Meta-Learning for Resource Allocation in Uplink Multi-Active STAR-RIS-aided NOMA System

2024-01-13

AI Summary

This work addresses the uplink multi-active STAR-RIS-aided NOMA system, jointly optimizing active beamforming, power allocation, STAR-RIS transmission/reflection beam design, and user-RIS association to maximize the sum rate. Methodologically, we propose Meta-DDPG—a novel reinforcement learning algorithm that integrates meta-learning with deep deterministic policy gradient (DDPG) for the first time, significantly enhancing policy generalization across diverse channel realizations. Furthermore, we introduce a first-of-its-kind modeling and exploitation of second-order cascaded reflection paths among multiple STAR-RIS units, thereby improving coverage and channel reuse gain. Simulation results demonstrate that Meta-DDPG achieves a 19% higher sum rate than standard DDPG; incorporating second-order reflection boosts the sum data rate by 74.1%, substantially outperforming both first-order reflection and conventional RIS-based schemes.

Technology Category

• Search and Optimization: Metareasoning and Metaheuristics
• Multiagent Systems: Multiagent Learning
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) is a novel technology which enables the full-space coverage. In this letter, a multi-active STAR-RIS-aided system using non-orthogonal multiple access in an uplink transmission is considered, where the second-order reflections among multiple active STAR-RISs assist the transmission from the single-antenna users to the multi-antenna base station. Specifically, the total sum rate maximization problem is solved by jointly optimizing the active beamforming, power allocation, transmission and reflection beamforming at the active STAR-RISs, and user-active STAR-RIS assignment. To solve the non-convex optimization problem, a novel deep reinforcement learning algorithm is proposed which integrates Meta-learning and deep deterministic policy gradient (DDPG), denoted by Meta-DDPG. Numerical results reveal that our proposed Meta-DDPG algorithm outperforms the DDPG algorithm with $19%$ improvement, while second-order reflections among multi-active STAR-RISs provide $74.1%$ enhancement in the total data rate.

Problem

• STAR-RIS
• Optimization
• Wireless Communication

Innovation

• Meta-DDPG
• STAR-RIS
• Resource Allocation