Gradient-Based Meta Learning for Uplink RSMA with Beyond Diagonal RIS

TL;DR

This paper introduces a gradient-based meta learning algorithm for optimizing beyond diagonal RIS in uplink RSMA, effectively handling large-scale problems without pre-training, and achieving significant performance improvements.

Contribution

It presents the first joint optimization of BS beamforming, BD-RIS scattering matrix, and user power in uplink RSMA using meta learning, reducing complexity and improving rate performance.

Findings

Outperforms conventional RIS RSMA by 22.5% in sum rate.

Works without pre-training for large-scale optimization.

First to optimize joint parameters in uplink RSMA with BD-RIS.

Abstract

Beyond diagonal reconfigurable intelligent surface (BD-RIS) has emerged as an innovative and generalized RIS framework that provides greater flexibility in wave manipulation and enhanced coverage. In comparison to conventional RIS, optimization of BD-RIS is more challenging due to the large number of optimization variables associated with it. Typically, optimization of large-scale optimization problems utilizing traditional optimization methods results in high complexity. To tackle this issue, we propose a gradient-based meta learning algorithm which works without pre-training and is able to solve large-scale optimization problems. With the objective to maximize the sum rate of the system, to the best of our knowledge, this is the first work considering joint optimization of receiving beamforming vectors at the base station (BS), scattering matrix of BD-RIS and transmission power of users equipment (UEs) in uplink rate-splitting multiple access (RSMA) communication. Numerical results demonstrate that our proposed scheme can outperform the conventional RIS RSMA framework by 22.5$\%$.