Scalable Design for RIS-Assisted Multi-User Downlink System Empowered by RSMA under Partial CSI

2026-04-15

AI Summary

This work addresses the performance and scalability limitations of large-scale reconfigurable intelligent surface (RIS)-assisted communication systems, which stem from the infeasibility of acquiring full channel state information (CSI) and must rely instead on partial CSI. To overcome this challenge, the paper proposes an unsupervised learning-based rate-splitting multiple access (RSMA) scheme that jointly designs a neural network, termed RISnet, to efficiently infer full CSI from partial observations, and a low-complexity RSMA precoder for robust transmission. By dynamically expanding anchor points to construct effective channel features, the proposed method approaches the performance achievable with full CSI under deterministic ray-tracing channels and significantly mitigates performance degradation under increased channel uncertainty, thereby substantially enhancing system robustness and scalability.

Technology Category

• Intelligent Robots: Learning & Optimization for ROB
• Planning, Routing, and Scheduling: Planning/Scheduling and Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Large-scale security measurements

Abstract

In large-scale reconfigurable intelligent surface (RIS) communication systems, the precise acquisition of channel state information (CSI) is challenging. Consider a practical RIS configuration where only a few reflective elements serve as anchors to estimate CSI, which are termed partial CSI. To improve the robustness against partial CSI and the scalability of RIS networks, this paper proposes an unsupervised learning-based rate-splitting multiple access (RSMA) scheme for RIS-assisted multi-user systems. Specifically, RISnet, a neural network architecture designed to infer full CSI from partial observations, is employed and integrated with a low-complexity RSMA precoder. Effective channel features are constituted from partial CSI, and the original elements with channel information contribute to new anchors after expansion in RISnet. Numerical results demonstrate that the proposed scheme approximates the performance with a full CSI of RIS under deterministic raytracing channel conditions. When channel uncertainty increases during training, RSMA has been shown to enhance RISnet robustness, significantly mitigating performance loss.

Problem

• Reconfigurable Intelligent Surface
• Partial CSI
• Robustness
• Scalability
• Multi-User Downlink

Innovation

• RIS
• RSMA
• partial CSI
• unsupervised learning
• scalable design