Graph Neural Network Based Beamforming and RIS Reflection Design in A Multi-RIS Assisted Wireless Network

TL;DR

This paper introduces a graph neural network approach to optimize beamforming and RIS phase shifts in multi-RIS wireless networks, demonstrating scalability and superior performance over traditional methods.

Contribution

The paper presents a novel GNN architecture tailored for multi-RIS wireless networks, enabling efficient and scalable optimization of beamforming and RIS configurations.

Findings

GNN outperforms conventional algorithms in simulations.

The approach scales well with network size.

The method generalizes to different network settings.

Abstract

We propose a graph neural network (GNN) architecture to optimize base station (BS) beamforming and reconfigurable intelligent surface (RIS) phase shifts in a multi-RIS assisted wireless network. We create a bipartite graph model to represent a network with multi-RIS, then construct the GNN architecture by exploiting channel information as node and edge features. We employ a message passing mechanism to enable information exchange between RIS nodes and user nodes and facilitate the inference of interference. Each node also maintains a representation vector which can be mapped to the BS beamforming or RIS phase shifts output. Message generation and update of the representation vector at each node are performed using two unsupervised neural networks, which are trained off-line and then used on all nodes of the same type. Simulation results demonstrate that the proposed GNN architecture provides strong scalability with network size, generalizes to different settings, and significantly outperforms conventional algorithms.