INSPIRE: Distributed Bayesian Optimization for ImproviNg SPatIal REuse in Dense WLANs

Abstract

WLANs, which have overtaken wired networks to become the primary means of connecting devices to the Internet, are prone to performance issues due to the scarcity of space in the radio spectrum. As a response, IEEE 802.11ax and subsequent amendments aim at increasing the spatial reuse of a radio channel by allowing the dynamic update of two key parameters in wireless transmission: the transmission power (TX POWER) and the sensitivity threshold (OBSS PD).In this paper, we present INSPIRE, a distributed solution performing local Bayesian optimizations based on Gaussian processes to improve the spatial reuse in WLANs. INSPIRE makes no explicit assumptions about the topology of WLANs and favors altruistic behaviors of the access points, leading them to find adequate configurations of their TX POWER and OBSS PD parameters for the "greater good" of the WLANs. We demonstrate the superiority of INSPIRE over other state-of-theart strategies using the ns-3 simulator and two examples inspired by real-life deployments of dense WLANs. Our results show that, in only a few seconds, INSPIRE is able to drastically increase the quality of service of operational WLANs by improving their fairness and throughput.

Cooperate or Not Cooperate: Transfer Learning With Multi-Armed Bandit for Spatial Reuse in Wi-Fi

“…More specifically, to cope with the large action space that consists of TP and Overlapping BSS/Preamble-Detection (OBSS/PD) thresholds, the authors utilize a MAB variant, namely the Infinitely Many-Armed Bandit (IMAB). Furthermore, a distributed solution based on Bayesian optimizations of Gaussian processes to improve spatial reuse is proposed in [18].…”