Delay-aware Backpressure Routing Using Graph Neural Networks

TL;DR

This paper introduces a delay-aware backpressure routing method that employs graph neural networks to learn biases based on link duty cycles, significantly improving delay performance in wireless multi-hop networks.

Contribution

It presents a novel GNN-based bias learning approach for backpressure routing, enhancing delay performance while maintaining low complexity and adaptability.

Findings

Improves delay performance over classical BP and existing bias-based BP methods.

Uses GNN to predict link duty cycle biases, adapting to interference density.

Maintains low computational overhead with only a one-time distributed implementation cost.

Abstract

We propose a throughput-optimal biased backpressure (BP) algorithm for routing, where the bias is learned through a graph neural network that seeks to minimize end-to-end delay. Classical BP routing provides a simple yet powerful distributed solution for resource allocation in wireless multi-hop networks but has poor delay performance. A low-cost approach to improve this delay performance is to favor shorter paths by incorporating pre-defined biases in the BP computation, such as a bias based on the shortest path (hop) distance to the destination. In this work, we improve upon the widely-used metric of hop distance (and its variants) for the shortest path bias by introducing a bias based on the link duty cycle, which we predict using a graph convolutional neural network. Numerical results show that our approach can improve the delay performance compared to classical BP and existing BP alternatives based on pre-defined bias while being adaptive to interference density. In terms of complexity, our distributed implementation only introduces a one-time overhead (linear in the number of devices in the network) compared to classical BP, and a constant overhead compared to the lowest-complexity existing bias-based BP algorithms.