Abstract
When a Wi-Fi device tries to connect to access points, it picks a channel, rate, and a particular access point (AP) out of a potentially large number of selections. Different selections result in different quality of user experiences, e.g., as measured by throughput and latency.
In many circumstances, the device has a past history of connecting to various access points in or near its current location. With user permission, this disclosure uses trained machinelearning models and the past history to select an optimal channel, rate, and access point. The selections made using this technique can result in superior throughput, latency, and can improve user experience.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Poichet, Jerome, "Wi-Fi Rate Selection Using Machine Learning Models", Technical Disclosure Commons, (July 05, 2018)
https://www.tdcommons.org/dpubs_series/1294