GAIN SCALING OF INPUT TO NEURAL NETWORK FOR END-TO-END LEARNING IN WIRELESS COMMUNICATION SYSTEM

    公开(公告)号:US20230114870A1

    公开(公告)日:2023-04-13

    申请号:US17498651

    申请日:2021-10-11

    Abstract: A method of wireless communication by a user equipment (UE) includes receiving different sets of parameters from different sources as input to a receiver neural network. The method also includes receiving, from a base station, a set of target long-term energy values associated with the receiver neural network. The method further includes calculating a scaling factor for each of the different sets of parameters based on the set of target long-term energy values, and separately scaling each of the different sets of parameters based on the scaling factor calculated for that set in order to generate multiple sets of scaled parameters. The method still further includes transmitting the multiple sets of scaled parameters to the receiver neural network.

    Neural Augmentation For Device Nonlinearity Mitigation In X-Node Machine Learning

    公开(公告)号:US20220070041A1

    公开(公告)日:2022-03-03

    申请号:US17394928

    申请日:2021-08-05

    Abstract: Various embodiments include methods for reducing peak to average power ratio of wireless transmission waveforms, performed in transmitter circuitry of a wireless communication. Various embodiments may include receiving frequency domain data tones, transforming the frequency domain data tones to time domain data signals, generating, using a set of peak reduction tone (PRT) neural networks, time domain PRTs using the time domain data signals in which the set of PRT neural networks have been trained in conjunction with an augmentation neural network, and a receiver neural network, generating an output of the augmentation neural network based on an input of final combined time domain signals including the time domain PRTs combined with previous combined time domain signals, and generating time domain wireless transmission waveforms that include the output of the augmentation neural network combined with the final combined time domain signals.

    PEAK REDUCTION TONE ALLOCATION TECHNIQUES

    公开(公告)号:US20210359890A1

    公开(公告)日:2021-11-18

    申请号:US17319014

    申请日:2021-05-12

    Abstract: Aspects presented herein may improve the efficiency and performance of the tone reservation PAPR reduction technique by allocating peak reduction tone based at least in part on a channel condition, such as based on the signal to noise ratio of the channel. In some aspects, a transmitting device measures a signal to noise ratio for a plurality of tones within a frequency resource. The transmitting device selects a location of one or more reserved tones (e.g., peak reduction tones) among one or more tones based at least in part on an SNR for one or more tones. The transmitting device transmits data to a receiving device in a subset of the plurality of tones that does not include the one or more peak reduction tones. Other aspects and features are also disclosed.

    TONE RESERVATION FOR PEAK TO AVERAGE POWER RATIO REDUCTION

    公开(公告)号:US20210344536A1

    公开(公告)日:2021-11-04

    申请号:US17306759

    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 set of transmission tones comprising a set of data tones and a set of peak reduction tones (PRTs), wherein the resource allocation indicates locations for the set of data tones and locations for the set of PRTs within a particular bandwidth, wherein the locations for the set of PRTs are arranged relative to the locations for the set of data tones according to a PRT sequence, and wherein the PRT sequence comprises a plurality of contiguous PRTs arranged relative to a plurality of contiguous data tones or a pseudo-random pattern generated using a pseudo-random number generator; and transmit a data transmission using a waveform based at least in part on the resource allocation. Numerous other aspects are provided.

    FULL DUPLEX INTERFERENCE MEASUREMENT AND REPORTING

    公开(公告)号:US20210194663A1

    公开(公告)日:2021-06-24

    申请号:US17101987

    申请日:2020-11-23

    Abstract: This disclosure provides systems, devices, apparatus and methods, including computer programs encoded on storage media, for interference measurement and reporting by a UE. The interference measurement can be self-initiated by the UE or based on a request received from a BS. To measure the interference, the UE transmits a first signal in UL resources to a first BS concurrently with receiving a second signal in DL resources from one of the first BS or a second BS. The received second signal includes interference associated with the transmitted first signal. Based on the received second signal, the UE determines a level of the interference that is associated with the transmitted first signal. Information associated with the level of the interference is then transmitted to the first BS, such as an indication of a guard band that is to be incorporated between the UL resources and the DL resources.

Patent Agency Ranking