Graph Neural Networks for Power Allocation in Wireless Networks with Full Duplex Nodes
This addresses power allocation for wireless networks with full-duplex nodes, offering improved efficiency and trade-offs, but it is incremental as it builds on existing GNN approaches.
The paper tackles the non-convex power allocation problem in wireless networks with full-duplex nodes by proposing a novel graph representation and a corresponding F-GNN to maximize throughput, achieving state-of-the-art performance with significantly reduced computation time and a 20% training time reduction using a distance-based threshold.
Due to mutual interference between users, power allocation problems in wireless networks are often non-convex and computationally challenging. Graph neural networks (GNNs) have recently emerged as a promising approach to tackling these problems and an approach that exploits the underlying topology of wireless networks. In this paper, we propose a novel graph representation method for wireless networks that include full-duplex (FD) nodes. We then design a corresponding FD Graph Neural Network (F-GNN) with the aim of allocating transmit powers to maximise the network throughput. Our results show that our F-GNN achieves state-of-art performance with significantly less computation time. Besides, F-GNN offers an excellent trade-off between performance and complexity compared to classical approaches. We further refine this trade-off by introducing a distance-based threshold for inclusion or exclusion of edges in the network. We show that an appropriately chosen threshold reduces required training time by roughly 20% with a relatively minor loss in performance.