Graph Neural Network based scheduling : Improved throughput under a generalized interference model

TL;DR

This paper introduces a GCN-based scheduling algorithm for adhoc networks that enhances throughput under a generalized interference model without requiring labeled training data, outperforming traditional greedy methods.

Contribution

It presents a novel GCN-based scheduling method that improves throughput in adhoc networks under a generalized interference model without needing labeled data for training.

Findings

GCN approach improves greedy scheduling performance by 4-20%.

The method effectively handles the $k$-tolerant conflict graph model.

No labeled dataset required for training, using a custom loss function.

Abstract

In this work, we propose a Graph Convolutional Neural Networks (GCN) based scheduling algorithm for adhoc networks. In particular, we consider a generalized interference model called the $k$-tolerant conflict graph model and design an efficient approximation for the well-known Max-Weight scheduling algorithm. A notable feature of this work is that the proposed method do not require labelled data set (NP-hard to compute) for training the neural network. Instead, we design a loss function that utilises the existing greedy approaches and trains a GCN that improves the performance of greedy approaches. Our extensive numerical experiments illustrate that using our GCN approach, we can significantly ($4$-$20$ percent) improve the performance of the conventional greedy approach.