Deep Reinforcement Learning Powered IRS-Assisted Downlink NOMA

TL;DR

This paper explores using deep reinforcement learning to optimize IRS-assisted downlink NOMA systems, significantly improving sum rates and handling complex non-convex optimization challenges in wireless communications.

Contribution

It introduces a DRL-based method for tuning IRS phase shifts in NOMA, demonstrating superior performance over traditional OMA schemes and analyzing the impact of SIC imperfections.

Findings

DRL-based IRS tuning achieves higher sum rates than OMA.

Increasing transmit power enables serving more users.

Imperfect SIC significantly reduces user data rates.

Abstract

In this work, we examine an intelligent reflecting surface (IRS) assisted downlink non-orthogonal multiple access (NOMA) scenario with the aim of maximizing the sum rate of users. The optimization problem at the IRS is quite complicated, and non-convex, since it requires the tuning of the phase shift reflection matrix. Driven by the rising deployment of deep reinforcement learning (DRL) techniques that are capable of coping with solving non-convex optimization problems, we employ DRL to predict and optimally tune the IRS phase shift matrices. Simulation results reveal that IRS assisted NOMA based on our utilized DRL scheme achieves high sum rate compared to OMA based one, and as the transmit power increases, the capability of serving more users increases. Furthermore, results show that imperfect successive interference cancellation (SIC) has a deleterious impact on the data rate of users performing SIC. As the imperfection increases by ten times, the rate decreases by more than 10%.