture. It is a technology that is needed to achieve the vision of a truly cognitive network that adapts itself to a variety of scenarios and deployments.SUMMARY

[0005] An apparatus may include at least one processor; and at least one memory storing instructions that when executed by the at least one processor, cause the apparatus at least to perform: receiving, by a user device from a network node, information of a set of candidate beams, wherein one or more beams of the set of candidate beams are to be used for beam failure recovery; obtaining, by the user device from a machine learning (ML) model at the user device, information indicating a set of predicted top beams; transmitting, by the user device to the network node, a report of the set of predicted top beams, the report comprising a beam identity for each predicted top beam of the set of predicted top beams; determining an event associated with the set of candidate beams based on a beam quality of at least one of the candidate beams; transmitting, by the user device to the network node, a report of the event associated with the set of candidate beams; determining, by the user device, a proposed set of candidate beams based on the set of predicted top beams; transmitting, by the user device to the network node, the proposed set of candidate beams; receiving, by the user device from the network node, an updated information of the set of candidate beams; and performing, by the user device to the network node, a beam failure recovery procedure based on the updated set of candidate beams.

[0006] A method may include receiving, by a user device from a network node, information of a set of candidate beams, wherein one or more beams of the set of candidate beams are to be used for beam failure recovery; obtaining, by the user device from a machine learning (ML) model at the user device, information indicating a set of predicted top beams; transmitting, by the user device to the network node, a report of the set of predicted top beams, the report comprising a beam identity for each predicted top beam of the set of predicted top beams; determining an event associated with the set of candidate beams based on a beam quality of at least one of the candidate beams; transmitting, by the user device to the network node, a report of the event associated with the set of candidate beams; determining, by the user device, a proposed set of candidate beams based on the set of predicted top beams; transmitting, by the user device to the network node, the proposed set of candidate beams; receiving, by the user device from the network node, an updated information of the set of candidate beams; and performing, by the user device tothe network node, a beam failure recovery procedure based on the updated set of candidate beams.

[0007] An apparatus may include at least one processor; and at least one memory storing instructions that when executed by the at least one processor, cause the apparatus at least to perform: transmitting, by a network node to a user device, information of a set of candidate beams, wherein one or more beams of the set of candidate beams are to be used for beam failure recovery; receiving, by the network node from the user device, a report of a set of predicted top beams, the report comprising a beam identity for each predicted top beam of the set of predicted top beams; receiving, by the network node from the user device, a report of an event of a candidate beam of the set of candidate beams; receiving, by the network node from the user device, a proposed set of candidate beams based on the set of predicted top beams; determining, by the network node, an updated information of the set of candidate beams based on the proposed set of candidate beams; transmitting, by the network node to the user device, the updated information of the set of candidate beams; and receiving, by the network node from the user device, a beam failure recovery transmission based on the updated information of the set of candidate beams.

[0008] A method may include transmitting, by a network node to a user device, information of a set of candidate beams, wherein one or more beams of the set of candidate beams are to be used for beam failure recovery; receiving, by the network node from the user device, a report of a set of predicted top beams, the report comprising a beam identity for each predicted top beam of the set of predicted top beams; receiving, by the network node from the user device, a report of an event of a candidate beam of the set of candidate beams; receiving, by the network node from the user device, a proposed set of candidate beams based on the set of predicted top beams; determining, by the network node, an updated information of the set of candidate beams based on the proposed set of candidate beams; transmitting, by the network node to the user device, the updated information of the set of candidate beams; and receiving, by the network node from the user device, a beam failure recovery transmission based on the updated information of the set of candidate beams.

[0009] Other examples and / or embodiments are provided or described for each of the example methods, including: means for performing any of the example methods;a non-transitory computer-readable storage medium comprising instructions stored thereon that, when executed by at least one processor, are configured to cause a computing system to perform any of the example methods; and an apparatus including at least one processor, and at least one memory including computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus at least to perform any of the example methods.

[0010] The details of one or more examples or embodiments are set forth in the accompanying drawings and the description below. Other features will be apparent from the description and drawings, and from the claims.BRIEF DESCRIPTION OF THE DRAWINGS

[0011] FIG. 1 is a block diagram of a wireless network.

[0012] FIG. 2 is a signaling diagram illustrating operation between a user device and a network node according to an example embodiment.

[0013] FIG. 3 is a flow chart illustrating operation of a user device according to an example embodiment.

[0014] FIG. 4 is a flow chart illustrating operation of a network node according to an example embodiment.

[0015] FIG. 5 is a block diagram of an example of wireless station or node (e.g., network node, user node or UE, relay node, or other node).DETAILED DESCRIPTION

[0016] It shall be understood that although the terms “first,” “second,”..., etc., in front of noun(s) and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another and they do not limit the order of the noun(s). For example, a first element could be termed a second element, and similarly, a second element could be termed a first element, without departing from the scope of example embodiments. As used herein, the term “and / or” includes any and all combinations of one or more of the listed terms.

[0017] As used herein, unless stated explicitly, performing a step “in response to A” does not indicate that the step is performed immediately after “A” occurs, and one or more intervening steps may be included.

[0018] FIG. 1 is a block diagram of a wireless network 130. In the wireless network 130 of FIG. 1 , user devices 131 , 132, 133 and 135, which may also be referred to as mobile stations (MSs) or user equipment (UEs), may be connected (and in communication) with a base station (BS) 134, which may also be referred to as an access point (AP), an enhanced Node B (eNB), a gNB, or a RAN(radio access network) node. BS (or AP) 134 provides wireless coverage within a cell 136, including to user devices (or UEs) 131, 132, 133 and 135. BS 134 is also connected to a core network 150 via a N2 or NG interface 151. Although only four user devices (or UEs) are shown as being connected or attached to one BS 134, any number of user devices and / or BS may be provided.

[0019] At least part of the functionalities of a BS (e.g., NG-RAN, gNB, access point (AP), base station (BS) or (e)Node B (eNB), RAN node) may also be carried out by any node, server or host which may be operably coupled to a transceiver, such as a remote radio head. For instance, some functionalities of a BS may be carried out, at least partly, in a central / centralized unit, CU and / or a distributed unit, DU. Thus, 5G networks architecture may be based on a so-called CU-DU split. The gNB-CU (central node) may control a plurality of spatially separated gNB-DUs, acting at least as transmit / receive (Tx / Rx) nodes. In some embodiments, however, the gNB-DUs (also called DU) may comprise e.g., a radio link control (RLC), medium access control (MAC) layer and a physical (PHY) layer, whereas the gNB-CU (also called a CU) may comprise the layers above RLC layer, such as a packet data convergence protocol (PDCP) layer, a radio resource control (RRC) and an internet protocol (IP) layer.Other functional splits are possible, too.

[0020] According to an illustrative example, a radio access network (RAN) may be part of a mobile telecommunication system. A RAN may include one or more BSs or RAN nodes that implement a radio access technology, e.g., to allow one or more UEs to have access to a network or core network (CN). Thus, for example, the RAN (RAN nodes, such as BSs or gNBs) may reside between one or more user devices or UEs and a core network. According to an example embodiment, each RAN node (e.g., BS, eNB, gNB, CU / DU, ...) or BS may provide one or more wireless communication services for one or more UEs or user devices, e.g., to allow the UEs to have wireless access to a network, via the RAN node. Each RAN node or BS may perform or provide wireless communication services, e.g., such as allowing UEs or user devices to establish a wireless connection to the RAN node, and sending datato and / or receiving data from one or more of the UEs. For example, after establishing a connection to a UE, a RAN node or network node (e.g., BS, eNB, gNB, CU / DU, ...) may forward data to the UE that is received from a network or the core network, and / or forward data received from the UE to the network or core network. RAN nodes or network nodes (e.g., BS, eNB, gNB, CU / DU, ...) may perform a wide variety of other wireless functions or services, e.g., such as broadcasting control information (e.g., such as system information or on-demand system information) to UEs, paging UEs when there is data to be delivered to the UE, assisting in handover of a UE between cells, scheduling of resources for uplink data transmission from the UE(s) and downlink data transmission to UE(s), sending configuration information to configure one or more UEs, and the like. These are a few examples of one or more functions that a RAN node or BS may perform.

[0021] A user device or user node (user terminal, user equipment (UE), mobile terminal, handheld wireless device, etc.) may refer to a portable computing device that includes wireless mobile communication devices operating either with or without a subscriber identification module (SIM), including, but not limited to, the following types of devices: a mobile station (MS), a mobile phone, a cell phone, a smartphone, a personal digital assistant (PDA), a handset, a device using a wireless modem (alarm or measurement device, etc.), a laptop and / or touch screen computer, a tablet, a phablet, a game console, a notebook, a vehicle, a drone, a sensor, and a multimedia device, as examples, or any other wireless device. It should be appreciated that a user device may also be (or may include) a nearly exclusive uplink only device, of which an example is a camera or video camera loading images or video clips to a network. Also, a user node may include a user equipment (UE), a user device, a user terminal, a mobile terminal, a mobile station, a mobile node, a subscriber device, a subscriber node, a subscriber terminal, or other user node. For example, a user node may be used for wireless communications with one or more network nodes (e.g., gNB, eNB, BS, AP, CU, DU, CU / DU) and / or with one or more other user nodes, regardless of the technology or radio access technology (RAT).

[0022] In 5G (which may be referred to as New Radio (NR)) (as an illustrative example), core network 150 may be referred to 5G core network (5GC), which may include an access and mobility management function (AMF). For the example, the AMF may include the following functionalities (e.g., some of the AMF functionalitiesmay be supported in a single instance of an AMF): termination of RAN control plane (CP) interface (N2), termination of non-access stratum (NAS) (or N1), NAS ciphering and integrity protection, registration management, connection management, reachability management, mobility management, lawful intercept, and / or the like. The 5GC may also include a session management function (SMF) that may include one or more of the following functionalities (one or more of the SMF functionalities may be supported in a single instance of a SMF): session management (e.g., session establishment, modification and release, including tunnel maintenance between a user plane function (UPF) and BS 134), IP address allocation & management (including optional authorization), selection and control of UPF(s), configuration of traffic steering at a UPF to route traffic to proper destination, and / or the like. In LTE (as an illustrative example), core network 150 may be referred to as Evolved Packet Core (EPC), which may include a mobility management entity (MME) which may handle or assist with mobility / handover of user devices between BSs, one or more gateways that may forward data and control signals between the BSs and packet data networks or the Internet, and other control functions or blocks.

[0023] In addition, the techniques described herein may be applied to various types of user devices or data service types, or may apply to user devices that may have multiple applications running thereon that may be of different data service types. New Radio (5G) development may support a number of different applications or a number of different data service types, such as for example: machine type communications (MTC), enhanced machine type communication (eMTC), Internet of Things (loT), and / or narrowband loT user devices, enhanced mobile broadband (eMBB), and ultra-reliable and low-latency communications (URLLC). Many of these new 5G (NR) - related applications may require generally higher performance than previous wireless networks.

[0024] loT may refer to an ever-growing group of objects that may have Internet or network connectivity, so that these objects may send information to and receive information from other network devices. For example, many sensor type applications or devices may monitor a physical condition or a status and may send a report to a server or other network device, e.g., when an event occurs. Machine Type Communications (MTC, or Machine to Machine communications) may, for example, be characterized by fully automatic data generation, exchange, processing and actuation among intelligent machines, with or without intervention of humans.Enhanced mobile broadband (eMBB) may support much higher data rates than currently available in LTE.

[0025] Ultra-reliable and low-latency communications (URLLC) is a new data service type, or new usage scenario, which may be supported for New Radio (5G) systems. This enables emerging new applications and services, such as industrial automations, autonomous driving, vehicular safety, e-health services, and so on. 3GPP targets in providing connectivity with reliability corresponding to block error rate (BLER) of 10’5and up to 1 ms U-Plane (user / data plane) latency, by way of illustrative example. Thus, for example, URLLC user devices / UEs may require a significantly lower block error rate than other types of user devices / UEs as well as low latency (with or without requirement for simultaneous high reliability). Thus, for example, a URLLC UE (or URLLC application on a UE) may require much shorter latency, as compared to an eMBB UE (or an eMBB application running on a UE).

[0026] The techniques described herein may be applied to a wide variety of wireless technologies or wireless networks, such as 5G (New Radio (NR)), cmWave, and / or mmWave band networks, loT, MTC, eMTC, eMBB, URLLC, 6G, etc., or any other wireless network or wireless technology. These example networks, technologies or data service types are provided only as illustrative examples.

[0027] A machine learning (ML) model may be used within a wireless network to perform (or assist with performing) one or more tasks. In general, one or more nodes (e.g., BS, gNB, eNB, RAN node, user node, UE, user device, relay node, or other wireless node) within a wireless network may use or employ a ML model, e.g., such as, for example a neural network model (e.g., which may be referred to as a neural network, an artificial intelligence (Al) neural network, an Al neural network model, an Al model, a machine learning (ML) model or algorithm, a model, or other term) to perform, or assist in performing, one or more ML-enabled tasks. Other types of models may also be used. A ML-enabled task may include tasks that may be performed (or assisted in performing) by a ML model, or a task for which a ML model has been trained to perform or assist in performing).

[0028] A UE may use a random access procedure to perform initial access to a gNB or to establish a connection to the gNB. In an example, a four-step random access (RA) procedure may include the following. At step 1 a UE may transmit to a gNB a random access (RA) preamble, e.g., in a physical random-access channel(PRACH) (e.g., message 1 or msg 1 ). At step 2, the gNB may transmit to the UE, a random-access response (RAR) (e.g., message 2 or msg 2) indicating resource parameters needed for the device transmitting an UL message to the network.In an example, the gNB (in the RAR or msg 2) may provide a timing advance or time-alignment command to the UE to adjust the UE uplink (UL) transmission timing based on the timing of the received RA preamble. In an example, the gNB (in the RAR or msg 2) may provide an uplink (UL) grant for the UL message. At step 3 and step 4, the UE and the gNB may exchange messages (uplink message 3 or msg 3 and subsequent downlink message 4 or msg 4) with the aim of resolving potential collisions, also referred to as contention resolution. A two-step random access procedure may also be performed, instead of the four-step random access procedure.

[0029] ML-based algorithms or ML models may be used to perform and / or assist with performing a variety of wireless and / or radio resource management (RRM) and / or RAN-related functions or tasks to improve network performance, such as, e.g., in the UE for beam prediction (e.g., predicting a best beam or best beam pair based on measured reference signals), antenna panel or beam control, RRM (radio resource measurement) measurements and feedback (channel state information (CSI) feedback), link monitoring, Transmit Power Control (TPC), etc.In some cases, ML models may be used to improve performance of a wireless network in one or more aspects or as measured by one or more performance indicators or performance criteria.

[0030] Models (e.g., neural networks or ML models) may be or may include, for example, computational models used in machine learning made up of nodes organized in layers. The nodes are also referred to as artificial neurons, or simply neurons, and perform a function on provided input to produce some output value. A neural network or ML model may typically require a training period to learn the parameters, i.e., weights, used to map the input to a desired output. The mapping may occur via the function that is learned from a given data for the problem in question. Thus, the weights are weights for the mapping function of the neural network. Each neural network model or ML model may be trained for a particular task.

[0031] To provide the output given the input, the ML functionality of a neural network model or ML model should be trained, which may involve learning the proper value for a large number of parameters (e.g., weights and / or biases) for themapping function (or of the ML functionality of the ML model). For example, the parameters may be used to weight and / or adjust terms in the mapping function. This training may be an iterative process, with the values of the weights and / or biases being tweaked over many (e.g., tens, hundreds and / or thousands) of rounds of training episodes or training iterations until arriving at the optimal, or most accurate, values (or weights and / or biases). In the context of neural networks (neural network models) or ML models, the parameters may be initialized, often with random values, and a training optimizer iteratively updates the parameters (e.g., weights) of the neural network to minimize error in the mapping function. In other words, during each round, or step, of iterative training the network updates the values of the parameters so that the values of the parameters eventually converge to the optimal values.

[0032] ML models may be trained in either a supervised or unsupervised manner, as examples. In supervised learning, training examples are provided to the ML model or other machine learning algorithm. A training example includes the inputs and a desired or previously observed output. Training examples are also referred to as labeled data because the input is labeled with the desired or observed output. In the case of a neural network (which may be a specific case of ML model), the network (or ML model) learns the values for the weights used in the mapping function or ML functionality of the ML model that most often result in the desired output when given the training inputs. In unsupervised training, the ML model learns to identify a structure or pattern in the provided input. In other words, the model identifies implicit relationships in the data. Unsupervised learning is used in many machine learning problems and typically requires a large set of unlabeled data.

[0033] According to an example embodiment, A network node, e.g., a gNB may configure a UE with a set of candidate beams that may be used by the UE to perform beam failure recovery. The gNB may configure a UE with a set of candidate beams, e.g., by providing the beam index (e.g., channel state information-reference signal (CSI-RS) beam index or a CSI-RS resource indicator (CRI), or a synchronization signal block (SSB) beam index or a SSB resource indicator (SSBRI)), and / or the time / frequency resources for each of the candidate beams. The UE may perform beam measurement or measure a beam quality (e.g., measure reference signal received power (RSRP), reference signal received quality (RSRQ), signal to interference plus noise ratio (SINR), or other beam quality measurement or beammeasurement) on one or more beams of the set of candidate beams, and the UE may send a report to the gNB of the beam measurements (or beam quality measurement) and / or may indicate when an event has occurred with respect to one or more of the candidate beams. An example event may include the UE determining when a candidate beam has a beam quality (or beam measurement) that is less than a threshold, for example.

[0034] A UE may use a candidate beam(s) of the set of candidate beams to perform beam failure recovery (e.g., with respect to a currently used beam that is used for communication by the UE with the gNB). If a beam failure of the currently used beam occurs or is detected (e.g., detected by the UE based on a beam quality, or detected by the gNB and reported to the UE), the UE may perform beam failure recovery, e.g., which may include the UE transmitting a beam failure recovery transmission to the gNB. The beam failure recovery transmission may include, for example, the UE transmitting a random access preamble (PRACH) (msg1 of the random access (RA) procedure) on one or more of the candidate beams, e.g., which notifies the gNB that this is the new beam that the UE will use for communicating with the gNB. The gNB may receive the random access preamble, and may send a random access response (msg2 of RA procedure) to the UE, which confirms to the UE that the UE may use this beam (for which a corresponding random access response was received by the UE) for communication with the gNB.

[0035] In addition, a UE may use or employ a ML model to obtain a set of predicted top-K beams from the ML model. The set of predicted top-K beams may be provided in spatial and temporal (time) domains, e.g., one or more best or top predicted beams (e.g., predicted to have a best beam quality) for one or more time periods or time intervals (e.g., the top-3 beams predicted for each of the next X time intervals). The ML model may predict a set of top-K beams (e.g., top-1 beam, top-3 beams, top-5 beams, top-8 beams,...) for the UE. When reporting the set of predicted top-K beams (e.g., in an inference report) to the gNB, the report may include a beam identity of the beam (e.g., CRI or SSBRI) and / or a predicted beam quality (e.g., measured and / or predicted RSRP, RSRQ, SINR or other beam quality of the beam).

[0036] UE initiated beam management (UEIBM) reporting refers to, or may include, the case where a UE may be configured with at least one event or condition, and then the UE transmits a beam report to the gNB if the event or condition is metor occurs. For example, the UE may be configured to measure a set of beams, which may include, e.g., the current beam, a candidate beam and / or a predicted beam, and the UE may send a beam measurement report to the gNB when the event is detected by the UE. The event may include many different events, e.g., such as the current beam quality (e.g., RSRP, RSRQ, SINR, or other beam quality) becoming worse than a threshold, or a candidate beam or a top-K beam becoming worse than a threshold or a threshold worse than some other specified beam, etc. Or, as an example, an event that may trigger a UEIBM report to the gNB may include where the beam quality of at least one new beam, e.g., L1-RSRP, becomes a threshold value (e.g., 3dB) better than the current beam, then the UE will transmit a report indicating occurrence of the event (e.g., identifying the one or more beams that satisfies this event), and / or a beam measurement report.

[0037] FIG. 2 is a signaling diagram illustrating operation between a user device and a network node according to an example embodiment. Referring to FIG. 2, a UE 210 may include a machine learning (ML) model. As noted, the ML model may provide or output a set of predicted top-K beams to the UE 210. UE 210 may be in communication with and / or may be connected to gNB 212 (or other network node). At step 1 of FIG. 2, UE 210 transmits a capability indication to gNB 212, indicating a capability of the UE 210 to perform beam prediction (e.g., downlink transmit beam prediction, or prediction of other beams), such as via use of the ML model that may provide or output a set of predicted top-K beams for the UE 210, and / or capability of the UE 210 to support update of a set of candidate beams for beam failure recovery.

[0038] At step 2 of FIG. 2, UE 210 receives from gNB 212 a configuration information, including a configuration of a CSI (channel state information) report based on which the beam prediction is performed.

[0039] Also, at step 2 of FIG. 2, the configuration information received by UE 210 may also indicate information of a set of candidate beams, including beam identification information (or beam identities), and information indicating random access preambles and / or random access resources (e.g., random access occasions) associated with each candidate beam of the set of candidate beams. As noted above, the candidate beams may be used by the UE 210 for beam failure recovery, after a beam failure detection of a current beam (currently used beam) has been detected.

[0040] At step 3 of FIG. 2, the gNB 212 transmits a set of reference signals (RSs) (e.g., which may be include CSI-RS and / or SSB reference signals). UE 210 may receive and perform beam quality measurements (e.g., RSRP, RSRQ, SINR, or other beam quality measurement) for one or more of the received reference signals, and these beam quality measurements may be input to the ML model of UE 210, e.g., to assist the ML model in determining (e.g., predicting) a set of predicted top-K beams for the UE 210.

[0041] At step 4 of FIG. 2, the ML model of UE 210 may perform beam prediction (e.g., DL transmit beam prediction, or other beam prediction), for example, to determine or output a set of predicted top-K beams. At step 4, UE 210 may obtain from the ML model information indicating a set of predicted top-K beams in spatial and temporal domains. The information indicating the set of predicted top-K beams obtained by the UE 210 from the ML model may include a beam identification (e.g., CRI and / or SSBRI) and / or a beam quality (e.g., predicted beam quality, such as RSRP, RSRQ, SINR, ...) for each of the predicted top beams of the set of predicted top-K beams

[0042] At step 5 of FIG. 2, UE 210 may transmit a report of the set of predicted top-K beams, e.g., wherein the report transmitted to the gNB 212 may include a beam identification (e.g., CRI and / or SSBRI), a beam quality (e.g., predicted beam quality, such as predicted RSRP, RSRQ, SINR, ...), and / or a time (e.g., time period or time interval) or timing indication or occasion for each of the predicted top beams of the set of predicted top-K beams.

[0043] Referring to FIG. 2, steps 6 and 7 are provided for event reporting on candidate beams. The detection of an event (step 6) and reporting of the event (step 7) may be implemented as UE initiated beam management (UEIBM) report, which refers to, or may include, the case where a UE may be configured with at least one event or condition, and then the UE transmits a beam report to the gNB if the event or condition is met or occurs.

[0044] At step 6 of FIG. 2, UE 210 determines whether an event has occurred for a candidate beam of the current set of candidate beams. The UE 210 may determine an event for a candidate beam based on a beam quality (e.g., measured beam quality measured by UE 210, or a predicted beam quality provided by the ML model for the set of predicted top-K beams, for example, if the candidate beam is one of the set of predicted top-K beams) of a candidate beam. For example, theevent associated with the set of candidate beams may include at least one of the following: event X1 : a beam quality of a best candidate beam of the set of candidate beams becomes a threshold worse than a beam quality of a best predicted beam of the set of predicted top-K beams; event X2: a beam quality of any candidate beam of the set of candidate beams becomes a threshold worse than a beam quality of a best predicted beam of the set of predicted top-K beams; or event X3: a beam quality of any candidate beam of the set of candidate beams is worse than a threshold. These are examples of events that may be detected by UE 210 for candidate beams. Thus, for example, in some cases, the event detected by UE 210 for a candidate beam may be detected based on a beam quality (measured or predicted beam quality) of the candidate beam with respect to a beam quality (measured quality or predicted quality) of a predicted beam of the set of predicted top-K beams. The beam quality of a candidate beam may include a measured beam quality or a predicted beam quality of the candidate beam, and the beam quality of a predicted beam may include a predicted beam quality or a measured beam quality of the predicted beam.

[0045] At step 7 of FIG. 2, UE 210 transmits a report of the detected event associated with the current set of candidate beams. The event report transmitted by the UE at step 7 may indicate the candidate beam (e.g., CRI or SSBRI of the candidate beam that satisfied the event), an identification of the event (e.g., event X1 , event X2, event X3), and / or an identification of the predicted top beam for which the event of the candidate beam was detected (e.g., an identification of the predicted top beam for which the beam quality of candidate beam was compared to beam quality of the predicted top beam, e.g., for events X1 , X2).

[0046] At step 8 of FIG. 2, the UE 210 determines information of a proposed set of candidate beams. For example, the UE 210 may determine a proposed set of candidate beams based on the set of predicted top-K beams and / or based on any events associated with a candidate beam of the set of candidate beams. For example, the proposed set of candidate beams may include at least one of the set of predicted top-K beams, or may include some or all of the set of predicted top-K beams.

[0047] Also, for example, with respect to step 8 of FIG. 2, the proposed set of candidate beams may be determined, by UE 210, to include the set of predicted top-K beams, excluding any of the predicted beam of the set of predicted top-K beams for which a beam failure detection has been detected, e.g., based on beamqualities (measured or predicted beam qualities) of this beam of the set of predicted top-K beams. For example, a beam that is part of the set of predicted top-K beams may be excluded if that beam has a beam quality (measured quality or predicted quality) that is less than a threshold.

[0048] At step 9 of FIG. 2, the UE 210 transmits to gNB 212 information of the proposed set of candidate beams, e.g., including information (e.g., CRI or SSBRI) identifying the beams of the proposed set of candidate beams.

[0049] At step 10 of FIG. 2, the gNB 212 may determine and send to the UE 210 updated information of the set of candidate beams (e.g., determines an updated set of candidate beams), e.g., based on the proposed set of candidate beams. The updated set of candidate beams determined by the gNB 212 may include at least one (and may include all or some) of the set of predicted top-K beams reported to gNB 212 at step 5. The updated set of candidate beams may include the proposed set of candidate beams, excluding (but omitting) any proposed candidate beam for which a beam failure detection has been detected by the gNB 212. Thus, for example, the updated set of candidate beams may include, e.g.: a beam for which a beam failure detection has not been detected by the gNB 212 based on beam measurements or beam qualities (measured or predicted beam qualities); a predicted beam for which a beam failure detection has not been detected by the gNB 212 based on beam quality for the predicted beam; or a proposed candidate beam of the proposed set of candidate beams for which a beam failure detection has not been detected by the gNB 212 based on beam quality for the proposed candidate beam.

[0050] As an example, a beam failure detection may be detected based on a measured beam quality or a predicted beam quality being less than a threshold.The gNB 212 may determine an updated set of candidate beams even if UE 210 does not send information of a proposed set of candidate beams at step 9. Thus, the updated set of candidate beams may be determined based on the proposed set of candidate beams (if sent by the UE), and / or based on the set of predicted top-K beams reported to the gNB at step 5, and the updated set of candidate beams may exclude or omit, e.g., beams for which a beam failure detection has been detected by the gNB 212.

[0051] Thus, at step 10 of FIG. 2, the UE 210 may receive the updated information of the set of candidate beams (the information of the updated set of candidate beams),e.g., including beam identification, resources to be used for transmission of the beams, and / or a random access preamble and / or resources for random access preamble transmission.

[0052] At step 11 of FIG. 2, when a beam failure is detected, the UE 210 may transmit a beam failure recovery transmission, which may include the UE transmitting a random access preamble (or PRACH) associated with a candidate beam of the updated set of candidate beams that was sent to the UE at step 10. The transmission of the random access preamble (or PRACH) at step 11 indicates to gNB 212 the new beam that the UE 210 is proposing to use for communication with gNB 212.After receiving the random access preamble associated with the candidate beam of the updated set of candidate beams, the gNB 212 may transmit a random access response (msg2 of random access procedure) to the UE 210, confirming that the UE 210 may use this indicated candidate beam for communication with gNB 212.

[0053] FIG. 3 is a flow chart illustrating operation of a user device according to an example embodiment. Operation 310 includes receiving, by a user device (e.g., UE) from a network node (e.g., gNB), information of a set of candidate beams, wherein one or more beams of the set of candidate beams are to be used for beam failure recovery. Operation 320 includes obtaining, by the user device from a machine learning (ML) model at the user device, information indicating a set of predicted top beams. Operation 330 includes transmitting, by the user device to the network node, a report of the set of predicted top beams, the report comprising a beam identity for each predicted top beam of the set of predicted top beams. Operation 340 includes determining an event associated with the set of candidate beams based on a beam quality of at least one of the candidate beams. Operation 350 includes transmitting, by the user device to the network node, a report of the event associated with the set of candidate beams. Operation 360 includes determining, by the user device, a proposed set of candidate beams based on the set of predicted top beams.Operation 370 includes transmitting, by the user device to the network node, the proposed set of candidate beams. Operation 380 includes receiving, by the user device from the network node, an updated information of the set of candidate beams. And, operation 490 includes performing, by the user device to the network node, a beam failure recovery procedure based on the updated set of candidate beams.

[0054] FIG. 4 is a flow chart illustrating operation of a network node according to an example embodiment. Operation 410 includes transmitting, by a network node(e.g., gNB) to a user device (e.g., UE), information of a set of candidate beams, wherein one or more beams of the set of candidate beams are to be used for beam failure recovery. Operation 420 includes receiving, by the network node from the user device, a report of a set of predicted top beams, the report comprising a beam identity for each predicted top beam of the set of predicted top beams. Operation 430 includes receiving, by the network node from the user device, a report of an event of a candidate beam of the set of candidate beams. Operation 440 includes receiving, by the network node from the user device, a proposed set of candidate beams based on the set of predicted top beams. Operation 450 includes determining, by the network node, an updated information of the set of candidate beams based on the proposed set of candidate beams. Operation 460 includes transmitting, by the network node to the user device, the updated information of the set of candidate beams. And, operation 470 includes receiving, by the network node from the user device, a beam failure recovery transmission based on the updated information of the set of candidate beams.

[0055] Some examples will be described.

[0056] Example 1. A method comprising: receiving, by a user device from a network node, information of a set of candidate beams, wherein one or more beams of the set of candidate beams are to be used for beam failure recovery; obtaining, by the user device from a machine learning (ML) model at the user device, information indicating a set of predicted top beams; transmitting, by the user device to the network node, a report of the set of predicted top beams, the report comprising a beam identity for each predicted top beam of the set of predicted top beams; determining an event associated with the set of candidate beams based on a beam quality of at least one of the candidate beams; transmitting, by the user device to the network node, a report of the event associated with the set of candidate beams; determining, by the user device, a proposed set of candidate beams based on the set of predicted top beams; transmitting, by the user device to the network node, the proposed set of candidate beams; receiving, by the user device from the network node, an updated information of the set of candidate beams; and performing, by the user device to the network node, a beam failure recovery procedure based on the updated set of candidate beams.

[0057] Example 2. The method of Example 1 , wherein the updated information of the set of candidate beams includes information associated with one or more proposed candidate beams.

[0058] Example 3. The method of any of Examples 1 -2, wherein the proposed set of candidate beams comprises at least one of the predicted top beams of the set of predicted top beams.

[0059] Example 4. The method of any of Examples 1-3, wherein the information of the set of candidate beams comprises information of random access preambles and resources associated with the set of candidate beams.

[0060] Example 5. The method of any of Examples 1 -4, wherein the determining the proposed set of candidate beams comprises: determining, by the user device, the proposed set of candidate beams comprising the set of predicted top beams, excluding any of the predicted top beams of the set of top beams for which a beam failure detection has been detected by the user device based on beam qualities of the predicted top beams of the set of predicted top beams.

[0061] Example 6. The method of Example 5, wherein the excluded beam of the set of predicted top beams has a beam quality that is less than a threshold.

[0062] Example 7. The method of any of Examples 1 -6, wherein the event associated with the set of candidate beams comprises at least one of the following: a beam quality of a best candidate beam of the set of candidate beams becomes a threshold worse than a beam quality of a best predicted beam of the set of predicted top beams; a beam quality of any candidate beam of the set of candidate beams becomes a threshold worse than a beam quality of a best predicted beam of the set of predicted top beams; or a beam quality of any candidate beam of the set of candidate beams is worse than a threshold.

[0063] Example s. The method of Example 7, wherein: the beam quality of a candidate beam comprises a measured beam quality or a predicted beam quality of the candidate beam, and the beam quality of a predicted top beam comprises a predicted beam quality or a measured beam quality of the predicted top beam.

[0064] Example 9. The method of any of Examples 1 -8, further comprising: receiving, by the user device from the network node, reference signals for a plurality of beams; measuring the plurality of beams; wherein the obtained set of predicted top beams from the ML model comprises predicted top beams that are predicted based at least on the beam measurements.

[0065] Example 10. The method of any of Examples 1 -9, further comprising: transmitting, by the user device to the network node, a capability indication indicating a capability of the user device to support update of the set of candidate beams.

[0066] Example 11. An apparatus comprising: at least one processor; and at least one memory storing instructions that when executed by the at least one processor, cause the apparatus at least to perform: receiving, by a user device from a network node, information of a set of candidate beams, wherein one or more beams of the set of candidate beams are to be used for beam failure recovery; obtaining, by the user device from a machine learning (ML) model at the user device, information indicating a set of predicted top beams; transmitting, by the user device to the network node, a report of the set of predicted top beams, the report comprising a beam identity for each predicted top beam of the set of predicted top beams; determining an event associated with the set of candidate beams based on a beam quality of at least one of the candidate beams; transmitting, by the user device to the network node, a report of the event associated with the set of candidate beams; determining, by the user device, a proposed set of candidate beams based on the set of predicted top beams; transmitting, by the user device to the network node, the proposed set of candidate beams; receiving, by the user device from the network node, an updated information of the set of candidate beams; and performing, by the user device to the network node, a beam failure recovery procedure based on the updated set of candidate beams.

[0067] Example 12. The apparatus of Example 11 , wherein the updated information of the set of candidate beams includes information associated with one or more proposed candidate beams.

[0068] Example 13. The apparatus of any of Examples 11-12, wherein the proposed set of candidate beams comprises at least one of the predicted top beams of the set of predicted top beams.

[0069] Example 14. The apparatus of any of Examples 11-13, wherein the information of the set of candidate beams comprises information of random access preambles and resources associated with the set of candidate beams.

[0070] Example 15. The apparatus of any of Examples 11-14, wherein the determining the proposed set of candidate beams comprises: determining, by the user device, the proposed set of candidate beams comprising the set of predictedtop beams, excluding any of the predicted top beams of the set of top beams for which a beam failure detection has been detected by the user device based on beam qualities of the predicted top beams of the set of predicted top beams.

[0071] Example 16. The apparatus of Example 15, wherein the excluded beam of the set of predicted top beams has a beam quality that is less than a threshold.

[0072] Example 17. The apparatus of any of Examples 11-16, wherein the event associated with the set of candidate beams comprises at least one of the following: a beam quality of a best candidate beam of the set of candidate beams becomes a threshold worse than a beam quality of a best predicted top beam of the set of predicted top beams; a beam quality of any candidate beam of the set of candidate beams becomes a threshold worse than a beam quality of a best predicted top beam of the set of predicted top beams; or a beam quality of any candidate beam of the set of candidate beams is worse than a threshold.

[0073] Example 18. The apparatus of Example 17, wherein: the beam quality of a candidate beam comprises a measured beam quality or a predicted beam quality of the candidate beam, and the beam quality of a predicted top beam comprises a predicted beam quality or a measured beam quality of the predicted top beam.

[0074] Example 19. The apparatus of any of Examples 11-18, wherein the apparatus is further caused to perform: receiving, by the user device from the network node, reference signals for a plurality of beams; and measuring the plurality of beams; wherein the obtained set of predicted top beams from the ML model comprises predicted top beams that are predicted based at least on the beam measurements.

[0075] Example 20. The apparatus of any of Examples 11-19, wherein the apparatus is further caused to perform: transmitting, by the user device to the network node, a capability indication indicating a capability of the user device to support update of the set of candidate beams.

[0076] Example 21. A method comprising: transmitting, by a network node to a user device, information of a set of candidate beams, wherein one or more beams of the set of candidate beams are to be used for beam failure recovery; receiving, by the network node from the user device, a report of a set of predicted top beams, the report comprising a beam identity for each predicted top beam of the set of predicted top beams; receiving, by the network node from the user device, a report of an event of a candidate beam of the set of candidate beams; receiving, by the network nodefrom the user device, a proposed set of candidate beams based on the set of predicted top beams; determining, by the network node, an updated information of the set of candidate beams based on the proposed set of candidate beams; transmitting, by the network node to the user device, the updated information of the set of candidate beams; and receiving, by the network node from the user device, a beam failure recovery transmission based on the updated information of the set of candidate beams.

[0077] Example 22. The method of Example 21 , wherein the proposed set of candidate beams comprises at least one predicted top beam of the set of the predicted top beams.

[0078] Example 23. The method of any of Examples 21 -22, wherein the updated information of the set of candidate beams comprises at least one of: a beam for which a beam failure detection has not been detected by the network node based on beam quality; a predicted top beam for which a beam failure detection has not been detected by the network node based on beam quality for the predicted top beam; or a candidate beam of the proposed set of candidate beams for which a beam failure detection has not been detected by the network node based on beam quality for the candidate beam.

[0079] Example 24. The method of Example 23, wherein the beam failure detection (BFD) is detected based on a measured beam quality or a predicted beam quality being less than a threshold.

[0080] Example 25. The method of any of Examples 21 -24, wherein the event associated with the set of candidate beams comprises at least one of the following: a beam quality of a best candidate beam of the set of candidate beams becomes a threshold worse than a beam quality of a best predicted beam of the set of predicted top beams; a beam quality of any candidate beam of the set of candidate beams becomes a threshold worse than a beam quality of a best predicted beam of the set of predicted top beams; or a beam quality of any candidate beam of the set of candidate beams is worse than a threshold.

[0081] Example 26. An apparatus comprising: at least one processor; and at least one memory storing instructions that when executed by the at least one processor, cause the apparatus at least to perform: transmitting, by a network node to a user device, information of a set of candidate beams, wherein one or more beams of the set of candidate beams are to be used for beam failure recovery;receiving, by the network node from the user device, a report of a set of predicted top beams, the report comprising a beam identity for each predicted top beam of the set of predicted top beams; receiving, by the network node from the user device, a report of an event of a candidate beam of the set of candidate beams; receiving, by the network node from the user device, a proposed set of candidate beams based on the set of predicted top beams; determining, by the network node, an updated information of the set of candidate beams based on the proposed set of candidate beams; transmitting, by the network node to the user device, the updated information of the set of candidate beams; and receiving, by the network node from the user device, a beam failure recovery transmission based on the updated information of the set of candidate beams.

[0082] FIG. 5 is a block diagram of an example of a wireless station or node (e.g., UE, user device, AP, BS, eNB, gNB, RAN node, network node, TRP, or other node) 1800 according to an example embodiment. The wireless station 1800 may include, for example, one or more (e.g., two as shown in FIG. 5) RF (radio frequency) or wireless transceivers 1802A, 1802B, where each wireless transceiver includes a transmitter to transmit signals and a receiver to receive signals. The wireless station also includes a processor or control unit / entity (controller) 1804 to execute instructions or software and control transmission and receptions of signals, and a memory 1806 to store data and / or instructions.

[0083] Processor 1804 may also make decisions or determinations, generate frames, packets or messages for transmission, decode received frames or messages for further processing, and other tasks or functions described herein. Processor 1804, which may be a baseband processor, for example, may generate messages, packets, frames or other signals for transmission via wireless transceiver 1802 (1802A or 1802B). Processor 1804 may control transmission of signals or messages over a wireless network, and may control the reception of signals or messages, etc., via a wireless network (e.g., after being down-converted by wireless transceiver 1802, for example). Processor 1804 may be programmable and capable of executing software or other instructions stored in memory or on other computer media to perform the various tasks and functions described above, such as one or more of the tasks or methods described above. Processor 1804 may be (or may include), for example, hardware, programmable logic, a programmable processor that executes software or firmware, and / or any combination of these. Using otherterminology, processor 1804 and transceiver 1802 together may be considered as a wireless transmitter / receiver system, for example.

[0084] In addition, referring to FIG. 5, a controller (or processor) 1808 may execute software and instructions, and may provide overall control for the station 1800, and may provide control for other systems not shown in FIG. 5, such as controlling input / output devices (e.g., display, keypad), and / or may execute software for one or more applications that may be provided on wireless station 1800, such as, for example, an email program, audio / video applications, a word processor, a Voice over IP application, or other application or software.

[0085] In addition, a storage medium may be provided that includes stored instructions, which when executed by a controller or processor may result in the processor 1804, or other controller or processor, performing one or more of the functions or tasks described above.

[0086] According to another example, RF or wireless transceiver(s) 1802A / 1802B may receive signals or data and / or transmit or send signals or data. Processor 1804 (and possibly transceivers 1802A / 1802B) may control the RF or wireless transceiver 1802A or 1802B to receive, send, broadcast or transmit signals or data.

[0087] Examples of the various techniques described herein may be implemented in digital electronic circuitry, or in computer hardware, firmware, software, or in combinations of them. Embodiments may be implemented as a computer program product, i.e., a computer program tangibly embodied in an information carrier, e.g., in a machine readable storage device or in a propagated signal, for execution by, or to control the operation of, a data processing apparatus, e.g., a programmable processor, a computer, or multiple computers. Embodiments may also be provided on a computer readable medium or computer readable storage medium, which may be a non-transitory medium. Embodiments of the various techniques may also include embodiments provided via transitory signals or media, and / or programs and / or software embodiments that are downloadable via the Internet or other network(s), either wired networks and / or wireless networks. In addition, embodiments may be provided via machine type communications (MTC), and also via an Internet of Things (IOT).

[0088] The computer program may be in source code form, object code form, or in some intermediate form, and it may be stored in some sort of carrier, distribution medium, or computer readable medium, which may be any entity or device capableof carrying the program. Such carriers include a record medium, computer memory, read-only memory, photoelectrical and / or electrical carrier signal, telecommunications signal, and software distribution package, for example.Depending on the processing power needed, the computer program may be executed in a single electronic digital computer, or it may be distributed amongst a number of computers.

[0089] Furthermore, embodiments of the various techniques described herein may use a cyber-physical system (CPS) (a system of collaborating computational elements controlling physical entities). CPS may enable the embodiment and exploitation of massive amounts of interconnected ICT devices (sensors, actuators, processors microcontrollers,...) embedded in physical objects at different locations. Mobile cyber physical systems, in which the physical system in question has inherent mobility, are a subcategory of cyber-physical systems. Examples of mobile physical systems include mobile robotics and electronics transported by humans or animals. The rise in popularity of smartphones has increased interest in the area of mobile cyber-physical systems. Therefore, various embodiments of techniques described herein may be provided via one or more of these technologies.

[0090] A computer program, such as the computer program(s) described above, can be written in any form of programming language, including compiled or interpreted languages, and can be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit or part of it suitable for use in a computing environment. A computer program can be deployed to be executed on one computer or on multiple computers at one site or distributed across multiple sites and interconnected by a communication network.

[0091] Method steps may be performed by one or more programmable processors executing a computer program or computer program portions to perform functions by operating on input data and generating output. Method steps also may be performed by, and an apparatus may be implemented as special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit).

[0092] Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer, chip or chipset. Generally,a processor will receive instructions and data from a read-only memory or a random access memory or both. Elements of a computer may include at least one processor for executing instructions and one or more memory devices for storing instructions and data. Generally, a computer also may include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magnetooptical disks, or optical disks.Information carriers suitable for embodying computer program instructions and data include all forms of nonvolatile memory, including by way of example semiconductor memory devices, e.g., EPROM, EEPROM, and flash memory devices; magnetic disks, e.g., internal hard disks or removable disks; magnetooptical disks; and CDROM and DVD-ROM disks. The processor and the memory may be supplemented by, or incorporated in, special purpose logic circuitry.

[0093] To provide for interaction with a user, embodiments may be implemented on a computer having a display device, e.g., a cathode ray tube (CRT) or liquid crystal display (LCD) monitor, for displaying information to the user and a user interface, such as a keyboard and a pointing device, e.g., a mouse or a trackball, by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback, e.g., visual feedback, auditory feedback, or tactile feedback; and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0094] Embodiments may be implemented in a computing system that includes a backend component, e.g., as a data server, or that includes a middleware component, e.g., an application server, or that includes a frontend component, e.g., a client computer having a graphical user interface or a Web browser through which a user can interact with an embodiment, or any combination of such backend, middleware, or frontend components. Components may be interconnected by any form or medium of digital data communication, e.g., a communication network.Examples of communication networks include a local area network (LAN) and a wide area network (WAN), e.g., the Internet.

[0095] While certain features of the described embodiments have been illustrated as described herein, many modifications, substitutions, changes and equivalents will now occur to those skilled in the art. It is, therefore, to be understood that theappended claims are intended to cover all such modifications and changes as fall within the true spirit of the various embodiments.

Claims

WHAT IS CLAIMED IS:

1. A method, comprising:receiving, by a user device from a network node, information of a set of candidate beams, wherein one or more beams of the set of candidate beams are to be used for beam failure recovery;obtaining, by the user device from a machine learning (ML) model at the user device, information indicating a set of predicted top beams;transmitting, by the user device to the network node, a report of the set of predicted top beams, the report comprising a beam identity for each predicted top beam of the set of predicted top beams;determining an event associated with the set of candidate beams based on a beam quality of at least one of the candidate beams;transmitting, by the user device to the network node, a report of the event associated with the set of candidate beams;determining, by the user device, a proposed set of candidate beams based on the set of predicted top beams;transmitting, by the user device to the network node, the proposed set of candidate beams;receiving, by the user device from the network node, an updated information of the set of candidate beams; andperforming, by the user device to the network node, a beam failure recovery procedure based on the updated set of candidate beams.

2. The method of claim 1 , wherein the updated information of the set of candidate beams includes information associated with one or more proposed candidate beams.

3. The method of any of claims 1 -2, wherein the proposed set of candidate beams comprises at least one of the predicted top beams of the set of predicted top beams.

4. The method of any of claims 1 -3, wherein the information of the set of candidate beams comprises information of random access preambles and resources associated with the set of candidate beams.

5. The method of any of claims 1 -4, wherein the determining the proposed set of candidate beams comprises:determining, by the user device, the proposed set of candidate beams comprising the set of predicted top beams, excluding any of the predicted top beams of the set of top beams for which a beam failure detection has been detected by the user device based on beam qualities of the predicted top beams of the set of predicted top beams.

6. The method of claim 5, wherein the excluded beam of the set of predicted top beams has a beam quality that is less than a threshold.

7. The method of any of claims 1 -6, wherein the event associated with the set of candidate beams comprises at least one of the following:a beam quality of a best candidate beam of the set of candidate beams becomes a threshold worse than a beam quality of a best predicted beam of the set of predicted top beams;a beam quality of any candidate beam of the set of candidate beams becomes a threshold worse than a beam quality of a best predicted beam of the set of predicted top beams; ora beam quality of any candidate beam of the set of candidate beams is worse than a threshold.

8. The method of claim 7, wherein:the beam quality of a candidate beam comprises a measured beam quality or a predicted beam quality of the candidate beam, and the beam quality of a predicted top beam comprises a predicted beam quality or a measured beam quality of the predicted top beam.

9. The method of any of claims 1-8, further comprising:receiving, by the user device from the network node, reference signals for a plurality of beams;measuring the plurality of beams;wherein the obtained set of predicted top beams from the ML model comprises predicted top beams that are predicted based at least on the beam measurements.

10. The method of any of claims 1 -9, further comprising:transmitting, by the user device to the network node, a capability indication indicating a capability of the user device to support update of the set of candidate beams.

11. An apparatus, comprising:at least one processor; andat least one memory storing instructions that when executed by the at least one processor, cause the apparatus at least to perform:receiving, by a user device from a network node, information of a set of candidate beams, wherein one or more beams of the set of candidate beams are to be used for beam failure recovery;obtaining, by the user device from a machine learning (ML) model at the user device, information indicating a set of predicted top beams;transmitting, by the user device to the network node, a report of the set of predicted top beams, the report comprising a beam identity for each predicted top beam of the set of predicted top beams;determining an event associated with the set of candidate beams based on a beam quality of at least one of the candidate beams;transmitting, by the user device to the network node, a report of the event associated with the set of candidate beams;determining, by the user device, a proposed set of candidate beams based on the set of predicted top beams;transmitting, by the user device to the network node, the proposed set of candidate beams;receiving, by the user device from the network node, an updated information of the set of candidate beams; andperforming, by the user device to the network node, a beam failure recovery procedure based on the updated set of candidate beams.

12. The apparatus of claim 11 , wherein the updated information of the set of candidate beams includes information associated with one or more proposed candidate beams.

13. The apparatus of any of claims 11-12, wherein the proposed set of candidate beams comprises at least one of the predicted top beams of the set of predicted top beams.

14. The apparatus of any of claims 11-13, wherein the information of the set of candidate beams comprises information of random access preambles and resources associated with the set of candidate beams.

15. The apparatus of any of claims 11-14, wherein the determining the proposed set of candidate beams comprises:determining, by the user device, the proposed set of candidate beams comprising the set of predicted top beams, excluding any of the predicted top beams of the set of top beams for which a beam failure detection has been detected by the user device based on beam qualities of the predicted top beams of the set of predicted top beams.

16. The apparatus of claim 15, wherein the excluded beam of the set of predicted top beams has a beam quality that is less than a threshold.

17. The apparatus of any of claims 11-16, wherein the event associated with the set of candidate beams comprises at least one of the following:a beam quality of a best candidate beam of the set of candidate beams becomes a threshold worse than a beam quality of a best predicted top beam of the set of predicted top beams;a beam quality of any candidate beam of the set of candidate beams becomes a threshold worse than a beam quality of a best predicted top beam of the set of predicted top beams; ora beam quality of any candidate beam of the set of candidate beams is worse than a threshold.

18. The apparatus of claim 17, wherein:the beam quality of a candidate beam comprises a measured beam quality or a predicted beam quality of the candidate beam, and the beam quality of a predicted top beam comprises a predicted beam quality or a measured beam quality of the predicted top beam.

19. The apparatus of any of claims 11-18, wherein the apparatus is further caused to perform:receiving, by the user device from the network node, reference signals for a plurality of beams; andmeasuring the plurality of beams;wherein the obtained set of predicted top beams from the ML model comprises predicted top beams that are predicted based at least on the beam measurements.

20. The apparatus of any of claims 11-19, wherein the apparatus is further caused to perform:transmitting, by the user device to the network node, a capability indication indicating a capability of the user device to support update of the set of candidate beams.

21. A method, comprising:transmitting, by a network node to a user device, information of a set of candidate beams, wherein one or more beams of the set of candidate beams are to be used for beam failure recovery;receiving, by the network node from the user device, a report of a set of predicted top beams, the report comprising a beam identity for each predicted top beam of the set of predicted top beams;receiving, by the network node from the user device, a report of an event of a candidate beam of the set of candidate beams;receiving, by the network node from the user device, a proposed set of candidate beams based on the set of predicted top beams;determining, by the network node, an updated information of the set of candidate beams based on the proposed set of candidate beams;transmitting, by the network node to the user device, the updated information of the set of candidate beams; andreceiving, by the network node from the user device, a beam failure recovery transmission based on the updated information of the set of candidate beams.

22. The method of claim 21 , wherein the proposed set of candidate beams comprises at least one predicted top beam of the set of the predicted top beams.

23. The method of any of claims 21 -22, wherein the updated information of the set of candidate beams comprises at least one of:a beam for which a beam failure detection has not been detected by the network node based on beam quality;a predicted top beam for which a beam failure detection has not been detected by the network node based on beam quality for the predicted top beam; or a candidate beam of the proposed set of candidate beams for which a beam failure detection has not been detected by the network node based on beam quality for the candidate beam.

24. The method of claim 23, wherein the beam failure detection (BFD) is detected based on a measured beam quality or a predicted beam quality being less than a threshold.

25. The method of any of claims 21 -24, wherein the event associated with the set of candidate beams comprises at least one of the following:a beam quality of a best candidate beam of the set of candidate beams becomes a threshold worse than a beam quality of a best predicted beam of the set of predicted top beams;a beam quality of any candidate beam of the set of candidate beams becomes a threshold worse than a beam quality of a best predicted beam of the set of predicted top beams; ora beam quality of any candidate beam of the set of candidate beams is worse than a threshold.

26. An apparatus, comprising:at least one processor; andat least one memory storing instructions that when executed by the at least one processor, cause the apparatus at least to perform:transmitting, by a network node to a user device, information of a set of candidate beams, wherein one or more beams of the set of candidate beams are to be used for beam failure recovery;receiving, by the network node from the user device, a report of a set of predicted top beams, the report comprising a beam identity for each predicted top beam of the set of predicted top beams;receiving, by the network node from the user device, a report of an event of a candidate beam of the set of candidate beams;receiving, by the network node from the user device, a proposed set of candidate beams based on the set of predicted top beams;determining, by the network node, an updated information of the set of candidate beams based on the proposed set of candidate beams;transmitting, by the network node to the user device, the updated information of the set of candidate beams; andreceiving, by the network node from the user device, a beam failure recovery transmission based on the updated information of the set of candidate beams.

27. The apparatus of claim 26, wherein the proposed set of candidate beams comprises at least one predicted top beam of the set of the predicted top beams.

28. The apparatus of any of claims 26-27, wherein the updated information of the set of candidate beams comprises at least one of:a beam for which a beam failure detection has not been detected by the network node based on beam quality;a predicted top beam for which a beam failure detection has not been detected by the network node based on beam quality for the predicted top beam; or a candidate beam of the proposed set of candidate beams for which a beam failure detection has not been detected by the network node based on beam quality for the candidate beam.

29. The apparatus of claim 28, wherein the beam failure detection (BFD) is detected based on a measured beam quality or a predicted beam quality being less than a threshold.

30. The apparatus of any of claims 26-29, wherein the event associated with the set of candidate beams comprises at least one of the following:a beam quality of a best candidate beam of the set of candidate beams becomes a threshold worse than a beam quality of a best predicted beam of the set of predicted top beams;a beam quality of any candidate beam of the set of candidate beams becomes a threshold worse than a beam quality of a best predicted beam of the set of predicted top beams; ora beam quality of any candidate beam of the set of candidate beams is worse than a threshold.

31. An apparatus, comprising:means for receiving, by a user device from a network node, information of a set of candidate beams, wherein one or more beams of the set of candidate beams are to be used for beam failure recovery;means for obtaining, by the user device from a machine learning (ML) model at the user device, information indicating a set of predicted top beams;means for transmitting, by the user device to the network node, a report of the set of predicted top beams, the report comprising a beam identity for each predicted top beam of the set of predicted top beams;means for determining an event associated with the set of candidate beams based on a beam quality of at least one of the candidate beams;means for transmitting, by the user device to the network node, a report of the event associated with the set of candidate beams;means for determining, by the user device, a proposed set of candidate beams based on the set of predicted top beams;means for transmitting, by the user device to the network node, the proposed set of candidate beams;means for receiving, by the user device from the network node, an updated information of the set of candidate beams; andmeans for performing, by the user device to the network node, a beam failure recovery procedure based on the updated set of candidate beams.

32. An apparatus, comprising:means for transmitting, by a network node to a user device, information of a set of candidate beams, wherein one or more beams of the set of candidate beams are to be used for beam failure recovery;means for receiving, by the network node from the user device, a report of a set of predicted top beams, the report comprising a beam identity for each predicted top beam of the set of predicted top beams;means for receiving, by the network node from the user device, a report of an event of a candidate beam of the set of candidate beams;means for receiving, by the network node from the user device, a proposed set of candidate beams based on the set of predicted top beams;means for determining, by the network node, an updated information of the set of candidate beams based on the proposed set of candidate beams;means for transmitting, by the network node to the user device, the updated information of the set of candidate beams; andmeans for receiving, by the network node from the user device, a beam failure recovery transmission based on the updated information of the set of candidate beams.

33. A computer-readable storage medium comprising instructions stored thereon that, when executed by at least one processor, are configured to cause an apparatus to perform:receiving, by a user device from a network node, information of a set of candidate beams, wherein one or more beams of the set of candidate beams are to be used for beam failure recovery;obtaining, by the user device from a machine learning (ML) model at the user device, information indicating a set of predicted top beams;transmitting, by the user device to the network node, a report of the set of predicted top beams, the report comprising a beam identity for each predicted top beam of the set of predicted top beams;determining an event associated with the set of candidate beams based on a beam quality of at least one of the candidate beams;transmitting, by the user device to the network node, a report of the event associated with the set of candidate beams;determining, by the user device, a proposed set of candidate beams based on the set of predicted top beams;transmitting, by the user device to the network node, the proposed set of candidate beams;receiving, by the user device from the network node, an updated information of the set of candidate beams; andperforming, by the user device to the network node, a beam failure recovery procedure based on the updated set of candidate beams.

34. A computer-readable storage medium comprising instructions stored thereon that, when executed by at least one processor, are configured to cause an apparatus to perform:transmitting, by a network node to a user device, information of a set of candidate beams, wherein one or more beams of the set of candidate beams are to be used for beam failure recovery;receiving, by the network node from the user device, a report of a set of predicted top beams, the report comprising a beam identity for each predicted top beam of the set of predicted top beams;receiving, by the network node from the user device, a report of an event of a candidate beam of the set of candidate beams;receiving, by the network node from the user device, a proposed set of candidate beams based on the set of predicted top beams;determining, by the network node, an updated information of the set of candidate beams based on the proposed set of candidate beams;transmitting, by the network node to the user device, the updated information of the set of candidate beams; andreceiving, by the network node from the user device, a beam failure recovery transmission based on the updated information of the set of candidate beams.

Images