Joint SIM Configuration and Power Allocation for Stacked Intelligent Metasurface-assisted MU-MISO Systems with TD3

TL;DR

This paper introduces a joint optimization approach using TD3 for SIM-assisted MU-MISO systems, enhancing sum rate performance by optimizing phase shifts and power allocation, with insights on SIM structure effects.

Contribution

It proposes a novel joint optimization method based on TD3 for SIM-assisted MU-MISO systems, outperforming existing algorithms and analyzing SIM structural impacts.

Findings

TD3-based joint optimization outperforms DDPG and AO algorithms.

Increasing meta-atoms per layer improves performance.

Adding more SIM layers does not always enhance performance.

Abstract

The stacked intelligent metasurface (SIM) emerges as an innovative technology with the ability to directly manipulate electromagnetic (EM) wave signals, drawing parallels to the operational principles of artificial neural networks (ANN). Leveraging its structure for direct EM signal processing alongside its low-power consumption, SIM holds promise for enhancing system performance within wireless communication systems. In this paper, we focus on SIM-assisted multi-user multi-input and single-output (MU-MISO) system downlink scenarios in the transmitter. We proposed a joint optimization method for SIM phase shift configuration and antenna power allocation based on the twin delayed deep deterministic policy gradient (TD3) algorithm to efficiently improve the sum rate. The results show that the proposed algorithm outperforms both deep deterministic policy gradient (DDPG) and alternating optimization (AO) algorithms. Furthermore, increasing the number of meta-atoms per layer of the SIM is always beneficial. However, continuously increasing the number of layers of SIM does not lead to sustained performance improvement.