Coordinated Multi-Armed Bandits for Improved Spatial Reuse in Wi-Fi

TL;DR

This paper proposes a multi-agent multi-armed bandit approach for coordinated optimization of spatial reuse in Wi-Fi, demonstrating significant improvements in throughput, fairness, and delay through simulation.

Contribution

It introduces a novel MA-MAB framework for Wi-Fi spatial reuse coordination, leveraging online learning for interference management and performance enhancement.

Findings

Mean throughput increased by 15%

Fairness improved with a 210% rise in minimum throughput

Maximum access delay remained below 3 ms

Abstract

Multi-Access Point Coordination (MAPC) and Artificial Intelligence and Machine Learning (AI/ML) are expected to be key features in future Wi-Fi, such as the forthcoming IEEE 802.11bn (Wi-Fi~8) and beyond. In this paper, we explore a coordinated solution based on online learning to drive the optimization of Spatial Reuse (SR), a method that allows multiple devices to perform simultaneous transmissions by controlling interference through Packet Detect (PD) adjustment and transmit power control. In particular, we focus on a Multi-Agent Multi-Armed Bandit (MA-MAB) setting, where multiple decision-making agents concurrently configure SR parameters from coexisting networks by leveraging the MAPC framework, and study various algorithms and reward-sharing mechanisms. We evaluate different MA-MAB implementations using Komondor, a well-adopted Wi-Fi simulator, and demonstrate that AI-native SR enabled by coordinated MABs can improve the network performance over current Wi-Fi operation: mean throughput increases by 15%, fairness is improved by increasing the minimum throughput across the network by 210%, while the maximum access delay is kept below 3 ms.