Distributed machine learning in an information centric network

    公开(公告)号:US11868858B2

    公开(公告)日:2024-01-09

    申请号:US17892713

    申请日:2022-08-22

    申请人: Intel Corporation

    IPC分类号: G06N20/00 H04L67/00

    CPC分类号: G06N20/00 H04L67/34

    摘要: Systems and techniques for distributed machine learning (DML) in an information centric network (ICN) are described herein. Finite message exchanges, such as those used in many DML exercises, may be efficiently implemented by treating certain data packets as interest packets to reduce overall network overhead when performing the finite message exchange. Further, network efficiency in DML may be improved achieved by using local coordinating nodes to manage devices participating in a distributed machine learning exercise. Additionally, modifying a round of DML training to accommodate available participant devices, such as by using a group quality of service metric to select the devices, or extending the round execution parameters to include additional devices, may have an impact on DML performance.

    Distributed machine learning in an information centric network

    公开(公告)号:US11423332B2

    公开(公告)日:2022-08-23

    申请号:US16586593

    申请日:2019-09-27

    申请人: Intel Corporation

    IPC分类号: G06N20/00 H04L67/00

    摘要: Systems and techniques for distributed machine learning (DML) in an information centric network (ICN) are described herein. Finite message exchanges, such as those used in many DML exercises, may be efficiently implemented by treating certain data packets as interest packets to reduce overall network overhead when performing the finite message exchange. Further, network efficiency in DML may be improved achieved by using local coordinating nodes to manage devices participating in a distributed machine learning exercise. Additionally, modifying a round of DML training to accommodate available participant devices, such as by using a group quality of service metric to select the devices, or extending the round execution parameters to include additional devices, may have an impact on DML performance.

    Radio resource control messaging for dual connectivity networks

    公开(公告)号:US10231149B2

    公开(公告)日:2019-03-12

    申请号:US15437249

    申请日:2017-02-20

    申请人: Intel Corporation

    摘要: A 3GPP LTE protocol enhancement may realize the full benefit of dual connectivity in Long Term Evolution (LTE) networks by providing a mechanism to carry Radio Resource Control (RRC) messages and/or Information Elements (IE)s from a Secondary Evolved Node B (SeNB) to User Equipment (UE) via Master Evolved Node B (MeNB) RRC messages. Novel downlink (DL) Common Control Channel (CCCH) and Dedicated Control Channel (DCCH) messages, and augmented messages having Information Elements (IE)s for relaying RRC messages from a SeNB to a UE via a MeNB, are defined. Modifications to ASN.1 program coding of LTE 3rd Generation Partnership Project specifications to enable RRC messages from the MeNB to relay RRC information from the SeNB to the UE are provided. In one embodiment, the UE receives, from a MeNB, an RRC message comprising information relayed from a SeNB and interprets the RRC message for control channel and radio resource configuration information from the SeNB.