Beam management in communication networks

Abstract

A method, apparatus, and system for beam management in communications are disclosed, the method including: identifying optimal beam pairs based on one or more signals received from a base station; updating one or more learned models included in a UE based on the identified optimal beam pairs, the one or more learned models including at least one of one or more weights or one or more parameters; determining one or more beam directions for at least one of the UE or the base station based on the updated one or more learned models; and transmitting the updated one or more learned models, or at least one of the updated one or more weights, or the updated one or more parameters to the base station.

Description

[Technical Field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims the benefit of U.S. Provisional Application No. 63 / 482,084, filed January 30, 2023, entitled "BEAM MANAGEMENT IN COMMUNICATION NETWORK," which is incorporated herein by reference in its entirety.

[0002] Apparatus and methods consistent with the present disclosure relate generally to communications, and more particularly to methods, systems, and devices for beam management in communications. [Background technology]

[0003] Beam management is important in communications using radio signals, especially for high-frequency radio signals that experience high propagation loss. Beam management in the downlink / uplink involves beamforming between a user equipment (UE) and a base station, which typically involves beam sweeping in the UE and the base station. In conventional methods, beam sweeping is triggered only by the base station. This creates a problem in that triggering beam sweeping by the base station may not be responsive to the needs of the UE, thereby limiting the performance of beam management. A system and method that can enable the UE to trigger beam sweeping is desired. Another problem in beam management is the large overhead involved in beam management. The overhead may include the amount of reference signals transmitted between the UE and the base station, the number of beam sweeps performed in the UE and the base station, and the number of feedback signals provided after beam sweeping. The overhead in beam management can be reduced by utilizing artificial intelligence (AI) and machine learning (ML) (AI / ML) methods. Different configurations are possible for AI / ML methods. For example, each of the UE and the base station may have its own learning model for determining the beam direction, or the UE (or the base station) may have learning model(s) for both the UE and the base station. Cooperation between the UE and the base station in different deployments affects the overall performance of beam management. A system and method that can flexibly and efficiently perform beam management in different AI / ML configurations is desired. Summary of the Invention

[0004] According to some embodiments of the present disclosure, a UE for beam management in communication is provided, the UE comprising: a memory storing instructions; and a processor configured to execute the instructions stored in the memory to: send one or more requests to a base station for configuration of one or more resources used by the UE to transmit one or more requests to trigger beam sweeping; receive from the base station the configuration of one or more resources used by the UE to transmit the one or more requests to trigger beam sweeping; send to the base station the one or more requests to trigger beam sweeping on the one or more resources configured for the UE; receive from the base station a confirmation for the beam sweeping; and perform the beam sweeping based on the confirmation.

[0005] According to some embodiments of the present disclosure, a UE for beam management in communication is provided, the UE comprising: a memory storing instructions; and a processor, the processor executing the instructions stored in the memory to: send, to a base station through a random access procedure, one or more requests to trigger beam sweeping, where the one or more requests to trigger beam sweeping include at least one of one or more desired opportunities to perform beam sweeping or one or more configurations for performing beam sweeping; receive, from the base station, a confirmation of the beam sweeping; and perform the beam sweeping based on the confirmation. and

[0006] According to some embodiments of the present disclosure, a base station for beam management in communication is provided, the base station comprising: a memory storing instructions; and a processor configured to execute the instructions stored in the memory to: receive from a UE one or more requests for a configuration of one or more resources used by the UE to transmit one or more requests to trigger beam sweeping; send to the UE the configuration of one or more resources used by the UE to transmit the one or more requests to trigger beam sweeping; receive from the UE one or more requests to trigger beam sweeping; send to the UE a confirmation for the beam sweeping; and perform the beam sweeping based on the confirmation.

[0007] According to some embodiments of the present disclosure, a base station for beam management in communication is provided, the base station comprising: a memory storing instructions; and a processor configured to execute the instructions stored in the memory to: receive, from a UE through a random access procedure, one or more requests to trigger beam sweeping, where the one or more requests to trigger beam sweeping include at least one of one or more desired opportunities to perform beam sweeping or one or more configurations for performing beam sweeping; send a confirmation of the beam sweeping to the UE; and perform the beam sweeping based on the confirmation.

[0008] According to some embodiments of the present disclosure, a base station for beam management in communication is provided, the base station comprising: a memory storing instructions; and a processor configured to execute the instructions stored in the memory to: send one or more requests for one or more channel state information (CSI) reports to a UE, the one or more requests including configurations for one or more CSI measurements to be performed by the UE; receive one or more CSI reports from the UE; update one or more learned models included in the base station based on the received one or more CSI reports, the one or more learned models including at least one of one or more weights or one or more parameters; determine one or more beam directions for at least one of the base station or the UE based on the updated one or more learned models; and transmit the updated one or more learned models, the updated one or more weights, or the updated one or more parameters to the UE.

[0009] According to some embodiments of the present disclosure, a UE for beam management in communication is provided, the UE comprising: a memory that stores instructions; and a processor that is configured to execute the instructions stored in the memory to: receive one or more requests for one or more CSI reports from a base station, where the one or more requests include configurations for one or more CSI measurements to be performed by the UE; transmit the one or more CSI reports to the base station; receive from the base station an updated learned model for the UE, or at least one of updated one or more weights or updated one or more parameters of the learned model for the UE, where the learned model for the UE is included in the base station and updated by the base station based on the one or more CSI reports; and determine one or more beam directions for the UE based on the updated learned model for the UE, or at least one of the updated one or more weights or updated one or more parameters of the learned model for the UE.

[0010] According to some embodiments of the present disclosure, a UE for beam management in communication is provided, the UE comprising: a memory storing instructions; and a processor, the processor executing the instructions stored in the memory to receive from a base station one or more beams for one or more CSI reports. The base station is configured to: receive a request, where the one or more requests include configuration for one or more CSI measurements to be performed by the UE; transmit one or more CSI reports to the base station; receive from the base station one or more beam directions for the UE determined by a learning model included in the base station, where the learning model is a learning model for both the UE and the base station; and determine a beam to be used by the UE based on the received one or more beam directions.

[0011] According to some embodiments of the present disclosure, a UE for beam management in communication is provided, the UE comprising: a memory storing instructions; and a processor configured to execute the instructions stored in the memory to: identify optimal beam pairs based on one or more signals received from a base station; update one or more learning models included in the UE based on the identified optimal beam pairs, the one or more learning models including at least one of one or more weights or one or more parameters; determine one or more beam directions for at least one of the UE or the base station based on the updated one or more learning models; and transmit the updated one or more learning models, the updated one or more weights, or the updated one or more parameters to the base station.

[0012] According to some embodiments of the present disclosure, a base station for beam management in communication is provided, the base station comprising: a memory that stores instructions; and a processor that is configured to execute the instructions stored in the memory to: receive from a UE an updated learned model for the base station, or at least one of updated one or more weights or updated one or more parameters of the learned model for the base station, where the learned model for the base station is included in the UE and updated by the UE; and determine one or more beam directions for the base station based on the received updated learned model for the base station, or at least one of the updated one or more weights or updated one or more parameters of the learned model for the base station.

[0013] According to some embodiments of the present disclosure, a base station for beam management in communication is provided, the base station comprising: a memory for storing instructions; and a processor configured to execute the instructions stored in the memory to: receive, from a UE, one or more beam directions for the base station determined by a learned model included in the UE, where the learned model is a learned model for both the UE and the base station; and determine a beam for the base station based on the received one or more beam directions.

[0014] According to some embodiments of the present disclosure, a method for a UE for beam management in communication is provided, the method including: sending one or more requests to a base station for configuration of one or more resources used by the UE to transmit one or more requests to trigger beam sweeping, receiving from the base station the configuration of one or more resources used by the UE to transmit the one or more requests to trigger beam sweeping, sending to the base station the one or more requests to trigger beam sweeping on the one or more resources configured for the UE, receiving from the base station a confirmation for the beam sweeping, and performing the beam sweeping based on the confirmation.

[0015] According to some embodiments of the present disclosure, a method for a UE for beam management in communication is provided, the method including: sending, to a base station through a random access procedure, one or more requests for triggering beam sweeping, where the one or more requests for triggering beam sweeping include at least one of one or more desired opportunities for performing beam sweeping or one or more configurations for performing beam sweeping; receiving, from the base station, a confirmation of the beam sweeping; and performing the beam sweeping based on the confirmation. This includes:

[0016] According to some embodiments of the present disclosure, a method for a base station for beam management in communication is provided, the method including receiving, from a UE, one or more requests for a configuration of one or more resources used by the UE to transmit one or more requests to trigger beam sweeping, transmitting, to the UE, the configuration of one or more resources used by the UE to transmit the one or more requests to trigger beam sweeping, receiving, from the UE, the one or more requests to trigger beam sweeping, transmitting a confirmation for the beam sweeping to the UE, and performing the beam sweeping based on the confirmation.

[0017] According to some embodiments of the present disclosure, a method for a base station for beam management in communication is provided, the method including: receiving, from a UE through a random access procedure, one or more requests to trigger beam sweeping, where the one or more requests to trigger beam sweeping include at least one of one or more desired opportunities to perform beam sweeping or one or more configurations for performing beam sweeping; sending a confirmation for the beam sweeping to the UE; and performing the beam sweeping based on the confirmation.

[0018] According to some embodiments of the present disclosure, a method for a base station for beam management in communication is provided. The method includes: sending one or more requests for one or more CSI reports to a UE, where the one or more requests include configurations for one or more CSI measurements to be performed by the UE; receiving one or more CSI reports from the UE; updating one or more learned models included in the base station based on the received one or more CSI reports, where the one or more learned models include at least one of one or more weights or one or more parameters; determining one or more beam directions for at least one of the base station or the UE based on the updated one or more learned models; and transmitting the updated one or more learned models, the updated one or more weights, or the updated one or more parameters to the UE.

[0019] According to some embodiments of the present disclosure, a method for a UE for beam management in communication is provided. The method includes: receiving one or more requests for one or more CSI reports from a base station, where the one or more requests include configurations for one or more CSI measurements to be performed by the UE; transmitting the one or more CSI reports to the base station; receiving from the base station an updated learned model for the UE, or at least one of updated one or more weights or updated one or more parameters of the learned model for the UE, where the learned model for the UE is included in the base station and updated by the UE based on the one or more CSI reports; and determining one or more beam directions for the UE based on the updated learned model for the UE, or at least one of the updated one or more weights or updated one or more parameters of the learned model for the UE.

[0020] According to some embodiments of the present disclosure, a method for a UE for beam management in communication is provided, the method including: receiving one or more requests for one or more CSI reports from a base station, the one or more requests including configurations for one or more CSI measurements to be performed by the UE; transmitting the one or more CSI reports to the base station; receiving from the base station one or more beam directions for the UE determined by a learned model included in the base station, the learned model being a learned model for both the UE and the base station; and determining a beam direction to be used by the UE based on the received one or more beam directions. and determining a beam to be used.

[0021] According to some embodiments of the present disclosure, a method for a UE for beam management in communication is provided, the method including: identifying optimal beam pairs based on one or more signals received from a base station; updating one or more learning models included in the UE based on the identified optimal beam pairs, where the one or more learning models include at least one of one or more weights or one or more parameters; determining one or more beam directions for at least one of the UE or the base station based on the updated one or more learning models; and transmitting the updated one or more learning models, or at least one of the updated one or more weights, or the updated one or more parameters to the base station.

[0022] According to some embodiments of the present disclosure, a method for a base station for beam management in communication is provided, the method including: receiving, from a UE, at least one of an updated learned model for the base station, or one or more updated weights of the learned model for the base station, or one or more updated parameters, where the learned model for the base station is included in the UE and updated by the UE; and determining one or more beam directions for the base station based on the received updated learned model for the base station, or at least one of the updated weights of the learned model for the base station, or one or more updated parameters.

[0023] According to some embodiments of the present disclosure, a method for a base station for beam management in communications is provided, the method including receiving, from a UE, one or more beam directions for the base station determined by a learned model included in the UE, the learned model being a learned model for both the UE and the base station, and determining a beam for the base station based on the received one or more beam directions.

[0024] According to some embodiments of the present disclosure, a non-transitory computer-readable medium storing instructions executable by one or more processors of a UE for communication to perform a method is provided, the method including sending one or more requests to a base station for a configuration of one or more resources used by the UE to transmit the one or more requests to trigger beam sweeping, receiving from the base station the configuration of one or more resources used by the UE to transmit the one or more requests to trigger beam sweeping, sending to the base station the one or more requests to trigger beam sweeping on the one or more resources configured for the UE, receiving from the base station a confirmation for the beam sweeping, and performing the beam sweeping based on the confirmation.

[0025] According to some embodiments of the present disclosure, a non-transitory computer-readable medium storing instructions executable by one or more processors of a UE for communication to perform a method is provided, the method including: sending, to a base station through a random access procedure, one or more requests to trigger beam sweeping, where the one or more requests to trigger beam sweeping include at least one of one or more desired opportunities to perform beam sweeping or one or more configurations for performing beam sweeping; receiving, from the base station, a confirmation of the beam sweeping; and performing the beam sweeping based on the confirmation.

[0026] According to some embodiments of the present disclosure, a non-transitory computer-readable medium storing instructions executable by one or more processors of a base station for communication to perform a method is provided, the method including receiving from a UE one or more requests for a configuration of one or more resources used by the UE to transmit one or more requests to trigger beam sweeping. The method includes receiving a request, sending to the UE a configuration of one or more resources to be used by the UE to send one or more requests to trigger beam sweeping, receiving from the UE one or more requests to trigger beam sweeping, sending a confirmation for the beam sweeping to the UE, and performing the beam sweeping based on the confirmation.

[0027] According to some embodiments of the present disclosure, a non-transitory computer-readable medium storing instructions executable by one or more processors of a base station for communication to perform a method is provided, the method including receiving, from a user equipment (UE) through a random access procedure, one or more requests to trigger beam sweeping, where the one or more requests to trigger beam sweeping include at least one of one or more desired opportunities for performing beam sweeping or one or more configurations for performing beam sweeping, sending a confirmation for the beam sweeping to the UE, and performing the beam sweeping based on the confirmation.

[0028] According to some embodiments of the present disclosure, a non-transitory computer-readable medium storing instructions executable by one or more processors of a base station for communication to perform a method is provided. The method includes: sending one or more requests for one or more CSI reports to a UE, where the one or more requests include configurations for one or more CSI measurements to be performed by the UE; receiving one or more CSI reports from the UE; updating one or more learned models included in the base station based on the received one or more CSI reports, where the one or more learned models include at least one of one or more weights or one or more parameters; determining one or more beam directions for at least one of the base station or the UE based on the updated one or more learned models; and transmitting the updated one or more learned models, or the updated one or more weights, or the updated one or more parameters to the UE.

[0029] According to some embodiments of the present disclosure, a non-transitory computer-readable medium storing instructions executable by one or more processors of a UE for communication to perform a method is provided. The method includes: receiving one or more requests for one or more CSI reports from a base station, where the one or more requests include configurations for one or more CSI measurements to be performed by the UE; transmitting the one or more CSI reports to the base station; receiving from the base station an updated learned model for the UE, or at least one of updated one or more weights or updated one or more parameters of the learned model for the UE, where the learned model for the UE is included in the base station and updated by the UE based on the one or more CSI reports; and determining one or more beam directions for the UE based on the updated learned model for the UE, or at least one of the updated one or more weights or updated one or more parameters of the learned model for the UE.

[0030] According to some embodiments of the present disclosure, a non-transitory computer-readable medium storing instructions executable by one or more processors of a UE for communication to perform a method is provided, the method including: receiving one or more requests for one or more CSI reports from a base station, the one or more requests including configurations for one or more CSI measurements to be performed by the UE; transmitting the one or more CSI reports to the base station; receiving from the base station one or more beam directions for the UE determined by a learned model included in the base station, the learned model being a learned model for both the UE and the base station; and determining a beam to be used by the UE based on the received one or more beam directions.

[0031] According to some embodiments of the present disclosure, a non-transitory computer-readable medium storing instructions executable by one or more processors of a UE for communication to perform a method is provided, the method including: identifying optimal beam pairs based on one or more signals received from a base station; updating one or more learning models included in the UE based on the identified optimal beam pairs, the one or more learning models including at least one of one or more weights or one or more parameters; determining one or more beam directions for at least one of the UE or the base station based on the updated one or more learning models; and transmitting the updated one or more learning models, or at least one of the updated one or more weights, or the updated one or more parameters to the base station.

[0032] According to some embodiments of the present disclosure, a non-transitory computer-readable medium storing instructions executable by one or more processors of a base station for communication to perform a method is provided, the method including receiving, from a UE, at least one of an updated learned model for the base station, or one or more updated weights or one or more updated parameters of the learned model for the base station, where the learned model for the base station is included in the UE and updated by the UE, and determining one or more beam directions for the base station based on the received updated learned model for the base station, or at least one of the updated weights or one or more updated parameters of the learned model for the base station.

[0033] According to some embodiments of the present disclosure, a non-transitory computer-readable medium is provided that stores instructions executable by one or more processors of a base station for communication to perform a method, the method including receiving, from a UE, one or more beam directions for the base station determined by a learned model included in the UE, the learned model being a learned model for both the UE and the base station, and determining a beam for the base station based on the received one or more beam directions. [Brief explanation of the drawings]

[0034] [Figure 1] Figure 1A is a schematic diagram showing the existence of a line-of-sight signal path for an optimal beam pair in the downlink (DL), consistent with some embodiments of the present disclosure; Figure 1B is a schematic diagram showing the existence of a line-of-sight signal path for an optimal beam pair in the uplink (UL); Figure 1C is a schematic diagram showing the absence of a line-of-sight signal path in the downlink due to interference between the transmitter and receiver; and Figure 1D is a schematic diagram showing the absence of a line-of-sight signal path in the uplink due to interference between the transmitter and receiver. [Figure 2] FIG. 2 is a schematic diagram illustrating three phases of beam management consistent with certain embodiments of the present disclosure. [Figure 3A] FIG. 1 is a schematic diagram showing beam sweep procedure 1 (P1). [Figure 3B] FIG. 10 is a schematic diagram showing beam sweep procedure-2 (P2). [Figure 3C] FIG. 10 is a schematic diagram illustrating beam sweeping procedure-3 (P3), consistent with some embodiments of the present disclosure. [Figure 4] FIG. 1 is a schematic diagram illustrating a method for beam management based on downlink SSB or CSI-RS signals, consistent with certain embodiments of the present disclosure. [Figure 5] FIG. 1 is a schematic diagram illustrating a method for beam management based on uplink SRS signals, consistent with certain embodiments of the present disclosure. [Figure 6] FIG. 1 is a schematic diagram illustrating Scenario-1 of an AI / ML method without a labeled dataset, consistent with some embodiments of the present disclosure. [Figure 7] FIG. 1 is a schematic diagram illustrating a beam management method consistent with certain embodiments of the present disclosure. [Figure 8] FIG. 1 is a schematic diagram illustrating a method for beam management consistent with certain embodiments of the present disclosure. [Figure 9] FIG. 1 is a schematic diagram illustrating a beam management method consistent with certain embodiments of the present disclosure. [Figure 10] FIG. 1 is a schematic diagram illustrating a beam management method consistent with certain embodiments of the present disclosure. [Figure 11] FIG. 1 is a schematic diagram illustrating a beam management method consistent with certain embodiments of the present disclosure. [Figure 12] FIG. 1 is a schematic diagram illustrating a beam management method consistent with certain embodiments of the present disclosure. [Figure 13] 13 is a block diagram of a device 1300 consistent with certain embodiments of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0035] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. The following description refers to the accompanying drawings, in which like numbers in different drawings represent the same or similar elements unless otherwise stated. The implementations described in the following exemplary embodiments are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of systems, apparatus, and methods consistent with aspects related to the present disclosure, as set forth in the appended claims.

[0036] Beamforming is an important technology for coverage extension and throughput improvement, especially in millimeter wave frequency radio signals. Using beamforming, a transmitter can adjust its transmit (Tx) beam to point in a specific direction, while a receiver can also adjust its receive (Rx) beam direction to point in a specific direction and reject signals coming from other directions. The beam can be wide to cover a larger area or narrow to reach a farther area.

[0037] FIG. 1A is a schematic diagram illustrating the existence of a line-of-sight signal path for an optimal beam pair in the downlink (DL), FIG. 1B is a schematic diagram illustrating the existence of a line-of-sight signal path for an optimal beam pair in the uplink (UL), FIG. 1C is a schematic diagram illustrating the absence of a line-of-sight signal path in the downlink due to interference between a transmitter and a receiver, and FIG. 1D is a schematic diagram illustrating the absence of a line-of-sight signal path in the uplink due to interference between a transmitter and a receiver, consistent with some embodiments of the present disclosure. Referring to FIG. 1A, a communication system includes a base station 102 and a UE 104. The base station 102 may be any currently existing base station (e.g., a gNodeB (gNB)), such as a base station for Long Term Evolution (LTE) or New Radio (NR), or a base station for a future generation (sixth generation (6G), seventh generation (7G), or any other future generation) radio access technology (RAT). To obtain beam alignment between the transmitter (Tx) beam of the base station 102 and the receiver (Rx) beam of the UE 104, the base station 102 may transmit reference signals, such as Channel Station Information Reference Signals (CSI-RS) or synchronization signals and physical broadcast channels (SSB), using different sequences in different beam directions, for example, by performing Tx beam sweeping. Meanwhile, the UE 104 also positions its Rx beam across different beam directions, for example, by performing Rx beam sweeping. The base station 102 and the UE 104 finally find the optimal pair of Tx and Rx beams with the maximum received signal strength. In FIG. 1A, the black areas in the Tx and Rx beams indicate the optimal beam pair. In this case, there is a line-of-sight signal path for the optimal beam pair in the downlink.

[0038] 1B, the communication system includes a base station 106 and a UE 108. The base station 106 may be similar to the base station 102, and the UE 108 may be similar to the UE 104 in FIG. 1A. For brevity, descriptions of the base station 106 and the UE 108 are omitted here. Compared with FIG. 1A, in FIG. 1B, the UE 108 is a transmitter and transmits signals and / or data using a Tx beam, and the base station 106 is a receiver and receives signals and / or data from the UE 108 using an Rx beam. To obtain beam alignment between the Tx beam of the UE 108 and the Rx beam of the base station 106, the UE 108 may transmit a reference signal, such as a sounding reference signal (SRS), having different sequences in different beam directions, for example, by performing Tx beam sweeping. Meanwhile, the base station 106 also positions its Rx beam across different beam directions, for example, by performing Rx beam sweeping. The UE 108 and the base station 106 finally find an optimal pair of Tx beam and Rx beam with the maximum received signal strength. In Figure 1B, the black areas in the Tx and Rx beams indicate the optimal beam pair, where there is a line-of-sight signal path for the optimal beam pair in the uplink.

[0039] 1C, a communication system includes a base station 110 and a UE 112. Similar to FIG. 1A, in FIG. 1C, the base station 110 is a transmitter and the UE 112 is a receiver. To obtain beam alignment between the Tx beam of the base station 110 and the Rx beam of the UE 112, the base station 110 may transmit a reference signal, such as a channel state information reference signal (CSI-RS) or SSB, having different sequences in different beam directions. However, due to obstructions between the base station 110 and the UE 112, beam alignment is not achieved, and a line-of-sight signal path does not exist in the downlink, as indicated by the unaligned black portions in the Tx and Rx beams.

[0040] 1D, the communication system includes a base station 114 and a UE 116. Similar to FIG. 1B, in FIG. 1D, the UE 116 is a transmitter and the base station 114 is a receiver. To obtain beam alignment between the Tx beam of the UE 116 and the Rx beam of the base station 114, the UE 116 may transmit a reference signal, such as an SRS with different sequences in different beam directions. However, due to obstructions between the UE 116 and the base station 114, beam alignment is not achieved, and there is no line-of-sight signal path in the uplink, as indicated by the unaligned black portions in the Tx and Rx beams.

[0041] FIG. 2 is a schematic diagram illustrating three phases of beam management consistent with some embodiments of the present disclosure. Referring to FIG. 2, beam management may include three phases: (1) initial beam establishment, (2) beam adjustment, and (3) beam (link) recovery. These three phases involve six steps: a beam sweeping step, a beam measurement step, a beam reporting step, a beam determination step, a beam maintenance step, and a beam failure recovery step. The beam maintenance step may include a beam tracking and / or beam refinement process. The initial beam establishment phase may include a beam sweeping step, a beam measurement step, a beam reporting step, and a beam determination step. The beam adjustment phase may include a beam sweeping step, a beam measurement step, a beam reporting step, a beam determination step, and a beam maintenance step. The beam (link) recovery phase may include a beam sweeping step, a beam measurement step, a beam reporting step, a beam determination step, and a beam failure recovery step. The beam sweep may include three steps, namely, step-1, step-2, and step-3, as described below with respect to FIGS. 3A, 3B, 3C, 4, and 5.

[0042] FIG. 3A is a schematic diagram illustrating beam sweeping procedure-1 (P1), FIG. 3B is a schematic diagram illustrating beam sweeping procedure-2 (P2), and FIG. 3C is a schematic diagram illustrating beam sweeping procedure-3 (P3), consistent with some embodiments of the present disclosure. Procedure-1 is for downlink. 3A , the communication system includes a base station 302 and a UE 304. To obtain beam alignment between the Tx beam of the base station 302 and the Rx beam of the UE 304, the base station 302 may transmit reference signals, such as CSI-RS or SSB, with different sequences in different beam directions, for example, by performing Tx beam sweeping. The base station 302 may have N Tx beams, and the UE 304 may have M Rx beams, where N and M are natural numbers. Each of the N Tx beams is transmitted M times from the base station 302 so that the UE 304 can receive the Tx beam using M beams per Tx beam. Therefore, the base station 302 transmits a total of N×M CSI-RS or SSB signals. The UE 304 may measure the quality of the received CSI-RS or SSB signals, for example, the reference signal received power (RSRP) for all CSI-RS or SSB signals, and select the best beam. The UE 304 may further report the selected beam to the base station 302.

[0043] 3B, in step-2, the base station 302 transmits N beamforming CRI-RS signals to the UE 304. The UE 304 receives the set of N Tx beams transmitted from the base station 302 using the same Rx beam. This Rx beam may correspond to (e.g., be reciprocal to) the beam selected in step-1.

[0044] 3C, in Step-3, the UE 304 sweeps M Rx beams, and the base station 302 configures M beamforming CSI-RS transmissions using the same Tx beam for the UE 304 to sweep across the M Rx beams.

[0045] FIG. 4 is a schematic diagram illustrating a method for beam management based on downlink SSB or CSI-RS signals, consistent with some embodiments of the present disclosure. Referring to FIG. 4, the method 400 for beam management is initiated by a base station 402. The method 400 includes step 406 of transmitting SSB or CSI-RS signals for beam sweeping. For example, the base station 402 may transmit SSB or CSI-RS signals to a UE 404 using Tx beamforming. The SSB or CSI-RS signals may be swept and transmitted in different angular directions. The UE may use an Rx beam (e.g., a wide beam) to receive the SSB or CSI-RS signals. The method 400 includes step 408 of performing beam selection based on the beamforming SSB or CSI-RS. For example, the UE 404 may measure the quality of the received SSB or CSI-RS signals. The UE 404 may measure RSRP and / or signal-to-noise ratio (SNR) for the received signals and select the best beam. The best beam may have the highest RSRP and / or SNR value. In some embodiments, the UE may select two or more beams (e.g., the top four beams). Method 400 includes step 410 of reporting one or more identities (IDs) of the selected one or more beams. For example, based on beam measurements over the received SSB or CSI-RS, the UE 404 may report one or more IDs of the one or more selected beams to the base station 402. Method 400 includes step 412 of transmitting beamforming CSI-RS based on the selected one or more beams. For example, the base station 402 may focus only on beam directions having beam IDs reported by the UE for transmission (known as selected beams) and transmit beamforming CSI-RS based on the selected beams. Method 400 includes step 414 of performing CSI derivation. For example, the UE 404 may use Rx beams to receive the base station's improved downlink CSI-RS beam sweep and derive CSI on these selected beams. The UE 404 may estimate the channel condition of the downlink channel. The method 400 includes transmitting 416 the CSI as feedback to the base station.For example, after performing CSI derivation, the UE 404 may transmit the CSI to the base station 402 as feedback.

[0046] FIG. 5 is a schematic diagram illustrating a method for beam management based on an uplink SRS signal, consistent with some embodiments of the present disclosure. Referring to FIG. 5 , the method 500 for beam management is initiated by a UE 504 through transmitting an SRS signal for beam sweeping. The method 500 includes a step 506 of transmitting the SRS signal for beam sweeping. For example, the UE 504 may transmit the SRS signal to a base station 502 using Tx beamforming. The SRS signal may be swept and transmitted in different angular directions. The base station 502 may use an Rx beam (e.g., a wide beam) to receive the SRS signal. The method 500 includes a step 508 of performing beam selection based on the beamforming SRS. For example, the base station 502 may measure the quality of the received SRS signal. The base station 502 may measure the RSRP and / or SNR for the received SRS signal and select the best beam. The best beam may have the highest RSRP and / or SNR value. In some embodiments, the base station 502 may select two or more beams (e.g., the top four beams) and focus on the selected beam. The method 500 includes a step 510 of transmitting a beamformed CSI-RS based on the selected beam. For example, the base station 502 transmits the beamformed CSI-RS using the selected beam. The method 500 includes a step 512 of performing CSI derivation. For example, the UE 504 may use an Rx beam to receive the base station's CSI-RS beam sweep and derive CSI on these selected beams. For example, the UE 504 may estimate the channel condition of the downlink channel. The method 500 includes a step 514 of transmitting the CSI to the base station as feedback. For example, after performing CSI derivation, the UE 504 may transmit the CSI to the base station 502 as feedback. In method 400 of FIG. 4 and method 500 of FIG. 5, the periodicity of CSI reporting is configured by the base station (base station 402 or base station 502). Therefore, only the base station can initiate beam sweeping, for example, through radio resource control (RRC) signaling; the UE (UE 404 or UE 504) cannot initiate beam sweeping. This may limit the performance of beam management because there is no guarantee that the base station will always initiate beam sweeping whenever the UE needs to perform beam sweeping. At least some embodiments of the present disclosure provide a solution to this problem. For example, at least some embodiments of the present disclosure provide a method for beam management that allows the UE to initiate beam sweeping, as described below with respect to FIG. 7 and FIG. 8. Another problem with beam management is the large overhead involved in beam management. The overhead may include the amount of reference signals transmitted, the number of beam sweeps performed, and the provision of CSI feedback. At least some embodiments of the present disclosure provide a solution to this problem. For example, at least some embodiments of the present disclosure provide a beam management method in which AI / ML is utilized, thereby reducing overhead in beam management, as described below with respect to Figures 9-12.

[0047] In some embodiments, AI / ML methods involving labeled datasets are utilized in beam management. In these embodiments, there is a supervisor responsible for collecting and labeling the datasets. The labeled datasets are then provided and deployed to base stations and / or UEs.

[0048] In some embodiments, an AI / ML method without a labeled dataset is utilized for beam management. In these embodiments, the base station and / or UE collect data and train a model themselves. This disclosure describes the application of learning methods in beam management as an exemplary embodiment. However, the application of AI / ML methods is not so limited. For example, the concepts and procedures of the AI / ML method without a labeled dataset described herein can be applied to any other field. For the AI / ML method without a labeled dataset, there may be two design scenarios, namely, Scenario-1 and Scenario-2, as described below.

[0049] FIG. 6 is a schematic diagram illustrating Scenario-1 of an AI / ML method without a labeled dataset, consistent with some embodiments of the present disclosure. Referring to FIG. 6 , in Scenario-1, at least one learning agent is included in the base station 602 and at least one learning agent is included in the UE 604. In some embodiments, the base station 602 and the UE 604 make beam management decisions individually. In some embodiments, the learning agent in the base station 602 may be responsible for making decisions about and / or predicting beam directions at the base station 602. In some embodiments, the learning agent in the base station 602 may infer assistance information for beam management. The assistance information may include the location of the UE 604, the orientation of the UE 604, the velocity of the UE 604, the likelihood of beam obstruction, one or more beam angles, the likelihood of measurements for signals transmitted between the UE 604 and the base station 602, etc. In some embodiments, the learning agent in the UE 604 may be responsible for making decisions about and / or predicting beam directions at the UE 604. In some embodiments, the learning agent in the base station 602 may infer assistance information for beam management. The aiding information may include the location of the base station 602, the orientation of the base station 602, the velocity of the base station 602, the possibility of beam obstruction, one or more beam angles, the possibility of measurements on signals transmitted between the UE 604 and the base station 602, etc. The learning agent in the base station 602 and the learning agent in the UE 604 make decisions and / or predictions independently.

[0050] As shown in FIG. 6, the learning agent in the UE 604 and the learning agent in the base station 602 independently perform beam direction determination and / or prediction. To train and update the learning model, each learning agent should know the true optimal beam pair to further improve the beam direction determination and / or prediction. To achieve this, beam sweeping can be performed. However, as described above, in current beam management methods, only the base station has the ability to trigger beam sweeping. In this case, the learning agent in the base station 602 should be able to capture the true optimal beam pair. However, the UE 604 cannot trigger beam sweeping. The UE 604 can capture the optimal beam pair through beam sweeping triggered by the base station 602. For example, as shown in FIG. 6, the base station 602 can provide a CSI feedback configuration to the UE 604 so that the UE 604 can provide CSI feedback to the base station 602. The CSI feedback configuration provided to the UE 604 may include an explicit instruction for beam sweeping. Alternatively, a CSI feedback configuration transmitted from the base station 602 to the UE 604 can implicitly inform the UE 604 to perform beam sweeping. However, because the transmission of the CSI configuration is determined by the base station, beam sweeping may not always be triggered by the base station 602 whenever the UE 604 needs it. As a result, the performance of beam direct determination and / or prediction may be limited. At least some embodiments of the present disclosure provide methods for beam management that enable the UE to initiate beam sweeping, as described below with respect to Figures 7 and 8.

[0051] In Scenario-2, the base station 602 and the UE 604 jointly make beam management decisions. In this scenario, the base station 602 may perform joint decisions and / or predictions or model training for both the base station 602 and the UE 604. Alternatively, the UE 604 may perform joint decisions and / or predictions or model training for both the base station 602 and the UE 604. In this scenario, there may be issues regarding which (the base station or the UE) should perform joint beam management and how to perform joint beam management. At least some embodiments of the present disclosure address the above-mentioned issues in Scenario-2, as described with respect to Figures 9-12 below.

[0052] FIG. 7 is a schematic diagram illustrating a beam management method consistent with certain embodiments of the present disclosure. For reference, the method 700 includes a step 706 in which the UE 704 transmits a request for a resource configuration for transmitting a request to trigger a beam sweep. For example, the UE 704 transmits one or more requests to the base station 702 for a configuration of one or more resources to be used by the UE 704 for transmitting the one or more requests to trigger a beam sweep. In some embodiments, the UE 704 transmits the one or more requests for the configuration of one or more resources to be used by the UE 704 through a random access procedure.

[0053] The method 700 includes receiving 708 a configuration of resource(s) for the UE 704 to send a request to trigger a beam sweep. For example, after receiving one or more requests from the UE 704 for configuration of one or more resources to be used by the UE 704, the base station 702 configures one or more resources for the UE 704. The base station 702 further transmits the configuration to the UE 704 so that the UE 704 receives the configuration of the one or more resources and uses the one or more resources. In some embodiments, the base station 702 transmits the configuration of the one or more resources at least through Message 4 (Msg4) of a random access procedure. In some embodiments, the base station 702 transmits the configuration of the one or more resources via at least one of an RRC signal, a medium access control (MAC) control element (CE), or downlink control information (DCI). In some embodiments, the base station 702 may transmit the configuration of the one or more resources to be used by the UE 704 periodically, semi-periodically, or aperiodically. For example, in one embodiment, the base station 702 may transmit periodic or semi-periodic RRC signals to indicate periodicity or semi-periodicity, respectively. In this embodiment, the base station 702 may also transmit MAC CE or DCI to activate and / or deactivate resource configurations in the UE 704. In one embodiment, the base station 702 may transmit aperiodic MAC CE or DCI for one or more resource configurations. It may transmit a CE or a DCI.

[0054] The method 700 includes a step 710 of transmitting a request to trigger a beam sweep. For example, upon receiving a configuration of one or more resources from the base station 702, the UE 704 transmits one or more requests to the base station 702 to trigger a beam sweep on the one or more resources configured for the UE 704. In some embodiments, the one or more requests to trigger a beam sweep may include at least one of one or more desired opportunities to perform a beam sweep or one or more configurations for performing a beam sweep. In some embodiments, the UE 704 may transmit one or more requests to trigger a beam sweep through the beam pair identified during the random access procedure or other identified beam pairs.

[0055] The method 700 includes receiving 712 a confirmation for beam sweeping by the UE 704. For example, after receiving one or more requests to trigger beam sweeping sent from the UE 704, the base station 702 transmits a confirmation for beam sweeping, and the UE 704 receives the confirmation. In some embodiments, the confirmation may indicate (confirm) an opportunity and / or configuration for performing beam sweeping included in the one or more requests to trigger beam sweeping. In some embodiments, the confirmation for beam sweeping received from the base station 702 may include at least one of: (1) whether the base station 702 uses CSI-RS or SSB to perform the beam sweeping, (2) one or more sets of beam directions for the beam sweeping, or (3) one or more widths of one or more beams for the beam sweeping.

[0056] The method 700 includes a step 714 of performing beam sweeping. For example, after the UE 704 receives a confirmation for beam sweeping, the UE 704 may initiate beam sweeping, and both the base station 702 and the UE 704 may perform beam sweeping. Beam sweeping may be performed using SRS signals. The base station 702 can perform beam sweeping using CSI-RS or SSB signals. In this way, the UE 702 actively initiates beam sweeping.

[0057] 8 is a schematic diagram illustrating a method for beam management consistent with some embodiments of the present disclosure. Referring to FIG. 8, method 800 includes transmitting 806 a request to trigger beam sweeping through a random access procedure. For example, a UE 804 transmits one or more requests to trigger beam sweeping to a base station 802 through a random access procedure. In some embodiments, the one or more requests to trigger beam sweeping may include at least one of one or more desired opportunities to perform beam sweeping or one or more configurations for performing beam sweeping.

[0058] The method 800 includes receiving 808 a confirmation for beam sweeping. For example, after receiving one or more requests to trigger beam sweeping transmitted from the UE 804, the base station 802 transmits a confirmation for beam sweeping, and the UE 804 receives the confirmation. The confirmation may confirm the opportunity and / or configuration for performing beam sweeping included in the one or more requests to trigger beam sweeping. In some embodiments, the confirmation for beam sweeping transmitted from the base station 802 may include at least one of: (1) whether the base station 802 uses CSI-RS or SSB to perform beam sweeping, (2) one or more sets of beam directions for the beam sweeping, or (3) one or more widths of one or more beams for the beam sweeping.

[0059] The method 800 includes a step 810 of performing beam sweeping. For example, after the UE 804 receives confirmation for beam sweeping, the UE 804 may initiate beam sweeping, and both the base station 802 and the UE 804 can perform beam sweeping. The UE 804 may perform beam sweeping using at least SRS signals. The base station 802 can perform beam sweeping using CSI-RS or SSB signals. In this manner, the UE 802 actively initiates beam sweeping.

[0060] 9 is a schematic diagram illustrating a beam management method consistent with some embodiments of the present disclosure. Referring to FIG. 9, a base station 902 includes a learning model for a UE and a learning model for a base station. The learning model for the UE is for beam management for the UE 904, and the learning model for the base station is for beam management for the base station 902. The base station 902 is responsible for training both learning models. The beam management process performed by the UE 904 and the base station 902 may include two stages: an initial stage and a subsequent stage.

[0061] In the initial stage of beam management, the base station 902 and the UE 904 may adopt one or more training models based on an agreement. For example, in some embodiments, a specific number of structures for training models are provided as a standard. The base station 902 may support all or part of the structures in the standard and notify the UE 904 of the structures for the supported training models. For example, the base station 902 may notify the supported structures for the training models via a master information block (MIB) or a system information block (SIB). The UE 904 may also support all or part of the structures in the standard and notify the base station 902 of the structures for the supported training models. For example, the UE 902 may notify the supported structures for the training models as UE capability information transmitted via RRC signaling.

[0062] In an initial stage, in some embodiments, the base station 902 (or core network) may determine which structure for the training model should be adopted and may notify the UE 904 of the adopted structure for the training model. The UE 904 may determine which structure for the model should be adopted and may notify the base station 902 (or core network) of the adopted structure of the training model. If the UE 904 notifies the base station 902 of the adopted structure of the training model, the base station 902 may allocate radio resources for the UE 904 to transmit information regarding the adopted structure of the training model to the base station 902. In some embodiments, the UE 904 and the base station 902 may adopt one or more structures for training a model defined in a standard (e.g., a 3GPP standard).

[0063] In an initial stage, in some embodiments, the base station 902 (or core network) may determine adopted weights and / or parameters for the training model and notify the UE 904 of the adopted weights and / or parameters for the training model. In some embodiments, the UE 904 may determine adopted weights and / or parameters for the training model and notify the base station 902 (or core network) of the adopted weights and / or parameters for the training model. If the UE 904 notifies the base station 902 of the adopted weights and / or parameters for the training model, the base station 902 (or core network) may allocate radio resources for the UE 904 to transmit information regarding the adopted weights and / or parameters for the training model to the base station 902. In some embodiments, the UE 904 and the base station 902 may adopt the weights and / or parameters for the training model defined in a standard (e.g., a 3GPP standard).

[0064] In an initial stage, in some embodiments, the base station 902 and the UE 904 may employ one or more neural networks. In these embodiments, the structure of the learning model may be specified based on at least one of: a number of neural network layers, a number of neural nodes within each neural network layer, one or more connection structures (e.g., fully connected, etc.) between the neural network layers, one or more types of neural network layers (e.g., pooling layer, convolutional layer, etc.), one or more types of connections of the neural nodes (e.g., forward connections, convolutional connections, etc.), one or more types of computing operations (e.g., sigmoid functions) within each neural node, a number of weights of the one or more neural networks, a number of parameters of the one or more neural networks, one or more types of weights (e.g., real numbers, complex numbers, integers, floating-point numbers, etc.) of the one or more neural networks, one or more types of parameters (e.g., real numbers, complex numbers, integers, floating-point numbers, etc.) of the one or more neural networks, or one or more loss functions of the one or more neural networks. The one or more loss functions may be used to measure the difference and / or error of the one or more neural networks. In some embodiments, the base station 902 and the UE 904 may employ one or more deep neural networks.

[0065] In an initial stage, in some embodiments, the base station 902 and the UE 904 may employ one or more (deep) neural networks using generative advisory networks (GANs). In these embodiments, in addition to the structure of the learning model for the (deep) neural network described above, the structure of the learning model may also include at least one of a generator or a discriminator, and interconnections between the generator, the discriminator, and the neural network may also be specified.

[0066] In an initial stage, in some embodiments, the base station 902 and the UE 904 may employ one or more deep reinforcement learning (DRL) methods. In these embodiments, the structure of the learning model may be defined based on at least one of the state space of the DRL, the action space of the DRL, one or more reward functions of the DRL, the size of the replay memory and the contents (experience) in the replay memory, or the minimum batch size for sampling in the replay memory.

[0067] Referring to FIG. 9 , in a later step, the base station 902 has a learning model for the UE 904 and a learning model for the base station 902, and the UE 904 has only its own learning model. In step 906, the base station 902 requests or configures the UE 904 to provide one or more CSI reports. For example, the base station 902 may send one or more requests to the UE 904, and the one or more requests may include configurations for one or more CSI measurements to be performed by the UE 904. In step 908, the UE 904 performs CSI measurements and sends one or more CSI reports to the base station 902. Based on the received one or more CSI reports, the base station 902 can determine an optimal beam pair. For example, the base station 902 may trigger a beam sweep to identify the optimal beam pair. The optimal beam pair may be the beam pair with the highest measurement value in the CSI report. The base station 902 further estimates an error or difference between the optimal pair of directions and the one or more beam directions determined based on the learning model for the UE and / or the learning model for the base station. Based on the determined error or difference, in step 910, the base station 902 trains and updates weights and / or parameters of the learning model for the UE included in the base station 902. Similarly, in step 912, the base station 902 trains and updates weights and / or parameters of the learning model for the base station included in the base station 902. In step 914, the base station 902 estimates beam directions at the current time and / or future time based on the updated learning model for the base station and determines the beam directions of the base station 902. In step 916, the base station 902 transmits at least one of updated weights of the learning model for the UE, updated parameters of the learning model for the UE, or updated learning model for the UE to the UE 904. The base station 902 can configure one or more resources for transmitting the updated weights and / or parameters or the updated learning model for the UE to the UE 904. The base station 902 may further indicate the configured resources to the UE 904.The UE 904 may estimate a beam direction based on the updated weights and / or parameters or an updated learned model for the UE received from the base station 902. In step 918, the UE 904 further makes a decision regarding a beam direction for the UE 904 at the current time and / or future time.

[0068] In some embodiments, the base station 902 may periodically train and update the weights and / or parameters of the learned model for the UE and the weights and / or parameters of the learned model for the base station. In some embodiments, the base station 902 may train and update the weights and / or parameters of the learned model for the UE and the weights and / or parameters of the learned model for the base station when measurement results of one or more CSI reports received from the UE 904 are below a certain threshold.

[0069] 10 is a schematic diagram illustrating a beam management method consistent with some embodiments of the present disclosure. Referring to FIG. 10 , a base station 1002 includes a learning model for both the UE and the base station, and performs beam direction determination and / or prediction for both the UE 1004 and the base station 1002. In some embodiments, the learning model for both the UE and the base station may be two or more learning models. The UE 1004 does not have a learning model. The beam management method of FIG. 10 may include an initial stage and a subsequent stage. The operation of the base station 1002 and the UE 1004 in the initial stage is similar to the operation of the base station 902 and the UE 904 in FIG. 9. For brevity, a description of the operation of the base station 1002 and the UE 1004 in the initial stage is omitted here. The subsequent stages of beam management are described below with respect to FIG. 10.

[0070] 10, in step 1006, the base station 1002 requests or configures the UE 1004 to provide one or more CSI reports. For example, the base station 1002 may send one or more requests to the UE 1004, and the one or more requests may include configuration for one or more CSI measurements to be performed by the UE 1004. In step 1008, the U The E1004 performs CSI measurements and transmits one or more CSI reports to the base station 1002. Based on the received one or more CSI reports, the base station 1002 determines an optimal beam pair. For example, the base station 1002 may initiate beam sweeping to determine the optimal beam pair. The base station 1002 further estimates an error or difference between one or more beam directions determined based on the learning models for both the UE and the base station and the optimal pair direction. Based on the determined error or difference, in step 1010, the base station 1002 trains and updates weights and / or parameters of the learning models for both the UE and the base station. In step 1012, based on the updated learning models for both the UE and the base station, the base station 1002 estimates beam directions for both the base station 1002 and the UE 1004 and makes a decision on the beam directions for both the base station 1002 and the UE 1004. The beam directions for the base station 1002 and the beam directions for the UE 1004 may be beam directions at the current time and / or future time. In step 1014, the base station 1002 transmits the decision regarding the beam direction for the UE 1004 to the UE 1004. The base station 1002 may configure one or more resources for transmitting the decision regarding the beam direction to the UE 1004 and may further indicate the configured resources to the UE 1004. The UE 1004 adopts the decision regarding the beam direction transmitted from the base station 1002. Based on the decision regarding the beam direction received from the base station 1002, the UE 1004 may adjust its decision or make its own decision regarding its beam direction.

[0071] In some embodiments, the base station 1002 may periodically update its decision regarding the beam direction for both the base station 1002 and the UE 1004. In some embodiments, the base station 1002 may update its decision regarding the beam direction for both the base station 1002 and the UE 1004 when the measurement results of the CSI reports are below a certain threshold.

[0072] 11 is a schematic diagram illustrating a beam management method consistent with some embodiments of the present disclosure. As shown in FIG. 11, a UE 1104 has a learning model for the UE and a learning model for a base station, and the UE 1104 is responsible for training the learning models for the UE 1104 and the base station 1102. Meanwhile, the base station 1102 only has its own learning model. The beam management method of FIG. 11 may include an initial stage and a subsequent stage. The operations of the base station 1102 and the UE 1104 in the initial stage are similar to those of the base station 902 and the UE 904 in FIG. 9. For brevity, a description of the operations of the base station 1002 and the UE 1004 in the initial stage will be omitted here.

[0073] Referring to FIG. 11 , in step 1106, the UE 1104 may trigger a beam sweep. For example, the UE 1104 may initiate a beam sweep by sending a request to the base station 1102 to configure resources for the UE 1104, such as sending a request to trigger a beam sweep, as described with respect to FIG. 7 or FIG. 8 above. In some embodiments, the step of triggering a beam sweep by the UE 1104 is omitted. In step 1108, the UE 1104 may identify an optimal beam pair. In some embodiments, the UE 1104 may identify the optimal beam pair by performing the beam sweep triggered in step 1106. In some embodiments, the UE 1104 may identify the optimal beam pair through observing SSB and / or CSI-RS transmitted from the base station 1102 or through a beam sweep triggered by the base station 1102. The UE 1104 further estimates an error or difference between the optimal beam pair and one or more beam directions determined based on a learned model for the UE and / or a learned model for the base station. Based on the determined error or difference, in step 1112, the UE 1104 trains and updates weights and / or parameters of a learning model for the UE. Similarly, in step 1110, the UE 1104 trains and updates weights and / or parameters of a learning model for the base station included in the UE 1104. In step 1114, based on the updated learning model for the UE, The UE 1104 estimates a beam direction at the current time and / or a future time and makes a beam direction decision for the UE 1104. In step 1116, the UE 1104 transmits at least one of updated weights of the learned model for the base station, updated parameters of the learned model for the base station, or an updated learned model for the base station to the base station 1102. The base station 1102 may configure one or more resources for the UE 1104 to transmit the updated weights / parameters for the base station or the updated learned model. The base station 1102 may further indicate the configured resources to the UE 1104 so that the UE 1104 can use the resources for transmission. In step 1118, the base station 1102 estimates a beam direction for the current time and / or a future time using the updated weights / parameters or the updated learned model for the base station received from the UE 1104 and makes a decision on a beam direction for the base station 1102.

[0074] 12 is a schematic diagram illustrating a beam management method consistent with some embodiments of the present disclosure. As shown in FIG. 12, the UE 1204 includes learning models for both the UE and the base station and performs beam direction determination and / or prediction for both the UE 1204 and the base station 1202. The base station 1202 does not have a learning model. In some embodiments, the learning models for both the UE and the base station may be two or more learning models. The UE 1204 not only trains learning models for both the base station 1202 and the UE 1204, but also performs beam direction determination and / or prediction for both the base station 1202 and the UE 1204. The beam management method of FIG. 12 may include an initial stage and a subsequent stage. The operation of the base station 1202 and the UE 1204 in the initial stage is similar to the operation of the base station 902 and the UE 904 in FIG. 9. For brevity, a description of the operation of the base station 1202 and the UE 1204 will be omitted here.

[0075] 12, in step 1206, the UE 1204 may trigger a beam sweep. For example, the UE 1204 may initiate a beam sweep by sending a request to the base station 1202 to configure resources for the UE 1204, such as sending a request to trigger a beam sweep, as described with respect to FIG. 7 or FIG. 8 above. In some embodiments, the step of triggering a beam sweep by the UE 1204 is omitted. In step 1208, the UE 1204 may identify an optimal beam pair. In some embodiments, the UE 1204 may identify the optimal beam pair by performing the beam sweep triggered in step 1206. In some embodiments, the UE 1204 may identify the optimal beam pair through observing SSB and / or CSI-RS transmitted from the base station 1202 or through a beam sweep triggered by the base station 1202. The UE 1204 further estimates an error or difference between one or more beam directions determined based on the learned model for the UE and the direction of the optimal pair. Based on the determined error or difference, in step 1210, the UE 1204 trains and updates weights and / or parameters of learning models for both the UE and the base station. In step 1212, based on the updated learning models for both the UE and the base station, the UE 1204 determines beam directions for both the base station 1202 and the UE 1204 and makes a decision regarding the beam direction for both the base station 1202 and the UE 1204. The beam direction for the base station 1202 and the beam direction for the UE 1204 may be beam directions at the current time and / or future times. In step 1214, the UE 1204 transmits the decision regarding the beam direction for the base station 1202 to the base station 1202. The base station 1202 may configure one or more resources for transmitting the decision regarding the beam direction to the base station 1202 and indicate the configured resources to the UE 1204. The base station 1202 adopts the decision regarding the beam direction received from the UE 1204. Based on the decision regarding the beam direction received from the UE 1204, the base station 1202 may adjust its decision or make its own decision regarding its beam direction.

[0076] 13 is a block diagram of a device 1300 consistent with some embodiments of the present disclosure. In some embodiments, the device 1300 may be a UE. For example, the device 1300 may be the UE 704 of FIG. 7 or the UE 804 of FIG. 8 that triggers beam sweeping. In another example, the device 1300 may be the UE 904 of FIG. 9 or the UE 1004 of FIG. 10 that receives from a base station updated weights and / or parameters of a learned model for the UE determined by the base station, or a decision regarding a beam direction determined by the base station for the UE. In another example, the device 1300 may be the UE 1104 of FIG. 11 or the UE 1204 of FIG. 12 that includes one or more learned models for the UE and the base station and provides updated weights and / or parameters of the learned model, or a decision regarding a beam direction for the base station, to the base station. The UE may be mounted in a moving vehicle or at a fixed location. The UE may take any form, including, but not limited to, a vehicle, a component mounted on a vehicle, a roadside unit, a laptop computer, a wireless terminal including a mobile phone, a wireless handheld device, or a wireless personal device, or any other form. In some embodiments, the device 1300 may be a base station, such as base station 702 of Figure 7, base station 802 of Figure 8, base station 902 of Figure 9, base station 1002 of Figure 10, base station 1102 of Figure 11, or base station 1202 of Figure 12. In these embodiments, the device 1300 may take the form of a base station (or a component of a base station) or any network node.

[0077] 13, device 1300 may include an antenna 1302 that may be used for transmission or reception of electromagnetic signals to / from one or more other devices (e.g., a base station or a UE). Antenna 1302 may include one or more antenna elements and may enable different input / output antenna configurations, such as a multiple-input multiple-output (MIMO) configuration, a multiple-input single-output (MISO) configuration, and a single-input multiple-output (SIMO) configuration. In some embodiments, antenna 1302 may include multiple (e.g., tens or hundreds) antenna elements and may enable multi-antenna functionality such as beamforming. In some embodiments, antenna 1302 is a single antenna.

[0078] The device 1300 may include a transceiver 1304 coupled to an antenna 1302. The transceiver 1304 may be a wireless transceiver in the device 1300 and may communicate bidirectionally with another device (e.g., a base station or a UE). For example, in some embodiments, the device 1300 is a UE, and the transceiver 1304 may receive / transmit wireless signals to / from a base station via downlink / uplink communication. The transceiver 1304 may also receive / transmit wireless signals to / from another UE or a roadside unit via sidelink communication. The transceiver 1304 may include a modem for modulating packets, providing the modulated packets to the antenna 1302 for transmission, and demodulating packets received from the antenna 1302.

[0079] The device 1300 may include memory 1306. The memory 1306 may be any type of computer-readable storage medium, including volatile or non-volatile memory devices, or a combination thereof. The computer-readable storage medium includes, but is not limited to, non-transitory computer storage media. The non-transitory storage medium may be accessed by a general-purpose or special-purpose computer. Examples of non-transitory storage media may include, but are not limited to, portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable ROM (EEPROM), digital versatile disks (DVDs), flash memory, compact disk (CD) ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, etc. The non-transitory medium may be used to carry or store desired program code means (e.g., instructions and / or data structures) and may be accessed by a general-purpose or special-purpose computer or a general-purpose or special-purpose processor. In some examples, the software / program code may be It may be transmitted from a remote source (e.g., a website, a server, etc.) using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave. In such examples, coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are within the definition of media. Combinations of the above examples are also within the scope of computer-readable media.

[0080] The memory 1306 may store information related to the identification of the device 1300 and signals and / or data received by the antenna 1302. The memory may also store one or more learning models for AI / ML methods. In some embodiments, the memory 1306 includes learning models for both the UE and the base station. In some embodiments, the memory 1306 includes only learning models for the UE or only learning models for the base station. The memory 1306 may also store post-processed signals and / or data. The memory 1306 may also store computer-readable program instructions, mathematical models, and algorithms used in signal processing in the transceiver 1304 and calculations in the processor 1308 included in the device 1300. The memory 1306 may further store computer-readable program instructions for execution by the processor 1308 to operate the device 1300 to perform various functions described in this disclosure. In some examples, the memory 1306 may include a basic input / output system (BIOS) that may control basic hardware or software operations, such as interaction with peripheral components or devices. In some embodiments, the memory 1306 includes a learned model for the UE and a learned model for the base station.

[0081] The computer-readable program instructions of the present disclosure may be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​and conventional procedural programming languages. The computer-readable program instructions may be executed entirely on a computing device as a standalone software package, or may be executed partially on a first computing device and partially on a second computing device remote from the first computing device. In the latter scenario, the second, remote computing device may be connected to the first computing device via any type of network, including a local area network (LAN) or a wide area network (WAN).

[0082] The processor 1308 may include a hardware device having processing capabilities. The processor 1308 may include at least one of a general-purpose processor, a digital signal processor (DSP), a central processing unit (CPU), a microcontroller, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a programmable logic device, discrete gate or transistor logic components, discrete hardware components, or other programmable logic devices. Examples of general-purpose processors include, but are not limited to, a microprocessor, any conventional processor, controller, microcontroller, or state machine. In some embodiments, the processor 1308 may be implemented using a combination of devices (e.g., a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration). The processor 1308 can receive downlink / uplink signals or sidelink signals from the transceiver 1304 and further process the signals. The processor 1308 can also receive data packets from the transceiver 1304 and further process the packets. In some embodiments, the processor The processor 1308 may be configured to operate the memory using a memory controller. In some embodiments, the memory controller may be integrated into the processor 1308. The processor 1308 may be configured to execute computer-readable instructions stored in a memory (e.g., memory 1306) to cause the device 1300 to perform various functions, such as the methods illustrated in FIGS. 7-12.

[0083] The device 1300 may include a global positioning system (GPS) 1310. The GPS 1310 may be used to enable location-based services or other services based on the geographic position of the device 1300 and / or synchronization between UEs. The GPS 1310 may receive global navigation satellite system (GNSS) signals from a single satellite or multiple satellite signals via the antenna 1302 and provide the geographic position of the device 1300 (e.g., coordinates of the UE 1300). In some embodiments, the GPS 1310 is omitted. In some embodiments, a timer is included.

[0084] The device 1300 may include input / output (I / O) devices 1312 that can be used to communicate the results of signal processing and calculations to a user or another device. The I / O devices 1312 may include a user interface, including a display and input devices, for sending user commands to the processor 1308. The display may be configured to display the status of signal reception in the device 1300, data stored in the memory 1306, the status of signal processing, and the results of calculations. The display may include, but is not limited to, a cathode ray tube (CRT), a liquid crystal display (LCD), a light-emitting diode (LED), a gas plasma display, a touchscreen, or other image projection devices for displaying information to a user. The input devices may be any type of computer hardware equipment used to receive data and control signals from a user. The input devices may include, but are not limited to, a keyboard, a mouse, a scanner, a digital camera, a joystick, a trackball, cursor direction keys, a touchscreen monitor, an audio / video commander, or the like.

[0085] The device 1300 may further include a machine interface 1314 , such as an electrical bus, that connects the transceiver 1304 , the memory 1306 , the processor 1308 , the GPS 1310 , and the I / O device(s) 1312 .

[0086] In some embodiments, the device 1300 may be a UE that triggers beam sweeping in communication. The processor 1308 may be configured or programmed to execute instructions stored in the memory 1306 to send one or more requests to a base station for a configuration of one or more resources to be used by the UE to send the one or more requests to trigger beam sweeping, receive from the base station a configuration of one or more resources to be used by the UE to send the one or more requests to trigger beam sweeping, send to the base station one or more requests to trigger beam sweeping on the one or more resources configured for the UE, receive from the base station a confirmation for the beam sweeping, and perform the beam sweeping based on the confirmation.

[0087] In some embodiments, the device 1300 may be another UE in communication that triggers beam sweeping. The processor 1308 may be configured or programmed to execute instructions stored in the memory 1306 to: send, to a base station through a random access procedure, one or more requests to trigger beam sweeping, where the one or more requests to trigger beam sweeping include at least one of one or more desired opportunities to perform beam sweeping or one or more configurations for performing beam sweeping; receive confirmation of the beam sweeping from the base station; and perform the beam sweeping based on the confirmation.

[0088] In some embodiments, the device 1300 may be a base station for beam management in communications. The processor 1308 may be configured or programmed to execute instructions stored in the memory 1306 to: receive from a UE one or more requests for a configuration of one or more resources to be used by the UE to send one or more requests to trigger beam sweeping, send to the UE the configuration of one or more resources to be used by the UE to send the one or more requests to trigger beam sweeping, receive from the UE one or more requests to trigger beam sweeping, send to the UE a confirmation for the beam sweeping, and perform the beam sweeping based on the confirmation.

[0089] In some embodiments, the device 1300 may be another base station for beam management in communication. The processor 1308 may be configured or programmed to execute instructions stored in the memory 1306 to: receive, from a UE through a random access procedure, one or more requests to trigger a beam sweep, where the one or more requests to trigger a beam sweep include at least one of one or more desired opportunities to perform the beam sweep or one or more configurations for performing the beam sweep; send a confirmation of the beam sweep to the UE; and perform the beam sweep based on the confirmation.

[0090] In some embodiments, the device 1300 may be another base station for beam management in communication. The processor 1308 may be configured or programmed to execute instructions stored in the memory 1306 to: send one or more requests for one or more CSI reports to a UE, where the one or more requests include configurations for one or more CSI measurements to be performed by the UE; receive one or more CSI reports from the UE; update one or more learned models included in the base station based on the received one or more CSI reports, where the one or more learned models include at least one of one or more weights or one or more parameters; determine one or more beam directions for at least one of the base station or the UE based on the updated one or more learned models; and transmit the updated one or more learned models, the updated one or more weights, or the updated one or more parameters to the UE.

[0091] In some embodiments, the device 1300 may be another UE for beam management in communication. The processor 1308 may be configured or programmed to execute instructions stored in the memory 1306 to: receive one or more requests for one or more CSI reports from a base station, where the one or more requests include configuration for one or more CSI measurements to be performed by the UE; transmit the one or more CSI reports to the base station; receive from the base station an updated learned model for the UE, or at least one of updated one or more weights or updated one or more parameters of the learned model for the UE, where the learned model for the UE is included in the base station and updated by the UE based on the one or more CSI reports; and determine one or more beam directions for the UE based on the updated learned model for the UE, or at least one of the updated one or more weights or updated one or more parameters of the learned model for the UE.

[0092] In some embodiments, the device 1300 may be another UE for beam management in communication. The processor 1308 executes instructions stored in the memory 1306 to receive one or more requests for one or more CSI reports from a base station, the one or more requests including configuration for one or more CSI measurements to be performed by the UE. the base station; receiving from the base station one or more beam directions for the UE determined by a learning model included in the base station, the learning model being a learning model for both the UE and the base station; and determining a beam to be used by the UE based on the received one or more beam directions.

[0093] In some embodiments, the device 1300 may be another UE for beam management in communication. The processor 1308 may be configured or programmed to execute instructions stored in the memory 1306 to: identify optimal beam pairs based on one or more signals received from a base station; update one or more learning models included in the UE based on the identified optimal beam pairs, where the one or more learning models include at least one of one or more weights or one or more parameters; determine one or more beam directions for at least one of the UE or the base station based on the updated one or more learning models; and transmit the updated one or more learning models, or the updated one or more weights, or the updated one or more parameters to the base station.

[0094] In some embodiments, the device 1300 may be another base station for beam management in communication. The processor 1308 may be configured or programmed to execute instructions stored in the memory 1306 to: receive from the UE an updated learned model for the base station, or one or more updated weights or one or more updated parameters of the learned model for the base station, where the learned model for the base station is included in and updated by the UE; and determine one or more beam directions for the base station based on the received updated learned model for the base station, or at least one of the updated weights or one or more updated parameters of the learned model for the base station.

[0095] In some embodiments, device 1300 may be another base station for beam management in communication. Processor 1308 may be configured or programmed to execute instructions stored in memory 1306 to: receive, from the UE, one or more beam directions for the base station determined by a learned model included in the UE, where the learned model is a learned model for both the UE and the base station; and determine a beam for the base station based on the received one or more beam directions.

[0096] As used in this disclosure, the use of the word "or" in a list of items indicates an inclusive list. The list of items may be prefaced by a phrase such as "at least one of" or "one or more of." For example, a list of at least one of A, B, or C includes A or B or C or AB (i.e., A and B) or AC or BC or ABC (i.e., A and B and C). Also, as used in this disclosure, prefacing a list of conditions with the phrase "based on" should not be construed as "based only on" the set of conditions, but rather as "based at least in part on" the set of conditions. For example, a result described as "based on condition A" could be based on both condition A and condition B without departing from the scope of this disclosure.

[0097] As used herein, the terms "comprise," "include," or "contain" can be used interchangeably, have the same meaning, and should be construed as being inclusive and open-ended. The terms "comprise," "include," or "contain" may be used before a list of elements to indicate that at least all of the recited elements in the list are present, but that other elements not in the list may also be present. For example, A contains B and C. Then both {B,C} and {B,C,D} are within the range of A.

[0098] The present disclosure describes exemplary configurations in connection with the accompanying drawings, which do not represent all examples that may be implemented or all configurations within the scope of the present disclosure. The term "exemplary" should not be interpreted as "preferred" or "advantageous over other examples," but rather as "an example, instance, or example." By reading this disclosure, including the description of the embodiments and drawings, those skilled in the art will understand that the technology disclosed herein may be implemented using alternative embodiments. Those skilled in the art will understand that the embodiments described herein, or specific features of the embodiments, may be combined to arrive at yet other embodiments for implementing the technology described in this disclosure. Thus, the present disclosure is not limited to the examples and designs described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0099] The flowcharts and block diagrams in the figures illustrate example architecture, functionality, and operation of possible implementations of systems, methods, and devices according to various embodiments. It should be noted that in some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending on the functionality involved. Likewise, additional steps may be included in methods consistent with various embodiments, and certain steps may be omitted or combined.

[0100] It is to be understood that the described embodiments are not mutually exclusive, and that elements, components, materials, or steps described in connection with one exemplary embodiment may be combined with or excluded from other embodiments in any suitable manner to achieve desired design objectives. References herein to "some embodiments" or "some exemplary embodiments" mean that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment. The appearances of the phrases "one embodiment," "some embodiments," or "another embodiment" in various places in this disclosure do not necessarily all refer to the same embodiments, and separate or alternative embodiments are not necessarily mutually exclusive of other embodiments.

[0101] Furthermore, the articles "a" and "an," as used in this disclosure and the appended claims, should generally be construed to mean "one or more," unless otherwise specified or unless it is clear from the context that the singular form is intended.

[0102] Unless expressly stated otherwise, each numerical value and range should be construed as approximate, as if the word "about" or "approximately" preceded the value or range value.

[0103] Although elements in the following method claims, if any, are recited in a particular order, those elements are not necessarily intended to be limited to being implemented in that particular order, unless the recitation of a claim otherwise implies a particular order for implementing some or all of those elements.

[0104] It should be understood that certain features of the present disclosure that are, for clarity, described in the context of separate embodiments, may also be provided in combination in a single embodiment. Conversely, various features herein that are, for brevity, described in the context of a single embodiment, may also be provided separately or in any suitable subcombination, or as appropriate, in any other described embodiment herein. Certain features described in the context of various embodiments are not essential features of those embodiments, unless so described.

[0105] It will be further understood that various modifications, substitutions, and variations in the details, materials, and arrangements of parts described and illustrated to illustrate the nature of the described embodiments may be made by those skilled in the art without departing from the scope thereof, and therefore the following claims will encompass all such substitutions, modifications, and variations that fall within the terms of the claims.

[0106] Clause 1: A user equipment (UE) for beam management in communication, the UE comprising: a memory for storing instructions; a processor, the processor executing the instructions stored in the memory to sending one or more requests to a base station for configuration of one or more resources used by the UE to send one or more requests to trigger beam sweeping; receiving, from the base station, the configuration of the one or more resources to be used by the UE to transmit the one or more requests to trigger the beam sweeping; sending, to the base station, the one or more requests to trigger the beam sweeping on the one or more resources configured for the UE; receiving a confirmation of the beam sweep from the base station; and performing the beam sweeping based on the confirmation.

[0107] Clause 2: The processor executes the instructions stored in the memory, 11. The UE of claim 1, configured to transmit to the base station, through a random access procedure, the one or more requests for the configuration of the one or more resources to be used by the UE.

[0108] Clause 3: The processor executes the instructions stored in the memory, 3. The UE of clause 2, configured to receive, from the base station, the configuration of the one or more resources to be used by the UE through at least message 4 (Msg4) of the random access procedure.

[0109] Clause 4: The processor executes the instructions stored in the memory, The UE of clause 1, configured to receive the configuration of the one or more resources used by the UE from the base station via at least one of a radio resource control (RRC) signal, a medium access control (MAC) control element (CE), or downlink control information (DCI).

[0110] Clause 5: The UE described in Clause 1, wherein the one or more requests to trigger the beam sweeping include at least one of one or more desired opportunities for performing the beam sweeping or one or more configurations for performing the beam sweeping.

[0111] Clause 6: The UE of Clause 1, wherein the confirmation regarding the beam sweeping received from the base station includes at least one of (1) whether a channel state information reference signal (CSI-RS) or a synchronization signal and a physical broadcast channel (SSB) should be used to perform the beam sweeping, (2) one or more sets of beam directions for the beam sweeping, or (3) one or more widths of one or more beams for the beam sweeping.

[0112] Clause 7: The processor executes the instructions stored in the memory, At least a sounding reference signal (SRS) is used to perform the beam sweep. 1. The UE of claim 1, configured to:

[0113] Clause 8: A user equipment (UE) for beam management in communication, the UE comprising: a memory for storing instructions; a processor, the processor executing the instructions stored in the memory to sending, to a base station through a random access procedure, one or more requests for triggering beam sweeping, wherein the one or more requests for triggering beam sweeping include at least one of one or more desired opportunities for performing the beam sweeping or one or more configurations for performing the beam sweeping; receiving a confirmation of the beam sweep from the base station; and performing the beam sweeping based on the confirmation.

[0114] Clause 9: A base station for beam management in communication, the base station comprising: a memory for storing instructions; a processor, the processor executing the instructions stored in the memory to receiving, from a user equipment (UE), one or more requests for configuration of one or more resources used by the UE to transmit one or more requests to trigger beam sweeping; transmitting to the UE the configuration of the one or more resources to be used by the UE to transmit the one or more requests to trigger the beam sweeping; receiving the one or more requests to trigger the beam sweeping from the UE; sending a confirmation of the beam sweep to the UE; and performing the beam sweeping based on the confirmation.

[0115] Clause 10: The processor executes the instructions stored in the memory, 10. The base station of clause 9, configured to receive from the UE, at least through a random access procedure, the one or more requests for the configuration of the one or more resources to be used by the UE.

[0116] Clause 11: The processor executes the instructions stored in the memory, The base station of clause 10, configured to transmit the configuration of the one or more resources to be used by the UE to the UE through at least message 4 (Msg4) of the random access procedure.

[0117] Clause 12: The processor executes the instructions stored in the memory, The base station of clause 9 is configured to transmit the configuration of the one or more resources to be used by the UE via at least one of a Radio Resource Control (RRC) signal, a Medium Access Control (MAC) control element (CE), or a Downlink Control Information (DCI) to the UE.

[0118] Clause 13: The processor executes the instructions stored in the memory, 10. The base station of clause 9, configured to perform the configuration of the one or more resources used by the UE periodically, semi-periodically, or aperiodically.

[0119] Clause 14: The processor executes the instructions stored in the memory, The base station of clause 9, configured to receive from the UE the one or more requests to trigger the beam sweeping on the configured one or more resources.

[0120] Clause 15: The base station described in Clause 9, wherein the one or more requests to trigger the beam sweeping received from the UE include at least one of one or more desired opportunities for performing the beam sweeping or one or more configurations for performing the beam sweeping.

[0121] Clause 16: The base station of Clause 9, wherein the confirmation for the beam sweeping transmitted to the UE includes at least one of (1) whether to use a Channel State Information Reference Signal (CSI-RS) or a synchronization signal and a Physical Broadcast Channel (SSB) to perform the beam sweeping, (2) one or more sets of beam directions for the beam sweeping, or (3) one or more widths of one or more beams for the beam sweeping.

[0122] Clause 17: A base station for beam management in communications, said base station comprising: a memory for storing instructions; a processor, the processor executing the instructions stored in the memory to receiving, from a user equipment (UE) through a random access procedure, one or more requests for triggering beam sweeping, wherein the one or more requests for triggering beam sweeping include at least one of one or more desired opportunities for performing the beam sweeping or one or more configurations for performing the beam sweeping; sending a confirmation of the beam sweep to the UE; and performing the beam sweeping based on the confirmation.

[0123] Clause 18: A base station for beam management in communications, said base station comprising: a memory for storing instructions; a processor, the processor executing the instructions stored in the memory to sending one or more requests for one or more channel state information (CSI) reports to a user equipment (UE), the one or more requests including configurations for one or more CSI measurements to be performed by the UE; receiving the one or more CSI reports from the UE; updating one or more learned models included in the base station based on the received one or more CSI reports, the one or more learned models including at least one of one or more weights or one or more parameters; determining one or more beam directions for at least one of the base station or the UE based on the updated one or more learned models; and transmitting at least one of the updated one or more learned models, or the updated one or more weights, or the updated one or more parameters to the UE.

[0124] Clause 19: The one or more learning models a training model for the base station and a training model for the UE; or 19. The base station of clause 18, including at least one of a learning model for both the base station and the UE.

[0125] Clause 20: The one or more learning models include a learning model for the base station and a learning model for the UE, and the processor executes the instructions stored in the memory. do, 19. The base station of clause 18, configured to update the learning model for the base station and the learning model for the UE based on the received one or more CSI reports.

[0126] Clause 21: The base station described in Clause 20, wherein the processor is configured to execute the instructions stored in the memory to determine the one or more beam directions for the base station.

[0127] Clause 22: The base station described in Clause 20, wherein the processor is configured to execute the instructions stored in the memory to transmit at least one of an updated learning model for the UE, or updated one or more weights of the learning model for the UE, or updated one or more parameters to the UE.

[0128] Clause 23: The one or more learning models include learning models for both the base station and the UE, and the processor executes the instructions stored in the memory to: 19. The base station of clause 18, configured to update the learned models for both the base station and the UE based on the received one or more CSI reports.

[0129] Clause 24: The base station described in Clause 23, wherein the processor is configured to execute the instructions stored in the memory to determine the one or more beam directions for both the base station and the UE.

[0130] Clause 25: The base station described in Clause 24, wherein the processor is configured to execute the instructions stored in the memory to transmit to the UE at least one of one or more beam directions for the UE at a current time or one or more beam directions for the UE at a future time.

[0131] Clause 26: The processor executes the instructions stored in the memory, configuring one or more resources for transmitting at least one of the updated one or more learned models, the updated one or more weights, or the updated one or more parameters; 19. The base station of clause 18, further configured to: notify the UE of the configured one or more resources.

[0132] Clause 27: The processor executes the instructions stored in the memory, 19. The base station of clause 18, further configured to notify the UE via a Master Information Block (MIB) or a System Information Block (SIB) of one or more supported structures for the one or more learning models.

[0133] Clause 28: The processor executes the instructions stored in the memory, The base station of clause 18, further configured to receive from the UE one or more supported structures for the one or more learning models, the one or more supported structures being included in UE capability information transmitted via RRC signaling.

[0134] Clause 29: One or more neural networks are employed by the base station, and the structure of the one or more learning models is: the number of neural network layers, the number of neural nodes in each neural network layer, one or more connectivity structures between the neural network layers; one or more types of neural network layers; one or more types of connections of said neural nodes; one or more types of computing operations at each neural node; the number of weights of said one or more neural networks; the number of parameters of said one or more neural networks; one or more types of weights of said one or more neural networks; one or more types of parameters of said one or more neural networks; or 19. The base station of clause 18, wherein the one or more neural networks are identified based on at least one of: one or more loss functions of the one or more neural networks.

[0135] Clause 30: One or more deep reinforcement learning (DRL) methods are employed by the base station, and the structure of the one or more learning models is: the state space of the DRL, the DRL action space, one or more reward functions of said DRL; The size of the replay memory and the contents of the replay memory, or a minimum batch size for sampling in the replay memory.

[0136] Clause 31: The processor executes the instructions stored in the memory, 19. The base station of clause 18, further configured to update the one or more learning models included in the base station in response to determining that one or more measurement values ​​in the one or more CSI reports received from the UE are lower than a predetermined threshold.

[0137] Clause 32: A user equipment (UE) for beam management in communication, the UE comprising: a memory for storing instructions; a processor, the processor executing the instructions stored in the memory to receiving one or more requests for one or more channel state information (CSI) reports from a base station, the one or more requests including configurations for one or more CSI measurements to be performed by the UE; transmitting the one or more CSI reports to the base station; receiving, from the base station, an updated learned model for the UE, or at least one of updated one or more weights or updated one or more parameters of the learned model for the UE, wherein the learned model for the UE is included in the base station and is updated by the base station based on the one or more CSI reports; determining one or more beam directions for the UE based on the updated learning model for the UE, or the at least one of the updated one or more weights or the updated one or more parameters of the learning model for the UE.

[0138] Clause 33: The UE described in Clause 32, wherein the one or more beam directions for the UE include at least one of the one or more beam directions for the UE at a current time or the one or more beam directions for the UE at a future time.

[0139] Clause 34: The processor executes the instructions stored in the memory, and one or more resources configured for transmission of the updated training model for the UE from the base station, or the updated one or more resources of the training model for the UE. 33. The UE of clause 32, further configured to receive the at least one of the above weights or the updated one or more parameters.

[0140] Clause 35: The processor executes the instructions stored in the memory, 33. The UE of clause 32, further configured to receive, from the base station, one or more supported structures for a learning model for the base station via a Master Information Block (MIB) or a System Information Block (SIB).

[0141] Clause 36: The processor executes the instructions stored in the memory, The UE of clause 32, further configured to transmit to the base station one or more supported structures for the learning model for the UE via at least one of a radio resource control (RRC) signal, a medium access control (MAC) control element (CE), or downlink control information (DCI).

[0142] Clause 37: A user equipment (UE) for beam management in communication, the UE comprising: a memory for storing instructions; a processor, the processor executing the instructions stored in the memory to receiving one or more requests for one or more channel state information (CSI) reports from a base station, the one or more requests including configurations for one or more CSI measurements to be performed by the UE; transmitting the one or more CSI reports to the base station; receiving from the base station one or more beam directions for the UE determined by a learned model included in the base station, the learned model being a learned model for both the UE and the base station; and determining a beam to be used by the UE based on the received one or more beam directions.

[0143] Clause 38: The UE described in Clause 37, wherein the one or more beam directions for the UE include at least one of the one or more beam directions for the UE at a current time or the one or more beam directions for the UE at a future time.

[0144] Clause 39: A user equipment (UE) for beam management in communication, the UE comprising: a memory for storing instructions; a processor, the processor executing the instructions stored in the memory to identifying an optimal beam pair based on one or more signals received from a base station; updating one or more learning models included in the UE based on the identified optimal beam pair, the one or more learning models including at least one of one or more weights or one or more parameters; determining one or more beam directions for at least one of the UE or the base station based on the updated one or more learned models; and transmitting at least one of the updated one or more learned models, or the updated one or more weights, or the updated one or more parameters to the base station.

[0145] Clause 40: The processor executes the instructions stored in the memory, Used by the UE to send one or more requests to trigger beam sweeping. transmitting one or more requests to the base station for configuration of one or more resources to be used; receiving the configuration of the one or more resources from the base station; 40. The UE of clause 39, further configured to: send the one or more requests to the base station for triggering the beam sweeping based on the received configuration of the one or more resources.

[0146] Clause 41: The processor executes the instructions stored in the memory. identifying the optimal beam pair based on one or more measurements of at least one of a Channel State Information Reference Signal (CSI-RS) or synchronization signal and a Physical Broadcast Channel (SSB) received from the base station; or The UE of clause 39, further configured to identify the optimal beam pair via beam sweeping triggered by the base station.

[0147] Clause 42: The one or more learning models a trained model for the UE and a trained model for the base station; or The UE of clause 39, including at least one of a learning model for both the UE and the base station.

[0148] Clause 43: The processor executes the instructions stored in the memory, sending, to the base station, one or more requests for configuration of one or more resources to be used by the UE for transmission of at least one of the updated one or more learned models, or the updated one or more weights, or the updated one or more parameters; receiving, from the base station, the configuration of the one or more resources to be used by the UE; The UE of Clause 39, further configured to: transmit at least one of the updated one or more learning models, or the updated one or more weights, or the updated one or more parameters to the base station based on the configuration of the one or more resources.

[0149] Clause 44: The one or more learning models include a learning model for the base station and a learning model for the UE, and the processor executes the instructions stored in the memory to: The UE of clause 39, further configured to update the learning model for the UE and the learning model for the base station based on the identified optimal beam pair.

[0150] Clause 45: The UE described in Clause 44, wherein the processor is configured to execute the instructions stored in the memory to determine the one or more beam directions for the UE.

[0151] Clause 46: The UE described in Clause 44, wherein the processor is configured to execute the instructions stored in the memory to send to the base station at least one of an updated learning model for the base station, or updated one or more weights of the learning model for the base station, or updated one or more parameters.

[0152] Clause 47: The one or more learning models include learning models for both the UE and the base station, and the processor executes the instructions stored in the memory to: Based on the identified optimal beam pair, 39. The UE of claim 39, further configured to update the learning model.

[0153] Clause 48: The UE described in Clause 47, wherein the processor is configured to execute the instructions stored in the memory to determine the one or more beam directions for both the UE and the base station.

[0154] Clause 49: The UE described in Clause 48, wherein the processor is configured to execute the instructions stored in the memory to transmit to the base station at least one of the one or more beam directions for the base station at the current time or one or more beam directions for the base station at a future time.

[0155] Clause 50: One or more neural networks are employed by the UE, and the structure of the one or more learning models is the number of neural network layers, the number of neural nodes in each neural network layer, one or more connectivity structures between the neural network layers; one or more types of neural network layers; one or more types of connections of said neural nodes; one or more types of computing operations at each neural node; the number of weights of said one or more neural networks; the number of parameters of said one or more neural networks; one or more types of weights of said one or more neural networks; one or more types of parameters of said one or more neural networks; or 39. The UE of claim 39, wherein the UE is identified based on at least one of: one or more loss functions of the one or more neural networks.

[0156] Clause 51: One or more deep reinforcement learning (DRL) methods are employed by the base station, and the structure of the one or more learning models is the state space of the DRL, the DRL action space, one or more reward functions of said DRL; The size of the replay memory and the contents of the replay memory, or a minimum batch size for sampling in the replay memory.

[0157] Clause 52: A base station for beam management in communications, said base station comprising: a memory for storing instructions; a processor, the processor executing the instructions stored in the memory to receiving, from a user equipment (UE), an updated learned model for the base station, or at least one of updated one or more weights or updated one or more parameters of the learned model for the base station, wherein the learned model for the base station is included in and updated by the UE; determining one or more beam directions for the base station based on at least one of the received updated learning model for the base station, or the updated one or more weights of the learning model for the base station, or the updated one or more parameters.

[0158] Clause 53: The one or more beam directions for the base station are the one or more beam directions for the base station at a current time or the one or more beam directions for the base station at a future time. 53. The base station of clause 52, including at least one of the one or more beam directions.

[0159] Clause 54: A base station for beam management in communications, said base station comprising: a memory for storing instructions; a processor, the processor executing the instructions stored in the memory to receiving, from a user equipment (UE), one or more beam directions for the base station determined by a learned model included in the UE, the learned model being a learned model for both the UE and the base station; and determining a beam for the base station based on the received one or more beam directions.

[0160] Clause 55: The base station described in Clause 54, wherein the one or more beam directions for the base station include at least one of the one or more beam directions for the base station at a current time or the one or more beam directions for the base station at a future time.

[0161] Clause 56: A method for a user equipment (UE) for beam management in communication, the method comprising: sending one or more requests to a base station for configuration of one or more resources used by the UE to send one or more requests to trigger beam sweeping; receiving, from the base station, the configuration of the one or more resources to be used by the UE to transmit the one or more requests to trigger the beam sweeping; sending, to the base station, the one or more requests to trigger the beam sweeping on the one or more resources configured for the UE; receiving a confirmation of the beam sweep from the base station; and performing the beam sweep based on the confirmation.

[0162] Clause 57: A method for a user equipment (UE) for beam management in communication, the method comprising: sending, to a base station through a random access procedure, one or more requests for triggering beam sweeping, wherein the one or more requests for triggering beam sweeping include at least one of one or more desired opportunities for performing the beam sweeping or one or more configurations for performing the beam sweeping; receiving a confirmation of the beam sweep from the base station; and performing the beam sweep based on the confirmation.

[0163] Clause 58: A method for a base station for beam management in communication, said method comprising: receiving, from a user equipment (UE), one or more requests for configuration of one or more resources used by the UE to transmit one or more requests to trigger beam sweeping; transmitting to the UE the configuration of the one or more resources to be used by the UE to transmit the one or more requests to trigger the beam sweeping; receiving the one or more requests to trigger the beam sweeping from the UE; sending a confirmation of the beam sweep to the UE; and performing the beam sweep based on the confirmation.

[0164] Clause 59: A method for a base station for beam management in communication, said method comprising: receiving, from a user equipment (UE) through a random access procedure, one or more requests for triggering beam sweeping, wherein the one or more requests for triggering beam sweeping include at least one of one or more desired opportunities for performing the beam sweeping or one or more configurations for performing the beam sweeping; sending a confirmation of the beam sweep to the UE; and performing the beam sweep based on the confirmation.

[0165] Clause 60: A method for a base station for beam management in communication, said method comprising: sending one or more requests for one or more channel state information (CSI) reports to a user equipment (UE), the one or more requests including configurations for one or more CSI measurements to be performed by the UE; receiving the one or more CSI reports from the UE; updating one or more learned models included in the base station based on the received one or more CSI reports, the one or more learned models including at least one of one or more weights or one or more parameters; determining one or more beam directions for at least one of the base station or the UE based on the updated one or more learned models; and transmitting to the UE at least one of the updated one or more learned models, or the updated one or more weights, or the updated one or more parameters.

[0166] Clause 61: A method for a user equipment (UE) for beam management in communication, the method comprising: receiving one or more requests for one or more channel state information (CSI) reports from a base station, the one or more requests including configurations for one or more CSI measurements to be performed by the UE; transmitting the one or more CSI reports to the base station; receiving, from the base station, an updated learned model for the UE, or at least one of updated one or more weights or updated one or more parameters of the learned model for the UE, wherein the learned model for the UE is included in the base station and is updated by the UE based on the one or more CSI reports; determining one or more beam directions for the UE based on the updated learning model for the UE, or the at least one of the updated one or more weights or the updated one or more parameters of the learning model for the UE.

[0167] Clause 62: A method for a user equipment (UE) for beam management in communication, the method comprising: receiving one or more requests for one or more channel state information (CSI) reports from a base station, the one or more requests including configurations for one or more CSI measurements to be performed by the UE; transmitting the one or more CSI reports to the base station; receiving from the base station one or more beam directions for the UE determined by a learned model included in the base station, the learned model being a learned model for both the UE and the base station; a beam to be used by the UE based on the received one or more beam directions; and determining

[0168] Clause 63: A method for a user equipment (UE) for beam management in communication, the method comprising: identifying an optimal beam pair based on one or more signals received from a base station; updating one or more learning models included in the UE based on the identified optimal beam pair, the one or more learning models including at least one of one or more weights or one or more parameters; determining one or more beam directions for at least one of the UE or the base station based on the updated one or more learned models; and transmitting at least one of the updated one or more learned models, or the updated one or more weights, or the updated one or more parameters to the base station.

[0169] Clause 64: A method for a base station for beam management in communication, said method comprising: receiving, from a user equipment (UE), an updated learned model for the base station, or at least one of updated one or more weights or updated one or more parameters of the learned model for the base station, wherein the learned model for the base station is included in and updated by the UE; determining one or more beam directions for the base station based on at least one of the received updated learned model for the base station, or the updated one or more weights of the learned model for the base station, or the updated one or more parameters.

[0170] Clause 65: A method for a base station for beam management in communication, said method comprising: receiving, from a user equipment (UE), one or more beam directions for the base station determined by a learned model included in the UE, the learned model being a learned model for both the UE and the base station; and determining a beam for the base station based on the received one or more beam directions.

[0171] Clause 66: A non-transitory computer-readable medium storing instructions executable by one or more processors of a user equipment (UE) for communication to perform a method for beam management, the method comprising: sending one or more requests to a base station for configuration of one or more resources used by the UE to send one or more requests to trigger beam sweeping; receiving, from the base station, the configuration of the one or more resources to be used by the UE to transmit the one or more requests to trigger the beam sweeping; sending, to the base station, the one or more requests to trigger the beam sweeping on the one or more resources configured for the UE; receiving a confirmation of the beam sweep from the base station; and performing the beam sweep based on the confirmation.

[0172] Clause 67: A non-transitory computer storing instructions executable by one or more processors of a user equipment (UE) for communication to perform a method for beam management. A readable medium, the method comprising: sending, to a base station through a random access procedure, one or more requests for triggering beam sweeping, wherein the one or more requests for triggering beam sweeping include at least one of one or more desired opportunities for performing the beam sweeping or one or more configurations for performing the beam sweeping; receiving a confirmation of the beam sweep from the base station; and performing the beam sweep based on the confirmation.

[0173] Clause 68: A non-transitory computer-readable medium storing instructions executable by one or more processors of a base station for communication to perform a method for beam management, said method comprising: receiving, from a user equipment (UE), one or more requests for configuration of one or more resources used by the UE to transmit one or more requests to trigger beam sweeping; transmitting to the UE the configuration of the one or more resources to be used by the UE to transmit the one or more requests to trigger the beam sweeping; receiving the one or more requests to trigger the beam sweeping from the UE; sending a confirmation of the beam sweep to the UE; and performing the beam sweep based on the confirmation.

[0174] Clause 69: A non-transitory computer-readable medium storing instructions executable by one or more processors of a base station for communication to perform a method for beam management, said method comprising: receiving, from a user equipment (UE) through a random access procedure, one or more requests for triggering beam sweeping, wherein the one or more requests for triggering beam sweeping include at least one of one or more desired opportunities for performing the beam sweeping or one or more configurations for performing the beam sweeping; sending a confirmation of the beam sweep to the UE; and performing the beam sweep based on the confirmation.

[0175] Clause 70: A non-transitory computer-readable medium storing instructions executable by one or more processors of a base station for communication to perform a method for beam management, said method comprising: sending one or more requests for one or more channel state information (CSI) reports to a user equipment (UE), the one or more requests including configurations for one or more CSI measurements to be performed by the UE; receiving the one or more CSI reports from the UE; updating one or more learned models included in the base station based on the received one or more CSI reports, the one or more learned models including at least one of one or more weights or one or more parameters; determining one or more beam directions for at least one of the base station or the UE based on the updated one or more learned models; and transmitting to the UE at least one of the updated one or more learned models, or the updated one or more weights, or the updated one or more parameters.

[0176] Clause 71: A non-transitory computer-readable medium storing instructions executable by one or more processors of a user equipment (UE) for communication to perform a method for beam management, the method comprising: receiving one or more requests for one or more channel state information (CSI) reports from a base station, the one or more requests including configurations for one or more CSI measurements to be performed by the UE; transmitting the one or more CSI reports to the base station; receiving, from the base station, an updated learned model for the UE, or at least one of updated one or more weights or updated one or more parameters of the learned model for the UE, wherein the learned model for the UE is included in the base station and is updated by the UE based on the one or more CSI reports; determining one or more beam directions for the UE based on the updated learned model for the UE, or the at least one of the updated one or more weights or the updated one or more parameters of the learned model for the UE.

[0177] Clause 72: A non-transitory computer-readable medium storing instructions executable by one or more processors of a user equipment (UE) for communication to perform a method for beam management, the method comprising: receiving one or more requests for one or more channel state information (CSI) reports from a base station, the one or more requests including configurations for one or more CSI measurements to be performed by the UE; transmitting the one or more CSI reports to the base station; receiving from the base station one or more beam directions for the UE determined by a learned model included in the base station, the learned model being a learned model for both the UE and the base station; and determining a beam to be used by the UE based on the received one or more beam directions.

[0178] Clause 73: A non-transitory computer-readable medium storing instructions executable by one or more processors of a user equipment (UE) for communication to perform a method for beam management, the method comprising: identifying an optimal beam pair based on one or more signals received from a base station; updating one or more learning models included in the UE based on the identified optimal beam pair, the one or more learning models including at least one of one or more weights or one or more parameters; determining one or more beam directions for at least one of the UE or the base station based on the updated one or more learned models; and transmitting at least one of the updated one or more learned models, or the updated one or more weights, or the updated one or more parameters to the base station.

[0179] Clause 74: A non-transitory computer-readable medium storing instructions executable by one or more processors of a base station for communication to perform a method for beam management, said method comprising: receiving, from a user equipment (UE), an updated learned model for the base station, or at least one of updated one or more weights or updated one or more parameters of the learned model for the base station, wherein the learned model for the base station is included in and updated by the UE; determining one or more beam directions for the base station based on at least one of the received updated learned model for the base station, or the updated one or more weights or the updated one or more parameters of the learned model for the base station.

[0180] Clause 75: A non-transitory computer-readable medium storing instructions executable by one or more processors of a base station for communication to perform a method for beam management, said method comprising: receiving, from a user equipment (UE), one or more beam directions for the base station determined by a learned model included in the UE, the learned model being a learned model for both the UE and the base station; determining a beam for the base station based on the received one or more beam directions.

Claims

1. 1. A user equipment (UE) for beam management in communications, comprising: a memory for storing instructions; a processor, The processor: Executing the instructions stored in the memory, sending one or more requests to a base station for configuration of one or more resources used by the UE to send one or more requests to trigger beam sweeping; receiving, from the base station, the configuration of the one or more resources to be used by the UE to transmit the one or more requests to trigger the beam sweeping; sending, to the base station, the one or more requests to trigger the beam sweeping on the one or more resources configured for the UE; receiving a confirmation of the beam sweep from the base station; performing the beam sweep based on the confirmation. UE.

2. The processor executes the instructions stored in the memory to 2. The UE of claim 1, configured to transmit the one or more requests for the configuration of the one or more resources to be used by the UE to the base station through a random access procedure.

3. The processor executes the instructions stored in the memory to 3. The UE of claim 2, configured to receive the configuration of the one or more resources to be used by the UE from the base station through at least Message 4 (Msg4) of the random access procedure.

4. The processor executes the instructions stored in the memory to 2. The UE of claim 1, configured to receive the configuration of the one or more resources used by the UE from the base station via at least one of a radio resource control (RRC) signal, a medium access control (MAC) control element (CE), or downlink control information (DCI).

5. 2. The UE of claim 1, wherein the one or more requests to trigger the beam sweeping include at least one of one or more desired opportunities for performing the beam sweeping or one or more configurations for performing the beam sweeping.

6. 2. The UE of claim 1, wherein the confirmation regarding the beam sweeping received from the base station includes at least one of: (1) whether a channel state information reference signal (CSI-RS) or a synchronization signal and physical broadcast channel (SSB) should be used to perform the beam sweeping; (2) one or more sets of beam directions for the beam sweeping; or (3) one or more widths of one or more beams for the beam sweeping.

7. The processor executes the instructions stored in the memory to The UE of claim 1 , configured to perform the beam sweeping using at least a sounding reference signal (SRS).

8. 1. A user equipment (UE) for beam management in communications, comprising: a memory for storing instructions; a processor, The processor executes the instructions stored in the memory to sending, to a base station through a random access procedure, one or more requests for triggering beam sweeping, wherein the one or more requests for triggering beam sweeping include at least one of one or more desired opportunities for performing the beam sweeping or one or more configurations for performing the beam sweeping; receiving a confirmation of the beam sweep from the base station; performing the beam sweep based on the confirmation. UE.

9. A base station for beam management in communications, comprising: a memory for storing instructions; a processor, The processor executes the instructions stored in the memory to receiving, from a user equipment (UE), one or more requests for a configuration of one or more resources to be used by the UE to transmit one or more requests to trigger beam sweeping; transmitting to the UE the configuration of the one or more resources to be used by the UE to transmit the one or more requests to trigger the beam sweeping; receiving the one or more requests to trigger the beam sweeping from the UE; sending a confirmation of the beam sweeping to the UE; performing the beam sweep based on the confirmation. Base station.

10. The processor executes the instructions stored in the memory to 10. The base station of claim 9, configured to receive from the UE, at least through a random access procedure, the one or more requests for the configuration of the one or more resources to be used by the UE.

11. The processor executes the instructions stored in the memory to 11. The base station of claim 10, configured to transmit the configuration of the one or more resources to be used by the UE to the UE through at least Message 4 (Msg4) of the random access procedure.

12. The processor executes the instructions stored in the memory to 10. The base station of claim 9, configured to transmit to the UE the configuration of the one or more resources to be used by the UE via at least one of a radio resource control (RRC) signal, a medium access control (MAC) control element (CE), or downlink control information (DCI).

13. The processor executes the instructions stored in the memory to 10. The base station of claim 9, configured to perform the configuration of the one or more resources used by the UE periodically, semi-periodically, or aperiodically.

14. The processor executes the instructions stored in the memory to The base station of claim 9 , configured to receive from the UE the one or more requests to trigger the beam sweeping on the configured one or more resources.

15. 10. The base station of claim 9, wherein the one or more requests to trigger the beam sweeping received from the UE include at least one of one or more desired opportunities for performing the beam sweeping or one or more configurations for performing the beam sweeping.

16. 10. The base station of claim 9, wherein the confirmation for the beam sweeping transmitted to the UE includes at least one of: (1) whether to use a channel state information reference signal (CSI-RS) or a synchronization signal and a physical broadcast channel (SSB) to perform the beam sweeping; (2) one or more sets of beam directions for the beam sweeping; or (3) one or more widths of one or more beams for the beam sweeping.

17. A base station for beam management in communications, comprising: a memory for storing instructions; a processor, The processor executes the instructions stored in the memory to receiving, from a user equipment (UE) through a random access procedure, one or more requests for triggering beam sweeping, wherein the one or more requests for triggering beam sweeping include at least one of one or more desired opportunities for performing the beam sweeping or one or more configurations for performing the beam sweeping; sending a confirmation of the beam sweeping to the UE; performing the beam sweep based on the confirmation. Base station.

18. A base station for beam management in communications, comprising: a memory for storing instructions; a processor, The processor executes the instructions stored in the memory to sending one or more requests for one or more channel state information (CSI) reports to a user equipment (UE), the one or more requests including configurations for one or more CSI measurements to be performed by the UE; receiving the one or more CSI reports from the UE; updating one or more learned models included in the base station based on the received one or more CSI reports, the one or more learned models including at least one of one or more weights or one or more parameters; determining one or more beam directions for at least one of the base station or the UE based on the updated one or more learned models; and transmitting at least one of the updated one or more learned models, or the updated one or more weights, or the updated one or more parameters to the UE. Base station.

19. the one or more learning models, a training model for the base station and a training model for the UE; or 20. The base station of claim 18, comprising at least one of a learned model for both the base station and the UE.

20. The one or more learning models include a learning model for the base station and a learning model for the UE, and the processor executes the instructions stored in the memory to:

20. The base station of claim 18, configured to update a learned model for the base station and a learned model for the UE based on the received one or more CSI reports.

21. 21. The base station of claim 20, wherein the processor is configured to execute the instructions stored in the memory to determine the one or more beam directions for the base station.

22. 21. The base station of claim 20, wherein the processor is configured to execute the instructions stored in the memory to transmit at least one of an updated learning model for the UE, or updated one or more weights, or updated one or more parameters of a learning model for the UE to the UE.

23. The one or more learning models include learning models for both the base station and the UE, and the processor executes the instructions stored in the memory to:

20. The base station of claim 18, configured to update a learning model for both the base station and the UE based on the received one or more CSI reports.

24. 24. The base station of claim 23, wherein the processor is configured to execute the instructions stored in the memory to determine the one or more beam directions for both the base station and the UE.

25. 25. The base station of claim 24, wherein the processor is configured to execute the instructions stored in the memory to transmit to the UE at least one of one or more beam directions for the UE at a current time or one or more beam directions for the UE at a future time.

26. The processor executes the instructions stored in the memory to configuring one or more resources for transmitting at least one of the updated one or more learned models, the updated one or more weights, or the updated one or more parameters; 20. The base station of claim 18, further configured to: notify the UE of the configured one or more resources.

27. The processor executes the instructions stored in the memory to 20. The base station of claim 18, further configured to inform the UE via a Master Information Block (MIB) or a System Information Block (SIB) of one or more supported structures for the one or more learning models.

28. The processor executes the instructions stored in the memory to 20. The base station of claim 18, further configured to receive from the UE one or more supported structures for the one or more learning models, the one or more supported structures being included in UE capability information transmitted via RRC signaling.

29. One or more neural networks are employed by the base station, and the structure of the one or more learning models is: the number of neural network layers, the number of neural nodes in each neural network layer, one or more connection structures between the neural network layers; one or more types of said neural network layers; one or more types of connections of said neural nodes; one or more types of computing operations at each neural node; the number of weights in said one or more neural networks; the number of parameters of said one or more neural networks; one or more types of weights of said one or more neural networks; one or more types of parameters of the one or more neural networks; or 19. The base station of claim 18, wherein the one or more neural networks are identified based on at least one of: one or more loss functions of the one or more neural networks.

30. One or more deep reinforcement learning (DRL) methods are employed by the base station, and the structure of the one or more learning models is: the state space of the DRL; the action space of the DRL, one or more reward functions of said DRL; The size of the replay memory and the contents of the replay memory, or 20. The base station of claim 18, wherein the replay memory is determined based on at least one of: a minimum batch size for sampling in the replay memory;

31. The processor executes the instructions stored in the memory to 20. The base station of claim 18, further configured to: update the one or more learning models included in the base station in response to determining that one or more measurements in the one or more CSI reports received from the UE are lower than a predetermined threshold.

32. 1. A user equipment (UE) for beam management in communications, comprising: a memory for storing 845817 instructions; a processor, The processor executes the instructions stored in the memory to receiving one or more requests for one or more channel state information (CSI) reports from a base station, the one or more requests including configurations for one or more CSI measurements to be performed by the UE; transmitting the one or more CSI reports to the base station; receiving from the base station an updated learned model for the UE, or at least one of updated one or more weights or updated one or more parameters of a learned model for the UE, wherein the learned model for the UE is included in the base station and is updated by the base station based on the one or more CSI reports; determining one or more beam directions for the UE based on the at least one of the updated learned model for the UE, or the updated one or more weights, or the updated one or more parameters of the learned model for the UE. UE.

33. 33. The UE of claim 32, wherein the one or more beam directions for the UE include at least one of the one or more beam directions for the UE at a current time or the one or more beam directions for the UE at a future time.

34. The processor executes the instructions stored in the memory to 33. The UE of claim 32, further configured to receive from the base station at least one of one or more resources configured for transmission of the updated learning model for the UE, or the updated one or more weights or the updated one or more parameters of the learning model for the UE.

35. The processor executes the instructions stored in the memory to receiving, from the base station, one or more supported structures for a training model for the base station via a master information block (MIB) or a system information block (SIB); The UE of claim 32, further configured to:

36. The processor executes the instructions stored in the memory to 33. The UE of claim 32, further configured to transmit to the base station one or more supported structures for the learning model for the UE via at least one of a radio resource control (RRC) signal, a medium access control (MAC) control element (CE), or downlink control information (DCI).

37. 1. A user equipment (UE) for beam management in communications, comprising: a memory for storing instructions; a processor, The processor executes the instructions stored in the memory to receiving one or more requests for one or more channel state information (CSI) reports from a base station, the one or more requests including configurations for one or more CSI measurements to be performed by the UE; transmitting the one or more CSI reports to the base station; receiving from the base station one or more beam directions for the UE determined by a learned model included in the base station, the learned model being a learned model for both the UE and the base station; and determining a beam to be used by the UE based on the received one or more beam directions.

38. 38. The UE of claim 37, wherein the one or more beam directions for the UE include at least one of the one or more beam directions for the UE at a current time or the one or more beam directions for the UE at a future time.

39. 1. A user equipment (UE) for beam management in communications, comprising: The UE a memory for storing instructions; a processor, The processor: Executing the instructions stored in the memory, identifying an optimal beam pair based on one or more signals received from a base station; updating one or more learning models included in the UE based on the identified optimal beam pair, the one or more learning models including at least one of one or more weights or one or more parameters; determining one or more beam directions for at least one of the UE or the base station based on the updated one or more learned models; and transmitting at least one of the updated one or more learned models, or the updated one or more weights, or the updated one or more parameters to the base station. UE.

40. The processor executes the instructions stored in the memory to sending one or more requests to the base station for configuration of one or more resources used by the UE to send one or more requests to trigger beam sweeping; receiving the configuration of the one or more resources from the base station; transmitting the one or more requests to the base station to trigger the beam sweeping based on the received configuration of the one or more resources.

40. The UE of claim 39.

41. The processor executes the instructions stored in the memory. identifying the optimal beam pair based on one or more measurements of at least one of a Channel State Information Reference Signal (CSI-RS) or synchronization signal and a Physical Broadcast Channel (SSB) received from the base station; or 40. The UE of claim 39, further configured to identify the optimal beam pair via beam sweeping triggered by the base station.

42. the one or more learning models, a learned model for the UE and a learned model for the base station; or 40. The UE of claim 39, including at least one of a learning model for both the UE and the base station.

43. The processor executes the instructions stored in the memory to sending to the base station one or more requests for configuration of one or more resources to be used by the UE for transmission of at least one of the updated one or more learned models, or the updated one or more weights, or the updated one or more parameters; receiving, from the base station, the configuration of the one or more resources to be used by the UE; 40. The UE of claim 39, further configured to: transmit at least one of the updated one or more learned models, the updated one or more weights, or the updated one or more parameters to the base station based on the configuration of the one or more resources.

44. The one or more learning models include a learning model for the base station and a learning model for the UE, and the processor executes the instructions stored in the memory to:

40. The UE of claim 39, further configured to update a learning model for the UE and a learning model for the base station based on the identified optimal beam pair.

45. 45. The UE of claim 44, wherein the processor is configured to execute the instructions stored in the memory to determine the one or more beam directions for the UE.

46. 45. The UE of claim 44, wherein the processor is configured to execute the instructions stored in the memory to send to the base station at least one of an updated learned model for the base station, or updated one or more weights or updated one or more parameters of the learned model for the base station.

47. The one or more learning models include learning models for both the UE and the base station, and the processor executes the instructions stored in the memory to:

40. The UE of claim 39, further configured to update a learning model for both the UE and the base station based on the identified optimal beam pair.

48. 48. The UE of claim 47, wherein the processor is configured to execute the instructions stored in the memory to determine the one or more beam directions for both the UE and the base station.

49. The processor executes the instructions stored in the memory to provide the base station with the one or more beam directions for the base station at a current time or a future time.

49. The UE of claim 48, configured to transmit at least one of one or more beam directions for the base station.

50. One or more neural networks are employed by the UE, and the structure of the one or more learning models is: the number of neural network layers, the number of neural nodes in each neural network layer, one or more connection structures between the neural network layers; one or more types of said neural network layers; one or more types of connections of said neural nodes; one or more types of computing operations at each neural node; the number of weights in said one or more neural networks; the number of parameters of said one or more neural networks; one or more types of weights of said one or more neural networks; one or more types of parameters of the one or more neural networks; or 40. The UE of claim 39, wherein the one or more neural networks are identified based on at least one of: one or more loss functions of the one or more neural networks.

51. One or more deep reinforcement learning (DRL) methods are employed by the base station, and the structure of the one or more learning models is: the state space of the DRL; the action space of the DRL, one or more reward functions of said DRL; The size of the replay memory and the contents of the replay memory, or a minimum batch size for sampling in the replay memory.

52. A base station for beam management in communications, comprising: a memory for storing instructions; a processor, The processor: Executing the instructions stored in the memory, receiving from a user equipment (UE) an updated learned model for the base station, or at least one of updated one or more weights or updated one or more parameters of the learned model for the base station, wherein the learned model for the base station is included in and updated by the UE; determining one or more beam directions for the base station based on at least one of the received updated learned model for the base station, or the updated one or more weights of a learned model for the base station, or the updated one or more parameters. Base station.

53. 53. The base station of claim 52, wherein the one or more beam directions for the base station include at least one of the one or more beam directions for the base station at a current time or the one or more beam directions for the base station at a future time.

54. A base station for beam management in communications, comprising: a memory for storing instructions; a processor, The processor: Executing the instructions stored in the memory, receiving, from a user equipment (UE), one or more beam directions for the base station determined by a learned model included in the UE, the learned model being a learned model for both the UE and the base station; determining a beam for the base station based on the received one or more beam directions. Base station.

55. 55. The base station of claim 54, wherein the one or more beam directions for the base station include at least one of the one or more beam directions for the base station at a current time or the one or more beam directions for the base station at a future time.

56. 1. A method for a user equipment (UE) for beam management in communication, comprising: sending one or more requests to a base station for configuration of one or more resources used by the UE to send one or more requests to trigger beam sweeping; receiving, from the base station, the configuration of the one or more resources to be used by the UE to transmit the one or more requests to trigger the beam sweeping; sending, to the base station, the one or more requests to trigger the beam sweeping on the one or more resources configured for the UE; receiving a confirmation of the beam sweep from the base station; performing the beam sweep based on the confirmation; and A method comprising:

57. 1. A method for a user equipment (UE) for beam management in communication, comprising: sending, to a base station through a random access procedure, one or more requests for triggering beam sweeping, wherein the one or more requests for triggering beam sweeping include at least one of one or more desired opportunities for performing the beam sweeping or one or more configurations for performing the beam sweeping; receiving a confirmation of the beam sweep from the base station; performing the beam sweep based on the confirmation; and A method comprising:

58. 1. A method for a base station for beam management in communications, comprising: receiving, from a user equipment (UE), one or more requests for a configuration of one or more resources to be used by the UE to transmit one or more requests to trigger beam sweeping; transmitting to the UE the configuration of the one or more resources to be used by the UE to transmit the one or more requests to trigger the beam sweeping; receiving the one or more requests to trigger the beam sweeping from the UE; sending a confirmation of the beam sweeping to the UE; performing the beam sweep based on the confirmation; and A method comprising:

59. 1. A method for a base station for beam management in communications, the method comprising: receiving, from a user equipment (UE) through a random access procedure, one or more requests to trigger beam sweeping, wherein the one or more requests to trigger beam sweeping indicate one or more desired opportunities to perform the beam sweeping, or including at least one of one or more configurations for performing beam sweeping; sending a confirmation of the beam sweeping to the UE; performing the beam sweep based on the confirmation; and A method comprising:

60. 1. A method for a base station for beam management in communications, comprising: sending one or more requests for one or more channel state information (CSI) reports to a user equipment (UE), the one or more requests including configurations for one or more CSI measurements to be performed by the UE; receiving the one or more CSI reports from the UE; updating one or more learned models included in the base station based on the received one or more CSI reports, the one or more learned models including at least one of one or more weights or one or more parameters; determining one or more beam directions for at least one of the base station or the UE based on the updated one or more learned models; transmitting at least one of the updated one or more learned models, or the updated one or more weights, or the updated one or more parameters to the UE; A method comprising:

61. 1. A method for a user equipment (UE) for beam management in communication, comprising: receiving one or more requests for one or more channel state information (CSI) reports from a base station, the one or more requests including configurations for one or more CSI measurements to be performed by the UE; transmitting the one or more CSI reports to the base station; receiving from the base station an updated learned model for the UE, or at least one of updated one or more weights or updated one or more parameters of the learned model for the UE, wherein the learned model for the UE is included in the base station and is updated by the UE based on the one or more CSI reports; determining one or more beam directions for the UE based on the updated learned model for the UE, or the at least one of the updated one or more weights or the updated one or more parameters of the learned model for the UE; A method comprising:

62. 1. A method for a user equipment (UE) for beam management in communication, comprising: receiving one or more requests for one or more channel state information (CSI) reports from a base station, the one or more requests including configurations for one or more CSI measurements to be performed by the UE; transmitting the one or more CSI reports to the base station; receiving from the base station one or more beam directions for the UE determined by a learned model included in the base station, the learned model being a learned model for both the UE and the base station; and determining a beam to be used by the UE based on the received one or more beam directions.

63. 1. A method for a user equipment (UE) for beam management in communication, comprising: identifying an optimal beam pair based on one or more signals received from a base station; updating one or more training models included in the UE based on the identified optimal beam pair, wherein the one or more training models include one or more weights or one or more including at least one of the above parameters; determining one or more beam directions for at least one of the UE or the base station based on the updated one or more learned models; and transmitting at least one of the updated one or more learned models, or the updated one or more weights, or the updated one or more parameters to the base station.

64. 1. A method for a base station for beam management in communications, comprising: receiving, from a user equipment (UE), an updated learned model for the base station, or at least one of updated one or more weights or updated one or more parameters of the learned model for the base station, wherein the learned model for the base station is included in and updated by the UE; determining one or more beam directions for the base station based on at least one of the received updated learned model for the base station, or the updated one or more weights of the learned model for the base station, or the updated one or more parameters; A method comprising:

65. 1. A method for a base station for beam management in communications, comprising: receiving, from a user equipment (UE), one or more beam directions for the base station determined by a learned model included in the UE, the learned model being a learned model for both the UE and the base station; and determining a beam for the base station based on the received one or more beam directions.

66. 1. A non-transitory computer-readable medium storing instructions executable by one or more processors of a user equipment (UE) for communication to perform a method for beam management, the method comprising: The method comprises: sending one or more requests to a base station for configuration of one or more resources used by the UE to send one or more requests to trigger beam sweeping; receiving, from the base station, the configuration of the one or more resources to be used by the UE to transmit the one or more requests to trigger the beam sweeping; sending, to the base station, the one or more requests to trigger the beam sweeping on the one or more resources configured for the UE; receiving a confirmation of the beam sweep from the base station; performing the beam sweep based on the confirmation; and 1. A non-transitory computer-readable medium comprising:

67. 1. A non-transitory computer-readable medium storing instructions executable by one or more processors of a user equipment (UE) for communication to perform a method for beam management, the method comprising: The method comprises: sending, to a base station through a random access procedure, one or more requests for triggering beam sweeping, wherein the one or more requests for triggering beam sweeping include at least one of one or more desired opportunities for performing the beam sweeping or one or more configurations for performing the beam sweeping; receiving a confirmation of the beam sweep from the base station; performing the beam sweep based on the confirmation; and 1. A non-transitory computer-readable medium comprising:

68. 1. A non-transitory computer-readable medium storing instructions executable by one or more processors of a base station for communication to perform a method for beam management, the method comprising: The method comprises: receiving, from a user equipment (UE), one or more requests for a configuration of one or more resources to be used by the UE to transmit one or more requests to trigger beam sweeping; transmitting to the UE the configuration of the one or more resources to be used by the UE to transmit the one or more requests to trigger the beam sweeping; receiving the one or more requests to trigger the beam sweeping from the UE; sending a confirmation of the beam sweeping to the UE; performing the beam sweep based on the confirmation; and 1. A non-transitory computer-readable medium comprising:

69. 1. A non-transitory computer-readable medium storing instructions executable by one or more processors of a base station for communication to perform a method for beam management, the method comprising: The method comprises: receiving, from a user equipment (UE) through a random access procedure, one or more requests for triggering beam sweeping, wherein the one or more requests for triggering beam sweeping include at least one of one or more desired opportunities for performing the beam sweeping or one or more configurations for performing the beam sweeping; sending a confirmation of the beam sweeping to the UE; performing the beam sweep based on the confirmation; and 1. A non-transitory computer-readable medium comprising:

70. 1. A non-transitory computer-readable medium storing instructions executable by one or more processors of a base station for communication to perform a method for beam management, the method comprising: The method comprises: sending one or more requests for one or more channel state information (CSI) reports to a user equipment (UE), the one or more requests including configurations for one or more CSI measurements to be performed by the UE; receiving the one or more CSI reports from the UE; updating one or more learned models included in the base station based on the received one or more CSI reports, the one or more learned models including at least one of one or more weights or one or more parameters; determining one or more beam directions for at least one of the base station or the UE based on the updated one or more learned models; transmitting at least one of the updated one or more learned models, or the updated one or more weights, or the updated one or more parameters to the UE; 1. A non-transitory computer-readable medium comprising:

71. 1. A non-transitory computer-readable medium storing instructions executable by one or more processors of a user equipment (UE) for communication to perform a method for beam management, the method comprising: The method comprises: receiving one or more requests for one or more channel state information (CSI) reports from a base station, the one or more requests being performed by the UE; Including configuration for CSI measurements; transmitting the one or more CSI reports to the base station; receiving from the base station an updated learned model for the UE, or at least one of updated one or more weights or updated one or more parameters of the learned model for the UE, wherein the learned model for the UE is included in the base station and is updated by the UE based on the one or more CSI reports; determining one or more beam directions for the UE based on the updated learned model for the UE, or the at least one of the updated one or more weights or the updated one or more parameters of the learned model for the UE; 1. A non-transitory computer-readable medium comprising:

72. 1. A non-transitory computer-readable medium storing instructions executable by one or more processors of a user equipment (UE) for communication to perform a method for beam management, the method comprising: The method comprises: receiving one or more requests for one or more channel state information (CSI) reports from a base station, the one or more requests including configurations for one or more CSI measurements to be performed by the UE; transmitting the one or more CSI reports to the base station; receiving from the base station one or more beam directions for the UE determined by a learned model included in the base station, the learned model being a learned model for both the UE and the base station; determining a beam to be used by the UE based on the received one or more beam directions; 1. A non-transitory computer-readable medium comprising:

73. 1. A non-transitory computer-readable medium storing instructions executable by one or more processors of a user equipment (UE) for communication to perform a method for beam management, the method comprising: The method comprises: identifying an optimal beam pair based on one or more signals received from a base station; updating one or more learning models included in the UE based on the identified optimal beam pair, the one or more learning models including at least one of one or more weights or one or more parameters; determining one or more beam directions for at least one of the UE or the base station based on the updated one or more learned models; and transmitting at least one of the updated one or more learned models, or the updated one or more weights, or the updated one or more parameters to the base station.

74. 1. A non-transitory computer-readable medium storing instructions executable by one or more processors of a base station for communication to perform a method for beam management, the method comprising: The method comprises: receiving, from a user equipment (UE), an updated learned model for the base station, or at least one of updated one or more weights or updated one or more parameters of the learned model for the base station, wherein the learned model for the base station is included in and updated by the UE; the received updated learning model for the base station, or a previous learning model for the base station determining one or more beam directions for the base station based on at least one of the updated one or more weights or the updated one or more parameters of the learned model; 1. A non-transitory computer-readable medium comprising:

75. 1. A non-transitory computer-readable medium storing instructions executable by one or more processors of a base station for communication to perform a method for beam management, the method comprising: The method comprises: receiving, from a user equipment (UE), one or more beam directions for the base station determined by a learned model included in the UE, the learned model being a learned model for both the UE and the base station; determining a beam for the base station based on the received one or more beam directions; 1. A non-transitory computer-readable medium comprising:

Images