IEEE 802.11bn Multi-AP Coordinated Spatial Reuse with Hierarchical Multi-Armed Bandits

2025-01-07

IEEE Communications Letters

AI Summary

In dense Wi-Fi 8 (IEEE 802.11bn) deployments, coordinated spatial reuse (C-SR) among multiple access points (APs) faces the challenge of dynamic group selection under time-varying interference. To address this, we propose a Hierarchical Multi-Armed Bandit (HMAB) framework—the first to introduce hierarchical reinforcement learning into C-SR control. Our approach features a lightweight Upper Confidence Bound (UCB)-based online learning mechanism that enables adaptive concurrent transmission scheduling while ensuring rapid convergence (40% faster), topology robustness, and long-term performance stability. Experiments across diverse, dynamically interfering topologies demonstrate significant gains in spectral efficiency and throughput. Crucially, the method sustains over 92% of optimal scheduling performance consistently, offering a scalable, low-overhead, distributed intelligent solution for C-SR in high-density wireless networks.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Online Learning & Bandits
• Intelligent Robots: Multi-Robot Systems

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Coordination among multiple access points (APs) is integral to IEEE 802.11bn (Wi-Fi 8) for managing contention in dense networks. This letter explores the benefits of Coordinated Spatial Reuse (C-SR) and proposes the use of reinforcement learning to optimize C-SR group selection. We develop a hierarchical multi-armed bandit (MAB) framework that efficiently selects APs for simultaneous transmissions across various network topologies, demonstrating reinforcement learning's promise in Wi-Fi settings. Among several MAB algorithms studied, we identify the upper confidence bound (UCB) as particularly effective, offering rapid convergence, adaptability to changes, and sustained performance.

Problem

• IEEE 802.11bn
• Channel Spatial Reuse
• Wireless Network Efficiency

Innovation

• Reinforcement Learning
• Multi-Armed Bandit (MAB) Algorithm
• Spatial Reuse Optimization