Scalable Power Control/Beamforming in Heterogeneous Wireless Networks with Graph Neural Networks
This addresses resource allocation problems in wireless networks, particularly for heterogeneous and large-scale scenarios, representing an incremental improvement.
The paper tackles the challenge of scalable power control and beamforming in heterogeneous wireless networks by proposing HIGNN, a graph neural network framework, which achieves higher execution efficiency compared to state-of-the-art benchmarks.
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.