公开(公告)号：US20230388807A1

公开(公告)日：2023-11-30

申请号：US18222992

申请日：2023-07-17

Applicant: CABLE TELEVISION LABORATORIES, INC.

Inventor： THOMAS SANDHOLM ,  BERNARDO HUBERMAN ,  SAYANDEV MUKHERJEE ,  LUIS ALBERTO CAMPOS

IPC: H04W16/14 ,  H04W16/10 ,  H04L41/16 ,  H04W28/24 ,  H04W24/02 ,  H04W28/20

CPC classification number: H04W16/14 ,  H04W16/10 ,  H04L41/16 ,  H04W28/24 ,  H04W24/02 ,  H04W28/20

Abstract: An artificial intelligence network operator (aiNO) that autonomously and dynamically acquires network resources on an open marketplace includes software running a machine learning model and a processor that controls backhaul connectivity and a network communication component. In some embodiments, the aiNO facilitates resale of the acquired network resource to end users.

公开(公告)号：US20210037569A1

公开(公告)日：2021-02-04

申请号：US16945466

申请日：2020-07-31

Applicant: CABLE TELEVISION LABORATORIES, INC.

Inventor： THOMAS SANDHOLM ,  BELAL HAMZEH ,  BERNARDO HUBERMAN

IPC: H04W74/08 ,  H04W28/02 ,  H04L12/863 ,  H04W24/08

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.