Patent · US Active

Wireless MAC mode selection using machine learning

US10674440B2 · kind B2 · utility

3Cited by
0References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 25, 2018
Grant dateJun 2, 2020
Priority date
Expiry dateJul 25, 2038

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH04W88/08
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

In one embodiment, a network monitoring service trains, using a training dataset from one or more wireless networks, a machine learning model to output an optimized set of media access control (MAC) mode parameters for a wireless access point given an input set of network characteristics. The service receives a plurality of network characteristics associated with a particular wireless access point in a particular wireless network. The service determines, using the received network characteristics as input to the machine learning-based model, a set of MAC mode parameters for the particular wireless access point. The service controls the particular wireless access point to communicate with one or more clients in the particular wireless network based on the determined set of MAC mode parameters.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.