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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Hao, An, Jiancheng, Ng, Derrick Wing Kwan, Alexandropoulos, George C., Gan, Lu
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913234369380352
author Liu, Hao
An, Jiancheng
Ng, Derrick Wing Kwan
Alexandropoulos, George C.
Gan, Lu
author_facet Liu, Hao
An, Jiancheng
Ng, Derrick Wing Kwan
Alexandropoulos, George C.
Gan, Lu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_09006
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DRL-Based Orchestration of Multi-User MISO Systems with Stacked Intelligent Metasurfaces
Liu, Hao
An, Jiancheng
Ng, Derrick Wing Kwan
Alexandropoulos, George C.
Gan, Lu
Signal Processing
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.
title DRL-Based Orchestration of Multi-User MISO Systems with Stacked Intelligent Metasurfaces
topic Signal Processing
url https://arxiv.org/abs/2402.09006