GRLinQ: An Intelligent Spectrum Sharing Mechanism for Device-to-Device Communications with Graph Reinforcement Learning

TL;DR

GRLinQ introduces a hybrid graph reinforcement learning approach for spectrum sharing in D2D communications, achieving superior, scalable, and explainable link scheduling and power control with less CSI dependence.

Contribution

It presents a novel hybrid model/data-driven spectrum sharing mechanism that integrates information theory with graph reinforcement learning for improved D2D link scheduling.

Findings

Outperforms existing methods in spectrum sharing tasks.

Requires less channel state information and training data.

Offers scalable and generalizable solutions across network scenarios.

Abstract

Device-to-device (D2D) spectrum sharing in wireless communications is a challenging non-convex combinatorial optimization problem, involving entangled link scheduling and power control in a large-scale network. The state-of-the-art methods, either from a model-based or a data-driven perspective, exhibit certain limitations such as the critical need for channel state information (CSI) and/or a large number of (solved) instances (e.g., network layouts) as training samples. To advance this line of research, we propose a novel hybrid model/datadriven spectrum sharing mechanism with graph reinforcement learning for link scheduling (GRLinQ), injecting information theoretical insights into machine learning models, in such a way that link scheduling and power control can be solved in an intelligent yet explainable manner. Through an extensive set of experiments, GRLinQ demonstrates superior performance to the existing model-based and data-driven link scheduling and/or power control methods, with a relaxed requirement for CSI, a substantially reduced number of unsolved instances as training samples, a possible distributed deployment, reduced online/offline computational complexity, and more remarkably excellent scalability and generalizability over different network scenarios and system configurations.