Scalable Power Control/Beamforming in Heterogeneous Wireless Networks with Graph Neural Networks

TL;DR

This paper introduces HIGNN, a scalable graph neural network framework for power control and beamforming in heterogeneous wireless networks, demonstrating high efficiency and robust performance on large networks.

Contribution

The paper presents a novel unsupervised GNN-based framework, HIGNN, that effectively handles heterogeneity and scalability in wireless resource allocation.

Findings

HIGNN outperforms existing benchmarks in efficiency and performance.

HIGNN maintains robustness when trained on small networks and applied to larger ones.

Numerical results confirm HIGNN's superior resource allocation capabilities.

Abstract

Machine learning (ML) has been widely used for efficient resource allocation (RA) in wireless networks. Although superb performance is achieved on small and simple networks, most existing ML-based approaches are confronted with difficulties when heterogeneity occurs and network size expands. In this paper, specifically focusing on power control/beamforming (PC/BF) in heterogeneous device-to-device (D2D) networks, we propose a novel unsupervised learning-based framework named heterogeneous interference graph neural network (HIGNN) to handle these challenges. First, we characterize diversified link features and interference relations with heterogeneous graphs. Then, HIGNN is proposed to empower each link to obtain its individual transmission scheme after limited information exchange with neighboring links. It is noteworthy that HIGNN is scalable to wireless networks of growing sizes with robust performance after trained on small-sized networks. Numerical results show that compared with state-of-the-art benchmarks, HIGNN achieves much higher execution efficiency while providing strong performance.