Distributed Link Sparsification for Scalable Scheduling Using Graph Neural Networks

TL;DR

This paper introduces a distributed link sparsification method using graph convolutional networks to reduce scheduling overhead in dense wireless networks while maintaining most of the network capacity.

Contribution

It presents a novel GCN-based distributed scheme for link sparsification that significantly reduces overhead with minimal capacity loss compared to classical methods.

Findings

Retains nearly 70% of network capacity

Uses only 0.4% of message complexity of classical methods

Reduces average interfering neighbors to 2.6%

Abstract

Distributed scheduling algorithms for throughput or utility maximization in dense wireless multi-hop networks can have overwhelmingly high overhead, causing increased congestion, energy consumption, radio footprint, and security vulnerability. For wireless networks with dense connectivity, we propose a distributed scheme for link sparsification with graph convolutional networks (GCNs), which can reduce the scheduling overhead while keeping most of the network capacity. In a nutshell, a trainable GCN module generates node embeddings as topology-aware and reusable parameters for a local decision mechanism, based on which a link can withdraw itself from the scheduling contention if it is not likely to win. In medium-sized wireless networks, our proposed sparse scheduler beats classical threshold-based sparsification policies by retaining almost $70\%$ of the total capacity achieved by a distributed greedy max-weight scheduler with $0.4\%$ of the point-to-point message complexity and $2.6\%$ of the average number of interfering neighbors per link.