ALGORITHM TO PREDICT OPTIMAL WI-FI CONTENTION WINDOW BASED ON LOAD

    公开(公告)号:US20210037569A1

    公开(公告)日:2021-02-04

    申请号:US16945466

    申请日:2020-07-31

    Abstract: A novel method that dynamically changes the contention window of access points based on system load to improve performance in a dense Wi-Fi deployment is disclosed. A key feature is that no MAC protocol changes, nor client side modifications are needed to deploy the solution. Setting an optimal contention window can lead to throughput and latency improvements up to 155%, and 50%, respectively. Furthermore, an online learning method that efficiently finds the optimal contention window with minimal training data, and yields an average improvement in throughput of 53-55% during congested periods for a real traffic-volume workload replay in a Wi-Fi test-bed is demonstrated.

    METHODS FOR NETWORK MAINTENANCE
    3.
    发明申请

    公开(公告)号:US20190356532A1

    公开(公告)日:2019-11-21

    申请号:US16416016

    申请日:2019-05-17

    Abstract: Methods, systems, and devices for network maintenance are described. A controller may receive an indication that the performance of a network device has decreased. The indication may include case identification data associated with the network device. The controller may request proactive network maintenance (PNM) data associated with the network device based on receiving the case identification data. The controller may transmit the PNM data to a machine learning (ML) engine. The ML engine may transmit, to the controller, an indication of a predetermined operation predicted to improve the performance of the network device. The controller may transmit the predetermined operation to a client device based on receiving the indication of the predetermined operation. The ML engine may receive feedback indicating whether an execution of the predetermined operation improved the performance of the network device. The ML engine may a training data set based on the feedback.

Patent Agency Ranking