Graph Neural Network based Active and Passive Beamforming for Distributed STAR-RIS-Assisted Multi-User MISO Systems

2024-05-03

arXiv.org

AI Summary

This work addresses the joint optimization of active beamforming at the base station and passive transmission/reflection phase shifts at a distributed STAR-RIS in a multi-user MISO system, aiming to maximize the sum rate under transmit power constraints. The problem is highly non-convex due to strong coupling between active and passive variables, rendering conventional iterative methods computationally expensive and poorly generalizable. To overcome these limitations, we propose the first heterogeneous graph neural network (HGNN) framework that explicitly models channel and RIS structural dependencies, enabling end-to-end joint beamforming design compatible with energy-splitting (ES) STAR-RIS. Our method achieves up to 18.7% sum-rate gain across diverse system scales. Crucially, the trained model supports zero-shot adaptation to unseen numbers of users and RIS elements, significantly enhancing scalability and generalizability—key bottlenecks in prior approaches.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

This paper investigates a joint active and passive beamforming design for distributed simultaneous transmitting and reflecting (STAR) reconfigurable intelligent surface (RIS) assisted multi-user (MU)- mutiple input single output (MISO) systems, where the energy splitting (ES) mode is considered for the STAR-RIS. We aim to design the active beamforming vectors at the base station (BS) and the passive beamforming at the STAR-RIS to maximize the user sum rate under transmitting power constraints. The formulated problem is non-convex and nontrivial to obtain the global optimum due to the coupling between active beamforming vectors and STAR-RIS phase shifts. To efficiently solve the problem, we propose a novel graph neural network (GNN)-based framework. Specifically, we first model the interactions among users and network entities are using a heterogeneous graph representation. A heterogeneous graph neural network (HGNN) implementation is then introduced to directly optimizes beamforming vectors and STAR-RIS coefficients with the system objective. Numerical results show that the proposed approach yields efficient performance compared to the previous benchmarks. Furthermore, the proposed GNN is scalable with various system configurations.

Problem

• Maximize user sum rate in MU-MISO systems
• Design joint active and passive beamforming
• Optimize STAR-RIS with GNN-based framework

Innovation

• Graph Neural Network framework
• Heterogeneous graph representation
• Optimizes beamforming and STAR-RIS