Delay-Oriented Distributed Scheduling Using Graph Neural Networks

TL;DR

This paper introduces a delay-oriented distributed scheduling method for wireless multi-hop networks using graph convolutional networks, improving delay performance over traditional myopic algorithms by considering network backlog dependencies.

Contribution

It proposes a novel GCN-based distributed scheduler that captures network topology and backlog lookahead, outperforming existing greedy and MWIS-based schedulers in delay-sensitive scenarios.

Findings

Outperforms traditional myopic schedulers in delay metrics

Generalizes well across different network topologies

Maintains low communication complexity

Abstract

In wireless multi-hop networks, delay is an important metric for many applications. However, the max-weight scheduling algorithms in the literature typically focus on instantaneous optimality, in which the schedule is selected by solving a maximum weighted independent set (MWIS) problem on the interference graph at each time slot. These myopic policies perform poorly in delay-oriented scheduling, in which the dependency between the current backlogs of the network and the schedule of the previous time slot needs to be considered. To address this issue, we propose a delay-oriented distributed scheduler based on graph convolutional networks (GCNs). In a nutshell, a trainable GCN module generates node embeddings that capture the network topology as well as multi-step lookahead backlogs, before calling a distributed greedy MWIS solver. In small- to medium-sized wireless networks with heterogeneous transmit power, where a few central links have many interfering neighbors, our proposed distributed scheduler can outperform the myopic schedulers based on greedy and instantaneously optimal MWIS solvers, with good generalizability across graph models and minimal increase in communication complexity.