Abstract: Device and techniques for wireless communications are described. A user equipment (UE) may switch from a first bandwidth part (BWP) configuration to a second BWP configuration based on a trigger for transitioning from a first activity state to a second activity state with respect to a cell group. The trigger may be an expiration of a timer at the UE, or the UE may receive control signaling indicating the transition. The second BWP configuration may be based on a mode configured at the UE associated with the second activity state. The configured mode may indicate one or more measurements the UE is to perform while in the second activity state. In some examples, the BWP configuration may include configured BWPs based on the indicated measurements of the configured mode.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive an indication that a high Doppler configuration for UE paging is activated. The UE may detect, based at least in part on receiving the indication that the high Doppler configuration is activated, a phase tracking reference signal (PTRS) for a paging communication. Numerous other aspects are provided.

Abstract: According to an example embodiment, a radio receiver includes at least one processor and at least one memory including computer program code. The at least one memory and the computer program code may be configured to, with the at least one processor, cause the radio receiver to: obtain a data array including a plurality of elements, wherein each element in the plurality of elements in the data array corresponds to a subcarrier in a plurality of subcarriers and to a timeslot in a time interval; obtain a reference signal array representing a reference signal configuration applied during the time interval; implement a neural network; input data into the neural network, wherein the data includes at least the data array and the reference signal array. A radio receiver, a method and a computer program product are disclosed.

Abstract: A data processing apparatus and method, a base station, and a storage medium are provided. The apparatus includes: a processor, configured to determine a computation parallelism degree according to the number of antennas and pilot frequency information, acquire antenna data and channel estimation matrices of respective users, and store the antenna data and the channel estimation matrices in groups in a memory, and determine, according to the computation parallelism degree, target antenna data processed in parallel by an arithmetic unit in a single computation, wherein the target antenna data is part of the antenna data of the respective users; the memory, configured to store the antenna data and the channel estimation matrices in groups, and output the target antenna data and the channel estimation matrices to the arithmetic unit; and the arithmetic unit, configured to compute user data based on the target antenna data and the channel estimation matrices.

Abstract: A communication apparatus includes a PHY frame generating circuit that generates a PHY frame including either of a short Sector Sweep frame and a Sector Sweep frame; and an array antenna that selects, based on the PHY frame, any sector from among a plurality of sectors and transmits the PHY frame. In a case where, in the PHY frame including the short Sector Sweep frame, a Direction field of the short Sector Sweep frame indicates Initiator Sector Sweep, the PHY frame generating circuit replaces a Short Sector Sweep Feedback field indicating a number of a selected best short Sector Sweep with a Short Scrambled Basic Service Set ID field indicating an abbreviated address generated from an address of a destination communication apparatus.

Abstract: The apparatus may be a first device at a first IAB node or the first IAB node itself. The IAB node may be configured to receive a configuration for a first set of reference signals associated with an IAB-MT function of the IAB node, wherein the first set of reference signals overlaps in time with a second set of time periods associated with an IAB-DU function of the IAB node. The IAB node may further be configured to extend an IAB-MT reference-signal measurement period based on the overlap between the first set of reference signals for measurement with the IAB-MT function of the IAB node and the second set of time periods associated with the IAB-DU function of the IAB node.

Abstract: The present disclosure provides a method for determining an antenna port and a communication device. The method includes: transmitting control information, the control information including a first information field, the first information field being used to indicate antenna port information of a plurality of antenna port sets; and determining an antenna port set corresponding to each TCI state in a plurality of TCI states, and determining antenna ports in the plurality of antenna port sets in accordance with the first information field. There is a correspondence between the TCI states and the antenna port sets.

Abstract: A node including a non-planar reflective surface is disclosed. The node may receive, from a base station, an indication of a surface configuration of at least one convex reflective surface of the node. The indication may indicate that the surface configuration corresponds to at least one of a broadcast configuration or a UE-specific configuration. The node may configure, upon receiving the indication of the surface configuration, the at least one convex reflective surface based on the surface configuration. The surface configuration may correspond to at least one of the broadcast configuration or the UE-specific configuration. The node may forward communication received from, or forward communication to, the base station based on the surface configuration of the at least one convex reflective surface.

Abstract: Apparatus and methods are provided for port selection codebook configuration. A user equipment (UE) may decode a channel state information (CSI) report configuration (CSI-ReportConfig) from a base station. The CSI-ReportConfig indicates up to L CSI reference signal (CSI-RS) ports for selection by the UE out of P CSI-RS ports configured for measuring and reporting CSI. The UE determines selected CSI-RS ports out of the P CSI-RS ports. The selected CSI-RS ports include the L CSI-RS ports or less. The UE generates a port selection matrix W1 corresponding to the selected CSI-RS ports. The UE also generates an indication of the port selection matrix W1 to the base station. The CSI-ReportConfig may further configure the UE to select a subset of frequency basis. The UE determines a selected subset of frequency basis and generates a frequency basis selection matrix Wf corresponding to the selected subset of frequency basis.

Abstract: Disclosed are techniques for wireless positioning. In an aspect, a user equipment (UE) reports, to a network entity, a minimum number of symbols of a positioning reference signal (PRS) resource of a first transmission-reception point (TRP) of a pair of TRPs based on a reference signal time difference (RSTD) uncertainty parameter for the pair of TRPs, wherein the minimum number of symbols is less than a total number of symbols allocated for the PRS resource, and performs a positioning measurement of the minimum number of symbols of the PRS resource.

Abstract: A configuration for a UE that measures CLI to determine the reception timing of the CLI signal transmitted from a UE in another cell. Aspects of a method, apparatus, and computer-readable medium are presented herein that provide a solution to the problem of measuring CLI signals by improving the manner in which a wireless device determines the reception timing of a transmitted CLI signal. An apparatus receives a first downlink signal from a first base station. The apparatus receiving a second downlink signal from a second base station. The apparatus determines a CLI signal measurement from a second UE received at the first UE based on a propagation delay difference, the propagation delay difference being based on the first downlink signal and the second downlink signal.

Abstract: Discussed herein are devices, systems, and methods for decentralized device management. A method can include receiving a first message from a second device, implementing a first machine learning (ML) model that operates on the received first message and an observation to determine a next objective to be completed by the first device, and training a simulator to produce the first message based on the observation.

Abstract: Methods, systems, and devices for wireless communications are described. A first user equipment (UE) may be associated with a reconfigurable surface for reflecting transmissions between second and third UEs (e.g., over sidelink resources). In one example, the first UE may transmit signaling indicating that retransmissions of a first message transmitted between a second and third UE and detected by the first UE may be reflected by the reconfigurable surface associated with the first UE. In another example, the first UE may receive a request from a second UE for signal enhancement using a reconfigurable surface, the request associated with a future transmission by the second UE to a third UE. In either case, the UE may determine to perform signal enhancement using a reconfigurable surface and may then reconfigure the reconfigurable surface for reflecting transmissions or retransmissions from the second UE to the third UE.

Abstract: Proposed is a mobile router for transmitting and receiving millimeter waves to and from a base station, the mobile router including a first member including an antenna array configured to transmit and receive the millimeter waves, a second member, and an angle adjustment part connecting the first member to the second member, wherein the angle adjustment part is formed such that the first member and the second member are adjusted at a predetermined angle so as to allow the antenna array to transmit and receive the millimeter waves at a specific angle. The first member including the antenna array is configured to be unfolded at a predetermined angle with respect to the second member in order to transmit and receive a 5G millimeter wave beam signal at a specific angle, and thus a user can optimally adjust the transmission/reception sensitivity of 5G millimeter waves.

Abstract: Embodiments of the present disclosure provide a method of processing received signal using a massive MIMO base station (BS). The BS comprises a radio unit (RU), a distributed unit (DU) and an interface. The method comprises receiving a plurality of signals corresponding to the plurality of antennas, said signals comprises at least one of data signals, demodulation reference signals (DMRS) and sounding reference signals (SRS). The RU or DU performs a grouping operation on a subset of the plurality of signals corresponding to a subset of antennas to generate signal groups. The RU performs a first stage filtering on the signals associated with each group using group specific filters to obtain group specific filtered signals. The DU performs a second stage filtering on the group specific filtered signals to obtain second stage filtered signals.

Abstract: A spatial position-dependent I/Q domain modulation method, dual domain modulation method and multiple access communication method are provided. The methods eliminate the dependence of physical layer secure communication on channel state information, and realize the function that a receiver at an expected position can communicate normally, while an eavesdropper at other positions cannot receive a signal or can only receive a wrong signal. The security capability of a wireless communication system is improved from the spatial dimension. The multiple access communication method can realize the distinguishing of multiple users according to precise spatial position points. Even if a plurality of users are located in the same sector in an angular domain, as long as the spatial positions of these users are different, the method can be used to perform multiple access communication, thereby further improving the spatial multiplexing rate of the system and increasing the system capacity.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive, from a base station, a federated learning configuration comprising an indication of a power control loop for providing an update associated with a machine learning component, wherein the power control loop facilitates receiving the update at a received power that satisfies a received power condition associated with an over-the-air update aggregation procedure. The UE may transmit the update to the base station based at least in part on the federated learning configuration. Numerous other aspects are provided.

Abstract: Receivers, methods, and cores, can provide decision feedback equalization with efficient burst error correction. An illustrative receiver includes: a decision feedback equalizer that derives symbol decisions from a receive signal; a subtractor that determines an equalization error for each said symbol decision; and a post-processor that operates on the symbol decisions and equalization error to detect and correct symbol decision errors. An illustrative receiving method includes: using a decision feedback equalizer to derive symbol decisions from a filtered receive signal; determining an equalization error for each said symbol decision; and processing the symbol decisions and equalization error to detect and correct symbol decision errors. An illustrative semiconductor intellectual property core generates circuitry for implementing a receiving and method as described above.

Abstract: A high-dimensional signal transmission method is provided. The method generates M M-dimensional first signals on the basis of M original signals and generates M M-dimensional second signals on the basis of a precoding signal and of the first signals, and finally, a transmitter sums all of the second signals and then transmits by utilizing M subchannels. As such, each subchannel carries information of the M original signals; hence, when any subchannel experiences deep fading, the deep fading is shared jointly by M signals, thus preventing the deep fading from causing a particularly severe impact on any signal. Moreover, all of the original signals can be recovered by utilizing the signals on the other subchannels, thus increasing the systematic resistance against subchannel deep fading. Meanwhile, the system implements the parallel transmission of the M original signals, thus ensuring the throughput of a communication system.

Abstract: Certain aspects of the present disclosure provide techniques for wireless communication by a user equipment (UE). For example, the UE receives a first indication indicating a same quasi co-location (QCL) mapping for multiple receive beams corresponding to a group of transmit and receive beam pairs from a network entity. Transmit and receive beam pairs are different from each other and grouping of the transmit and receive beam pairs is based on a distance between the UE and the network entity. The UE selects one of the multiple receive beams corresponding to the group of transmit and receive beam pairs, based on the distance between the UE and the network entity.

Abstract: Aspects described herein relate to concurrently communicating with a base station over multiple frequency bands using a same first beam, and switching, according to beam switching criteria, from the first beam to a second beam during a time period, wherein the time period is based on a timing reference associated with a reference band.

Abstract: Methods provide wireless communication using a plurality of Antenna Processing Units APUs distributed along a radio stripe and sharing a bus along the radio stripe. Access is provided to a plurality of APU activation/deactivation states for a respective plurality of environmental conditions, wherein each one of the plurality of APU activation/deactivation states defines APUs of the plurality of APUs that are activated and APUs of the plurality of APUs that are deactivated for the respective one of the plurality of environmental conditions. Responsive to detecting a first one of the plurality of environmental conditions, a first one of the plurality of APU activation/deactivation states corresponding to the first one of the plurality of environmental conditions is applied to activate a first subset of the APUs and to deactivate a second subset of the APUs, wherein the first and second subsets of APUs are mutually exclusive.

Abstract: Aspects are provided which allow a base station to segment a code block into individual code block segments and a UE to determine and indicate a quality of the individual code block segments in a CSI report to a base station. The base station transmits a code block to the UE which includes a plurality of code block segments. The UE determines a code block segment quality of each of the code block segments, and sends a CSI report including one or more of the code block segment qualities to the base station. Thus, the code block segment qualities indicated by the UE allow the base station to determine which segments of the code block should be re-transmitted, for example, based on a best RV to be applied for the code block retransmission, thereby improving retransmission performance.

Abstract: Methods, systems, and devices for reducing channel state information feedback channel overhead by compressing coefficients of precoding vectors and reporting a subset of the compressed coefficients based on several parameters including network-signaled parameters. Some embodiments may be used in wireless communication embodiments in which channel state information from many layers and many frequency domain units need to be reported.

Abstract: This application provides encoding and decoding methods to reduce retransmission in satellite communication. A sending apparatus obtains an information transport block, where the information transport block includes a plurality of code blocks; and generates a redundant code block based on at least two of the plurality of code blocks. The at least two code blocks and the redundant code block are sent over a satellite channel after channel coding. A receiving apparatus receives the to-be-decoded information over the satellite channel, calculates, based on the to-be-decoded information of the at least two code blocks and the redundant code block, an a priori log-likelihood ratio of a to-be-decoded bit, and combines the a priori log-likelihood ratio and a log-likelihood ratio obtained after demodulation, to obtain a diversity gain. Decoding is performed based on the combined log-likelihood ratio. This method improves decoding accuracy and reduces the need for retransmission.

Abstract: The disclosure relates to a method, performed by a user equipment (UE), of transmitting or receiving signals in a wireless communication system, and in an embodiment, the UE transmits, to a base station (BS), UE capability information regarding sequence initialization of a demodulation reference signal (DMRS), receives, from the BS, DMRS configuration information determined based on the UE capability information, and receives the DMRS from the BS based on the DMRS configuration information, wherein the DMRS is generated based on a sequence initialization parameter determined based on a code division multiplexing (CDM) group identifier included in the DMRS configuration information.

Abstract: The invention discloses a DNN watermarking method, comprising embedding part of the digital watermark in selected redundant elements of a deep neural network (DNN) model—without compromising the performance of the DNN. The proposed method aims for a robust watermark scheme by embedding a large watermark that can span the whole DNN model. If an adversary attempts to destroy the watermark, the whole DNN model will be destroyed. However, maximizing the hiding capacity can lead to degradation in the performance of the DNN model. In this work, this capacity-performance trade-off problem is solved using the Discrete Cosine Transform (DCT). Moreover, the DCT can work more efficiently with highly correlated data. Therefore, this work suggests segmenting the weights of the DNN model into correlated segments to fully exploit the advantages of the DCT.

Abstract: A method, network node and wireless device for phase error compensation for Fifth Generation downlink systems with four correlated uncalibrated antennas are provided. A method includes applying N incremented phase rotations to one of the four antennas to produce N channel state information reference signal resources, N being an integer greater than 1. The method also includes transmitting N CSI-RS on 4 CSI-RS ports to a wireless device, WD, each of the N CSI-RS resources being transmitted with a different one of the incremented phase rotations. The method further includes receiving from the WD a CSI-RS resource indication that indicates a particular one of the N CSI-RS resources. The method also includes applying, in subsequent transmissions to the WD, a phase rotation to the one of the four antennas, the phase rotation corresponding to the indicated CSI-RS resource.

Abstract: The present application relates to devices and components including apparatus, systems, and methods for determining a beam for communication between a user equipment and a base station. For example, angle of arrival estimates may be utilized for determining the beam for communication.

Abstract: Methods and systems for detecting human presence in an outdoor monitored site are disclosed. In an configuration, the method may include providing at least three transmitters for transmitting radio signals and at least three receivers for receiving radio signals. Channel state information (CSI) data is extracted from the radio signals. The CSI data include phase values and amplitude values. The CSI data is converted into an image representation map and then a surface map is generated using Machine Learning (ML) networks. The surface map is a representation of correspondence between the image representation map and a 3-dimensional (3D) surface associated with a human body.

Abstract: A communication device includes a plurality of distributed units (DUs), each including an antenna; and a central unit (CU) which is arranged to be spaced from each of the plurality of DUs, and which is connected through each of the plurality of DUs and a plurality of DU links. The central unit measures the channel quality of each of the plurality of DU links, and the central unit can perform control so that power is cut off to the DU corresponding to the DU link if it is determined that the DU link is in an abnormal status during the operation time of a timer (TDU_link) associated with the connection to the DU link, and perform control so that power is supplied to the DU corresponding to the DU link if it is determined that the DU link has returned to a normal status.

Abstract: Systems, methods, and devices to reduce the channel estimation overhead by collecting data from many UEs and building a location-based mathematical model are disclosed. During building of the model, a reference signal is used to collect location- and signal-related data from connected UEs. Once the model is successfully built, it is then transmitted and/or downloaded to each new UE that connects to the base station. The UEs and/or the base stations then use this model to determine their own transmission parameter values. The UEs also report their location to the base stations, which use the model to estimate channel conditions and adapt transmission parameters for themselves.

Abstract: Examples disclosed herein relate to a Multiple-Input Multiple-Output (MIMO) radar for virtual beam steering. The MIMO radar has a plurality of transmit antennas and a receive antenna array having a plurality of radiating elements. The MIMO radar also includes a digital signal processor (DSP) configured to synthesize a virtual receive array having N×M receive subarrays from the plurality of transmit antennas and the receive antenna array, where N is the number of transmit antennas and M is the number of receiving elements. Other examples disclosed herein relate to a method of virtual beam steering.

Abstract: A radio frequency structure includes: a radio frequency front-end module, a switch module, and an antenna module. The radio frequency front-end module includes a radio frequency transceiver, and a first processing module, a second processing module, a third processing module, a fourth processing module, and a fifth processing module that are connected to the radio frequency transceiver. The switch module includes a first switch module and a second switch module. The antenna module includes a first antenna, a second antenna, a third antenna, and a fourth antenna that are used to receive or send radio frequency signals.

Abstract: A high-frequency front end module includes a primary antenna terminal and a secondary antenna terminal, a first multiplexer and a second multiplexer, a switch circuit, and a first amplifier and a second amplifier. The first multiplexer has a first transmission filter and a first reception filter. The second multiplexer has a second transmission filter and a second reception filter. The switch circuit exclusively switches connection between the primary antenna terminal and the first multiplexer and connection between the primary antenna terminal and the second multiplexer, and exclusively switches connection between the secondary antenna terminal and the first multiplexer and connection between the secondary antenna terminal and the second multiplexer.

Abstract: A wireless device receives configuration parameters indicating a linkage between a first search space (SS), of a scheduled cell, and a second SS, of a first bandwidth part (BWP) of a scheduling cell, and that a third SS, of the scheduled cell, is not linked to any SSs of a second BWP of the scheduling cell. In response to the linkage and the first BWP being active, the second SS is monitored for receiving a scheduling indication for the scheduled cell. The wireless device switches from the first BWP to the second BWP as an active BWP of the scheduling cell. In response to the switching and the third SS not being linked to the any SSs of the second BWP, the third SS is monitored for receiving DCI for the scheduled cell. The DCI is received via the third SS and for transmission on the scheduled cell.

Abstract: Aspects presented may enable RF sensing to be adaptive to the environment to improve the sensing, performance, and/or the spectrum efficiency of cellular systems and the power efficiency of RF sensing nodes. In one aspect, an RF sensing node extracts one or more features for a set of objects of an area via at least one non-RF sensor. The RF sensing node transmits, to a network entity, the one or more features or at least one non-RF measurement derived from the one or more features. The RF sensing node receives, from the network entity, an RRS transmission configuration derived based on the one or more features or the at least one non-RF measurement transmitted to the network entity.

Abstract: Apparatuses, systems, and methods for multi-TRP by a UE, including out of order delivery of PDSCH, PUSCH, and/or DL ACK/NACK. The UE may receive, from a base station, a configuration that may include multiple control resource set (CORESET) pools and each CORESET pool may be associated with an index value. The UE may determine that at least two DCIs of the multiple DCIs end at a common symbol and determine, based on one or more predetermined rules, when the UE may be scheduled to receive PDSCHs, transmit PUSCHs, and/or transmit ACK/NACKs from CORESETs associated with the at least two DCIs.

Abstract: Methods, systems, and storage media are described for the Embodiments discussed herein may relate to enhancements to radio link monitoring (RLM) for new radio (NR) systems. Other embodiments may be described and/or claimed.

Abstract: Provided are a data modulation method and apparatus, a device, and a storage medium. The data modulation method comprises: modulating data according to a configured constellation point modulation symbol S(n) set, wherein n is an integer between 0 and N?1, and N is an even integer greater than or equal to 4; and transmitting the modulated data on a physical resource.

Abstract: Disclosed are various techniques for wireless communication. In an aspect, a user equipment (UE) identifies a set of positioning sources, each positioning source comprising a positioning reference signal (PRS) resource, a PRS resource set, a PRS frequency layer, and/or a transmission/reception point (TRP). From the set of positioning sources, the UE identifies a consistency group comprising a collection of positioning sources grouped based on expected values of at least one metric of a reference signal from each positioning source, measured values of the at least one metric for the reference signal from each positioning source, and an error threshold. The UE identifies one or more subsets of positioning sources within the consistency group, each subset having at least one metric error value. The UE reports, to a network entity, information about the consistency group and information about at least one of the subsets of positioning sources within the consistency group.

Abstract: The present disclosure relates to a communication technique for converging a 5G communication system, which is provided to support a higher data transmission rate beyond a 4G system with an IoT technology, and a system therefor. The disclosure may be applied to intelligent services (e.g., smart home, smart building, smart city, smart car or connected car, health care, digital education, retail business, security and safety related service, or the like) based on the 5G communication technology and the IoT related technology. The disclosure relates to a method for recovering a beam into a correct beam according to a position of a terminal using a non-contention-based and contention-based beam failure recovery method in order to recover a beam failure in which communication is disconnected due to movement of a terminal or the like in a wireless communication system performing beam-based communication services.

Abstract: A method for supporting a receiving operation based on 2D-NUC performed by a first wireless device according to the present embodiment, comprises the steps of: receiving first and second input information from a second wireless device; performing equalization on the first and second input information; and generating LLR information on the basis of lookup table information predetermined for the equalized first and second input information and 2D-NUC.

Abstract: Reduced-complexity maximum likelihood sequence detectors (rMLSD) are disclosed for detecting multibit symbols such as those found in pulse amplitude modulation (PAM), quadrature amplitude modulation (QAM), and phase shift keying (PSK) signal constellations with more than two constellation points. One illustrative digital communications receiver includes: an initial equalizer that derives an initial sequence of symbol decisions from a filtered receive signal, each symbol decision in the initial sequence having a second most likely symbol decision; and a rMLSD that derives a final sequence of symbol decisions by evaluating state metrics only for each symbol decision in the initial sequence and its second most likely symbol decision.

Abstract: An apparatus, method and computer program is described comprising: receiving, at a user device, a downlink reference signal from a communication node of a mobile communication system, wherein the downlink reference signal is received by one of a plurality of beams of a receiver of the user device in accordance with a configured beam alignment; determining whether to initiate beam switching to reconfigure the beam alignment at said receiver based, at least in part, on a signal power of the received downlink reference signal; and determining, in the event that beam switching is to be initiated, whether to initiate communication node assisted beam switching or non-communication node assisted beam switching.

Abstract: A wireless device may increment a beam failure instance counter based on detecting a first beam failure instance associated with one or more first reference signals, RSs, for beam failure detection. The wireless device may receive a medium access control control element, MAC CE, activating one or more second RSs for beam failure detection. The wireless device may resetting the beam failure instance counter in response to receiving the MAC CE. increment the beam failure instance counter based on detecting a second beam failure instance associated with the one or more second RSs. The wireless device may initiate a beam failure recovery based on the beam failure instance counter being equal to or greater than a first value.

Abstract: Various schemes pertaining to extremely-high-throughput long training filed (EHT-LTF) sequence design for distributed-tone resource units (dRUs) with peak-to-average power ration (PAPR) reduction in 6 GHz low-power indoor (LPI) systems are described. A communication entity distributes subcarriers of a RU with a resolution of four times (4×) subcarrier spacing to generate a 4×EHT-LTF of an uplink (UL) trigger-based (TB) physical-layer protocol data unit (PPDU) with a dRU. The communication entity then transmits the 4×EHT-LTF for the UL TB PPDU with dRU.

Abstract: A network device is provided that uses power measurements to measure a relative phase between a received signal from a reference antenna in a plurality of antennas and a received signal from each antenna in the plurality of antennas except the reference antenna. The network device may use a direct phase measurement to measure the phase of other received signals from additional antennas.

Abstract: Reliable communication in 5G and planned 6G networks depends on the fast, realtime decision-making regarding signal quality, beam parameters, and modulation. Rapid-fire messaging among hordes of diverse users in a busy urban setting will require efficient procedures for managing beam parameters in realtime, under complex changing conditions. The required time scales have already shrunk below the reflex time of humans. Therefore, artificial intelligence procedures are required for certain key aspects of feedback beam management. Disclosed are AI models for (a) instant evaluation of signal quality based on received signal properties and backgrounds, (b) incremental adjustment of beam parameters on demand, and (c) adapting the modulation scheme and size, based on fault patterns and QoS requirements. Each of these AI models can be tuned using network data, and then adapted for field use by a base station or a user device, for realtime beam parameter optimization.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a first network node may receive a signal. The first network node may transmit an angle of departure (AoD) report that indicates at least one predicted AoD associated with a dominant channel cluster, wherein the at least one predicted AoD is based at least in part on the signal. Numerous other aspects are described.