NEURAL NETWORK BASED NONLINEAR MU-MIMO PRECODING

    公开(公告)号:US20220263544A1

    公开(公告)日:2022-08-18

    申请号:US17178175

    申请日:2021-02-17

    Abstract: A base station may apply a nonlinear precoding to data for MU-MIMO transmission to a set of paired UEs to generate a first set of precoder symbols, and apply a linear precoding to the first set of precoder symbols to generate a second set of precoder symbols using a linear precoding matrix. The base station may normalize the second set of precoder symbols, and scale the second set of precoder symbols, before transmission of the data, using a scaling factor based on one or more of modulation symbols or a channel matrix. The base station may apply the linear precoding to DMRS associated with the data. The base station may transmit the second set of precoder symbols based on the second set of precoder symbols and the DMRS to the set of paired UEs.

    POWER LEVEL DETERMINATION FOR TRANSMISSION OF REFERENCE SIGNALS

    公开(公告)号:US20220217724A1

    公开(公告)日:2022-07-07

    申请号:US17142182

    申请日:2021-01-05

    Abstract: Disclosed are techniques for determining tone patterns and associated power levels for transmission of reference signals. A tone pattern (e.g., with each tone pattern occupying a resource element in a resource block) can be determined for a reference signal for use in wireless communications between a receiving device and a transmitting device. A plurality of power levels for the tone pattern can be determined. The plurality of power levels can include a respective power level determined for each resource element associated with the tone pattern. One or more of the tone pattern or the plurality of power levels can be used (e.g., transmitted to the transmitting device) for transmission of the reference signal (e.g., from the transmitting device to the receiving device).

    NON-UNIFORM QUANTIZED FEEDBACK IN FEDERATED LEARNING

    公开(公告)号:US20220103221A1

    公开(公告)日:2022-03-31

    申请号:US17448226

    申请日:2021-09-21

    Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a client device may determine a feedback associated with a machine learning component based at least in part on applying the machine learning component. Accordingly, the client device may transmit a quantized value based at least in part on the feedback. The quantized value is determined based at least in part on distances between the feedback and a non-uniform set of quantized digits. Numerous other aspects are provided.

    MULTI-STAGE MARKOV DECISION PROCESS (MDP) MODEL FOR A SPECTRUM SHARING SYSTEM

    公开(公告)号:US20220095119A1

    公开(公告)日:2022-03-24

    申请号:US17478669

    申请日:2021-09-17

    Abstract: A method of wireless communication performed by a first transmission device incudes receiving a first set of observations from a first receiving device based on transmissions from the first transmission device to the first receiving device at a previous time slot of a fixed contention-based spectrum sharing system. The first transmission device shares a spectrum with a second transmission device. The method also includes measuring an energy level from an ongoing data transmission of the second transmission device at a current time slot. The method further includes generating, at an artificial neural network of the first transmission device, at least one of a transmission determination, a set of transmission parameters, or a combination thereof, based on a second set of observations, the energy level, and a counter. The method also includes transmitting, to the first receiving device, during the current time slot based on at least one of the transmission determination, the set of transmission parameters, or the combination thereof.

    WIRELESS COMMUNICATIONS-BASED SENSING FOR LOCATION DETECTION ACROSS CARRIERS

    公开(公告)号:US20210392516A1

    公开(公告)日:2021-12-16

    申请号:US17343390

    申请日:2021-06-09

    Abstract: Disclosed are techniques for environment sensing. In an aspect, a first network node measures one or more first reference signals on a first carrier frequency, the one or more first reference signals received from a second network node to enable determination of one or more first characteristics associated with one or more target objects, and measures one or more second reference signals on a second carrier frequency, the one or more second reference signals received from the second network node to enable determination of one or more second characteristics associated with the one or more target objects, wherein an accuracy of the one or more second characteristics is higher than an accuracy of the one or more first characteristics based on the one or more first reference signals being measured on the first carrier frequency and the one or more second reference signals being measured on the second carrier frequency.

Patent Agency Ranking