知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

24 records (took 0.023 seconds)

    ADJUSTING DISCONTINUOUS RECEPTION BEHAVIOR OF A USER EQUIPMENT TO CONSERVE ENERGY USE
    2.
    发明公开
    ADJUSTING DISCONTINUOUS RECEPTION BEHAVIOR OF A USER EQUIPMENT TO CONSERVE ENERGY USE 审中-公开

    公开(公告)号：US20230171694A1

    公开(公告)日：2023-06-01

    申请号：US18100883

    申请日：2023-01-24

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Xenofon FOUKAS ,  Bozidar RADUNOVIC ,  Yongguang ZHANG ,  Landon Prentice COX

    IPC: H04W52/02 ,  H04W76/28

    CPC classification number: H04W52/0216 ,  H04W76/28 ,  H04W52/0235

    Abstract: A method for adjusting discontinuous reception (DRX) behavior of a user equipment (UE) to conserve energy use includes exposing a DRX application programming interface (API) that enables DRX parameters to be changed and defining a conflict resolution policy that controls when requests to change the DRX parameters should be granted. The method also includes receiving, via the DRX API, a request from an application to change a DRX parameter for the UE. The UE is in wireless communication with a base station, and the application is configured to send data to the UE via a mobile network that comprises the base station. The method also includes determining, based at least in part on the conflict resolution policy, that the request should be granted and sending a command to the base station that causes the base station to communicate a new value of the DRX parameter to the UE.

    HIERARCHICAL SCHEDULING FOR RADIO ACCESS NETWORK
    3.
    发明申请
    HIERARCHICAL SCHEDULING FOR RADIO ACCESS NETWORK 有权

    公开(公告)号：US20220386302A1

    公开(公告)日：2022-12-01

    申请号：US17333158

    申请日：2021-05-28

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Bozidar RADUNOVIC ,  Xenofon FOUKAS ,  Manikanta KOTARU ,  Anuj KALIA

    IPC: H04W72/04 ,  H04W72/12 ,  G06N20/00

    Abstract: Aspects of the present disclosure relate to allocating RAN resources among RAN slices according to reinforcement learning techniques. For example, a network slice controller (NSC) may generate a RAN resource allocation and associated expected slice characteristics may be determined for each slice based on the RAN resource allocation. Resources of the RAN may be allocated accordingly, such that resulting actual slice characteristics may be observed and compared to the expected slice characteristics. A reward may be generated for the resource allocation, for example based on a difference between the expected and observed slice characteristics. RAN resource allocation and slice characteristic forecasting may be adapted according to such rewards. As a result, RAN resource allocation generation may improve, even in instances with changing or unknown network conditions. Thus, even when a local scheduler exhibits unknown behavior, differences between expected and observed slice characteristics may be used to tune resource allocation accordingly.

    FRAMEWORK FOR ML-BASED ANALYTICS AND OPTIMIZATIONS FOR RADIO ACCESS NETWORKS
    4.
    发明申请
    FRAMEWORK FOR ML-BASED ANALYTICS AND OPTIMIZATIONS FOR RADIO ACCESS NETWORKS 有权

    公开(公告)号：US20240422576A1

    公开(公告)日：2024-12-19

    申请号：US18334164

    申请日：2023-06-13

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Daehyeok KIM ,  Ganesh ANANTHANARAYANAN ,  Bozidar RADUNOVIC ,  Xenofon FOUKAS

    IPC: H04W24/02

    Abstract: A system, method, and computer-readable media for executing applications for radio interface controller (RIC) management are disclosed. The system includes one or more far-edge datacenters including first computing resources configured to execute a radio access network (RAN) function and a real-time RIC; one or more near-edge datacenters including second computing resources configured to execute a core network function and at least one of a near-real-time RIC or a non-real-time RIC; and a central controller. The central controller is configured to: receive inputs of application requirements, hardware constraints, and a capacity of the first and the second computing resources; select, based on a policy applied to the inputs, a location a far-edge datacenter or a near-edge datacenters for executing each of a plurality of applications to form a pipeline; and deploy each of the applications to the real-time RIC, the near-real-time RIC, or the non-real-time RIC based on the selected location.

    INFERENCE WITH INLINE REAL-TIME ML MODELS IN APPLICATIONS
    8.
    发明公开
    INFERENCE WITH INLINE REAL-TIME ML MODELS IN APPLICATIONS 审中-公开

    公开(公告)号：US20230421459A1

    公开(公告)日：2023-12-28

    申请号：US18462178

    申请日：2023-09-06

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Xenofon FOUKAS ,  Bozidar RADUNOVIC

    IPC: H04L41/16 ,  G06N3/10

    CPC classification number: H04L41/16 ,  G06N3/10

    Abstract: Described are examples for using codelets executing within applications to use machine-learning (ML) models to infer a result based on application data. The codelets may be dynamically loaded into the applications during execution. A controller verifies, based on extended Berkeley packet filter (eBPF) bytecode of the codelet, that the codelet satisfies safety requirements for execution within the application. A computing device executing the application loads the verified codelet into a library of the application. The application executes the verified codelet to apply application data to the machine-learning model to infer a result. The ML model may be implemented by the eBPF code of the codelet or the codelet may include a call to a machine-learning model of a type supported by a controller of the application and a map for a serial representation of the machine-learning model. The computing device may reconstruct the ML model based on the serial representation.

Patent Agency Ranking