ITERATIVE INITIALIZATION OF MACHINE-LEARNING AGENT PARAMETERS IN WIRELESS COMMUNICATION NETWORK

    公开(公告)号:US20250097093A1

    公开(公告)日:2025-03-20

    申请号:US18729676

    申请日:2023-01-20

    Abstract: A machine-learning (ML) orchestrator entity provides distributed, flexible, and efficient parameter initialization and updating for ML agents can be installed on network nodes operating under similar radio conditions. The ML orchestrator entity instructs each of such network nodes to iteratively run the ML agent in a training mode. Each run yields a local set of parameters for the ML agent. After each run, the ML orchestrator entity collects and uses the local sets of parameters from two or more network nodes to derive a common set of parameters for the network nodes. The ML orchestrator further instructs each of the network nodes to update its own local set of parameters based on the common set of parameters and use the updated local set of parameters in a subsequent run. The ML orchestrator entity repeats these steps until a termination criterion for the training mode is met.

    MEASUREMENT GAP SETTING
    2.
    发明公开

    公开(公告)号:US20240236742A9

    公开(公告)日:2024-07-11

    申请号:US18546403

    申请日:2022-02-25

    CPC classification number: H04W24/10 H04W36/0088

    Abstract: An apparatus, method and computer program is described comprising: receiving mobile communication network data for a user device; providing the received mobile communication network data to a model for generating a measurement gap setting based on the received data, wherein the measurement gap setting defines measurement gap parameters for use in scheduling radio measurements of neighbouring cells; and returning the generated measurement gap setting.

    PASSIVE IOT ILLUMINATION POWER SETTING

    公开(公告)号:US20250030461A1

    公开(公告)日:2025-01-23

    申请号:US18762320

    申请日:2024-07-02

    Abstract: An apparatus comprising: means for receiving a proximity pathloss threshold from a network, wherein a pathloss between a passive device and a user equipment connected to the apparatus is less than the proximity pathloss threshold; means for receiving, from the user equipment, at least one measurement associated with the user equipment; means for determining a backscatter link beam direction, based at least on the at least one measurement associated with the user equipment; and means for determining an illumination power of an illumination transmission to the passive device, based at least on the proximity pathloss threshold.

    SELECTION OF USER EQUIPMENT FOR PROVIDING BACKSCATTERING SERVICE TO AMBIENT IOT DEVICES

    公开(公告)号:US20240406748A1

    公开(公告)日:2024-12-05

    申请号:US18656373

    申请日:2024-05-06

    Abstract: A network device includes at least one processor and at least one memory. The memory stores instructions which, when executed by the processor(s), cause the network device at least to: access ambient IoT device deployment information for ambient IoT devices and user equipment apparatus (UE) deployment information for user equipment apparatuses (UEs); select, based on the ambient IoT device deployment information and the UE deployment information, candidate user equipment apparatuses (candidate UEs), from among the UEs, for providing backscattering service to ambient IoT devices; and iteratively select a subset of UEs, among the candidate UEs, to provide the backscattering service, where the iterative selecting is based at least on, for each iteration, at least one of: respective availability of the plurality of candidate UEs to provide the backscattering service, or at least one criterion relating to respective information in backscattering signals provided by the plurality of ambient IoT devices.

    MEASUREMENT RELAXATION
    5.
    发明申请

    公开(公告)号:US20240414579A1

    公开(公告)日:2024-12-12

    申请号:US18699465

    申请日:2022-10-19

    Abstract: According to an example embodiment, a network node device is configured to obtain measurement data of radio measurements from at least one client device; detect an outage and/or failure of the at least one client device during a first prediction period; based on the measurement data and the detected outage and/or the detected failure, train a prediction model to predict an outage and/or failure probability during a prediction period from measurement data of radio measurements; and provide the trained prediction model to the at least one client device.

    RADIO MAP IMPROVEMENTS
    6.
    发明公开

    公开(公告)号:US20240302483A1

    公开(公告)日:2024-09-12

    申请号:US18666510

    申请日:2024-05-16

    CPC classification number: G01S5/02524

    Abstract: Disclosed is a solution for managing a radio map based on radio fingerprinting measurements. A method comprises: acquiring a radio map of an area, the radio map based on radio frequency measurements performed between at least one access node of a wireless network and terminal devices within the area; detecting at least one gap in the radio map and determining geographical coordinates of the at least one gap; causing transmission of a message comprising at least one information element requesting for additional measurements and comprising the geographical coordinates of the at least one gap; in response to the message, receiving at least one radio frequency measurement report related to at least one terminal device and comprising radio frequency measurement data and at least one measurement location where the radio frequency measurement data has been measured; and updating the radio map on the basis of the radio frequency measurement data.

    MEASUREMENT GAP SETTING
    8.
    发明公开

    公开(公告)号:US20240137796A1

    公开(公告)日:2024-04-25

    申请号:US18546403

    申请日:2022-02-25

    CPC classification number: H04W24/10 H04W36/0088

    Abstract: An apparatus, method and computer program is described comprising: receiving mobile communication network data for a user device; providing the received mobile communication network data to a model for generating a measurement gap setting based on the received data, wherein the measurement gap setting defines measurement gap parameters for use in scheduling radio measurements of neighbouring cells; and returning the generated measurement gap setting.

    DISTRIBUTED TRAINING IN COMMUNICATION NETWORKS

    公开(公告)号:US20230289656A1

    公开(公告)日:2023-09-14

    申请号:US18040406

    申请日:2020-08-03

    CPC classification number: G06N20/00 H04L41/16

    Abstract: It is provided a method comprising: monitoring if a distributed training host receives a request from a meta-training host to provide a machine learning model; checking whether a link from the distributed training host to the meta-training host is required for another data communication having higher priority than providing the machine learning model such that the other data communication will block the link for the providing the machine learning model to the meta-training host; informing the meta-training host, in response to the request, that the link is required for the other data communication if the link is required for the other data communication.

    MACHINE-LEARNING AGENT PARAMETER INITIALIZATION IN WIRELESS COMMUNICATION NETWORK

    公开(公告)号:US20250031065A1

    公开(公告)日:2025-01-23

    申请号:US18710244

    申请日:2022-12-15

    Abstract: The present disclosure relates to a machine-learning (ML) orchestrator entity that provides distributed, flexible, and efficient parameter initialization for ML agents installed on network nodes operating under similar radio conditions. For this end, the ML orchestrator entity instructs two or more of the network nodes to run two or more ML agents in a training mode, which results in generating two or more sets of parameters. Then, the ML orchestrator entity uses the sets of parameters to derive a common set of parameters for the network nodes. The common set of parameters is to be used in an inference mode of the ML agent at each of the network nodes. The transmission of the common set of parameters to the network nodes may be subsequently initiated by the ML orchestrator entity itself or by each of the network nodes independently.

Patent Agency Ranking