Wireless Link Scheduling with State-Augmented Graph Neural Networks

TL;DR

This paper introduces a novel GNN-based approach for optimal link scheduling in large-scale wireless networks, incorporating state augmentation to ensure fairness and improve long-term performance.

Contribution

It proposes a state-augmented graph neural network framework for constrained link scheduling, addressing long-term performance and fairness in wireless ad hoc networks.

Findings

The proposed method outperforms baseline algorithms in simulations.

State augmentation improves the adaptability of scheduling policies.

The approach effectively balances performance and fairness constraints.

Abstract

We consider the problem of optimal link scheduling in large-scale wireless ad hoc networks. We specifically aim for the maximum long-term average performance, subject to a minimum transmission requirement for each link to ensure fairness. With a graph structure utilized to represent the conflicts of links, we formulate a constrained optimization problem to learn the scheduling policy, which is parameterized with a graph neural network (GNN). To address the challenge of long-term performance, we use the state-augmentation technique. In particular, by augmenting the Lagrangian dual variables as dynamic inputs to the scheduling policy, the GNN can be trained to gradually adapt the scheduling decisions to achieve the minimum transmission requirements. We verify the efficacy of our proposed policy through numerical simulations and compare its performance with several baselines in various network settings.