SPECTRUM SHARING WITH DEEP REINFORCEMENT LEARNING (RL)

    公开(公告)号:US20220078626A1

    公开(公告)日:2022-03-10

    申请号:US17463053

    申请日:2021-08-31

    Abstract: A method of wireless communication performed by a first transmission device includes determining a set of spectrum sharing parameters based on sensing performed during a sensing period of a current time slot in a fixed contention based spectrum sharing system. The first transmission device shares a spectrum with a second transmission device. The method also includes determining, at a first artificial neural network of the first transmission device, a transmission device action, and/or a transmission parameter in response to receiving the set of spectrum sharing parameters. The method further includes transmitting, from the first transmission device, to a first receiving device during a data transmission phase of the current time slot based on the transmission device action and/or the transmission parameter.

    USE-CASE-SPECIFIC WIRELESS COMMUNICATIONS-BASED RADAR REFERENCE SIGNALS

    公开(公告)号:US20210392478A1

    公开(公告)日:2021-12-16

    申请号:US17329109

    申请日:2021-05-24

    Abstract: Disclosed are techniques for allocating resources for environment sensing. In an aspect, a base station transmits a first radar reference signal (RRS) on a first set of resources comprising first time resources, first frequency resources, first spatial resources, or any combination thereof, wherein the first set of resources is selected to enable a first user equipment (UE) to perform a first type of environment sensing, and transmits a second RRS on a second set of resources comprising second time resources, second frequency resources, second spatial resources, or any combination thereof, wherein the second set of resources is selected to enable a second UE to perform a second type of environment sensing, wherein the second set of resources is different from the first set of resources, and wherein the second type of environment sensing is different from the first type of environment sensing.

    TONE RESERVATION FOR PEAK TO AVERAGE POWER RATIO REDUCTION

    公开(公告)号:US20210344537A1

    公开(公告)日:2021-11-04

    申请号:US17306762

    申请日:2021-05-03

    Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment may receive a resource allocation indicating a plurality of transmission tones comprising a subset of data tones of a plurality of data tones and a subset of peak reduction tones (PRTs) of a plurality of PRTs, wherein the resource allocation indicates locations for the plurality of data tones and locations for the plurality of PRTs within a particular bandwidth, wherein the locations for the plurality of PRTs are arranged relative to the locations for the plurality of data tones according to a PRT subsequence of a universal PRT sequence, and wherein the PRT subsequence corresponds to a sub-band of the particular bandwidth; and transmit a data transmission using a waveform based at least in part on the resource allocation. Numerous other aspects are provided.

    REPORTING BEAM MEASUREMENTS FOR PROPOSED BEAMS AND OTHER BEAMS FOR BEAM SELECTION

    公开(公告)号:US20210336683A1

    公开(公告)日:2021-10-28

    申请号:US17238153

    申请日:2021-04-22

    Abstract: Various aspects of the present disclosure relate to beam management procedures in wireless communications systems. Some implementations of the present disclosure more specifically provide techniques for reporting measurements for proposed beams (such as beams predicted to be the best beams for communications to and from a UE and a network entity) and other beams detected by the UE. The techniques may be used, for example, to identify mismatches between a proposed set of beams and actual best beams for communications to and from a UE and a network entity and allow for the retraining of machine learning models used to identify the proposed set of beams for communications to and from a UE and a network entity.

    NEURAL NETWORK BASED CHANNEL STATE INFORMATION FEEDBACK

    公开(公告)号:US20210273707A1

    公开(公告)日:2021-09-02

    申请号:US16805467

    申请日:2020-02-28

    Abstract: Various aspects of the present disclosure generally relate to neural network based channel state information (CSI) feedback. In some aspects, a device may obtain a CSI instance for a channel, determine a neural network model including a CSI encoder and a CSI decoder, and train the neural network model based at least in part on encoding the CSI instance into encoded CSI, decoding the encoded CSI into decoded CSI, and computing and minimizing a loss function by comparing the CSI instance and the decoded CSI. The device may obtain one or more encoder weights and one or more decoder weights based at least in part on training the neural network model. Numerous other aspects are provided.

Patent Agency Ranking