DRL-Based Orchestration of Multi-User MISO Systems with Stacked Intelligent Metasurfaces

TL;DR

This paper introduces a deep reinforcement learning-based method to optimize stacked intelligent metasurfaces for enhancing multi-user MISO wireless systems, demonstrating improved performance over traditional schemes under low power conditions.

Contribution

It presents a novel joint design approach for SIM phase shifts and power allocation using DRL, advancing over existing methods with a customizable, environment-aware optimization.

Findings

Outperforms conventional precoding schemes at low transmit power

Effectively learns from the wireless environment in real-time

Enhances robustness with a whitening process

Abstract

Stacked intelligent metasurfaces (SIM) represents an advanced signal processing paradigm that enables over-the-air processing of electromagnetic waves at the speed of light. Its multi-layer structure exhibits customizable increased computational capability compared to conventional single-layer reconfigurable intelligent surfaces and metasurface lenses. In this paper, we deploy SIM to improve the performance of multi-user multiple-input single-output (MISO) wireless systems with low complexity transmit radio frequency (RF) chains. In particular, an optimization formulation for the joint design of the SIM phase shifts and the transmit power allocation is presented, which is efficiently solved via a customized deep reinforcement learning (DRL) approach that continuously observes pre-designed states of the SIM-parametrized smart wireless environment. The presented performance evaluation results showcase the proposed method's capability to effectively learn from the wireless environment while outperforming conventional precoding schemes under low transmit power conditions. Finally, a whitening process is presented to further augment the robustness of the proposed scheme.