Model transfer within wireless networks for channel estimation

    公开(公告)号:US11863354B2

    公开(公告)日:2024-01-02

    申请号:US17318850

    申请日:2021-05-12

    CPC classification number: H04L25/0254 H04L25/0222 H04W92/18

    Abstract: A method includes receiving, by a first user device in a wireless network, an indication of availability of a pre-trained model that estimates a channel between a second user device and a network node; receiving, by the first user device, information relating to the pre-trained model; determining, by the first user device, channel estimation information based at least on the information relating to the pre-trained model; and performing at least one of the following: transmitting, by the first user device, a report to the network node including the channel estimation information; or receiving data, by the first user device from the network node, based on the channel estimation information.

    MACHINE LEARNING BASED MULTICAST USER GROUPING

    公开(公告)号:US20220286819A1

    公开(公告)日:2022-09-08

    申请号:US17191330

    申请日:2021-03-03

    Abstract: In accordance with example embodiments of the present disclosure there is at least a method and apparatus to perform communicating between a network node and a user equipment of a communication network, authorization for the user equipment to join a group of user equipment to enable the user equipment to receive multicast configurations for multicast signaling authorized for the group, wherein the authorization is based on configurations in common between the user equipment and the group of user equipment; and based on the joining, utilizing the configurations in common to produce signaling between the communication network and the user equipment to receive multicast configurations for the multicast signaling authorized for the group.

    Frequency-domain transmitters and receivers which adapt to different subcarrier spacing configurations

    公开(公告)号:US10917278B2

    公开(公告)日:2021-02-09

    申请号:US16608350

    申请日:2017-04-28

    Abstract: 5G, New Radio (NR), numerology, receiver issues. The numerology scheme here consists in keeping the bandwidth constant but varying the subcarrier spacing (ie different tone spacing B for data and K*B for control channels), and correspondingly the symbol duration. Control symbols have a wider subcarrier separation but smaller symbol duration (In the case of beamforming reference signals, it would enable to train K beams in one symbol time period). Receiver issues: Embodiment 1 uses different Rx chains for data and control channels with different FFT sizes (size differing by factor K). Embodiment 2 uses a common identical FFT size (the one of the data channel) for both control and data: For the control channel, either repeat each control symbol K times prior to FFT and performs down-sampling afterwards and repeat it for each control symbol, or performs joint processing and FFT for all K control symbols jointly by either time domain linear combination or post FFT frequency processing.

    Machine learning based multicast user grouping

    公开(公告)号:US11622242B2

    公开(公告)日:2023-04-04

    申请号:US17191330

    申请日:2021-03-03

    Abstract: In accordance with example embodiments of the present disclosure there is at least a method and apparatus to perform communicating between a network node and a user equipment of a communication network, authorization for the user equipment to join a group of user equipment to enable the user equipment to receive multicast configurations for multicast signaling authorized for the group, wherein the authorization is based on configurations in common between the user equipment and the group of user equipment; and based on the joining, utilizing the configurations in common to produce signaling between the communication network and the user equipment to receive multicast configurations for the multicast signaling authorized for the group.

    MODEL TRANSFER WITHIN WIRELESS NETWORKS FOR CHANNEL ESTIMATION

    公开(公告)号:US20220368570A1

    公开(公告)日:2022-11-17

    申请号:US17318850

    申请日:2021-05-12

    Abstract: A method includes receiving, by a first user device in a wireless network, an indication of availability of a pre-trained model that estimates a channel between a second user device and a network node; receiving, by the first user device, information relating to the pre-trained model; determining, by the first user device, channel estimation information based at least on the information relating to the pre-trained model; and performing at least one of the following: transmitting, by the first user device, a report to the network node including the channel estimation information; or receiving data, by the first user device from the network node, based on the channel estimation information.

    MACHINE LEARNING BASED CHANNEL STATE INFORMATION ESTIMATION AND FEEDBACK CONFIGURATION

    公开(公告)号:US20220271851A1

    公开(公告)日:2022-08-25

    申请号:US17180061

    申请日:2021-02-19

    Abstract: Systems, methods, apparatuses, and computer program products for machine learning based channel state information (CSI) estimation and feedback configuration are provided. A method may include learning channel state information feedback from one or more user equipment as time series data. The method may also include building a predictive model for user equipment feedback based on the learned channel state information feedback. The method may further include configuring a channel state information trigger with the one or more user equipment based on the predictive model. In addition, the method may include signaling predicted channel state information to the one or more user equipment.

Patent Agency Ranking