Decentralized Channel Management in WLANs with Graph Neural Networks

TL;DR

This paper introduces a decentralized, learning-based channel allocation method for WLANs using graph neural networks, optimizing interference management in large, dynamic networks.

Contribution

It proposes a novel GNN-based, model-free, decentralized approach for WLAN channel management, ensuring scalability and permutation invariance.

Findings

Effective interference reduction demonstrated in simulations

Scalable solution suitable for large WLANs

Theoretical analysis confirms permutation equivariance

Abstract

Wireless local area networks (WLANs) manage multiple access points (APs) and assign scarce radio frequency resources to APs for satisfying traffic demands of associated user devices. This paper considers the channel allocation problem in WLANs that minimizes the mutual interference among APs, and puts forth a learning-based solution that can be implemented in a decentralized manner. We formulate the channel allocation problem as an unsupervised learning problem, parameterize the control policy of radio channels with graph neural networks (GNNs), and train GNNs with the policy gradient method in a model-free manner. The proposed approach allows for a decentralized implementation due to the distributed nature of GNNs and is equivariant to network permutations. The former provides an efficient and scalable solution for large network scenarios, and the latter renders our algorithm independent of the AP reordering. Empirical results are presented to evaluate the proposed approach and corroborate theoretical findings.