Meta-learning for RIS-assisted NOMA Networks

TL;DR

This paper introduces a RIS-assisted NOMA network framework that uses a meta-learning algorithm for joint optimization, significantly improving throughput over traditional methods and demonstrating the benefits of RIS integration.

Contribution

It presents a novel RIS-based transmission framework with a QoS-based clustering scheme and a MAML-based optimization algorithm for NOMA networks.

Findings

Higher transmission throughput compared to OMA networks.

Substantial throughput gains from RIS integration.

Effective QoS-based clustering improves performance.

Abstract

A novel reconfigurable intelligent surfaces (RISs)-based transmission framework is proposed for downlink non-orthogonal multiple access (NOMA) networks. We propose a quality-of-service (QoS)-based clustering scheme to improve the resource efficiency and formulate a sum rate maximization problem by jointly optimizing the phase shift of the RIS and the power allocation at the base station (BS). A model-agnostic meta-learning (MAML)-based learning algorithm is proposed to solve the joint optimization problem with a fast convergence rate and low model complexity. Extensive simulation results demonstrate that the proposed QoS-based NOMA network achieves significantly higher transmission throughput compared to the conventional orthogonal multiple access (OMA) network. It can also be observed that substantial throughput gain can be achieved by integrating RISs in NOMA and OMA networks. Moreover, simulation results of the proposed QoS-based clustering method demonstrate observable throughput gain against the conventional channel condition-based schemes.