Adaptive Passive Beamforming in RIS-Aided Communications with Q-Learning

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Reconfigurable Intelligent Surfaces (RIS) appear as a promising solution to combat wireless channel fading and interferences. However, the elements of the RIS need to be properly oriented to boost the data transmission rate. In this work, we propose a new strategy to adaptively configure the RIS without Channel State Information (CSI). Our goal is to minimize the number of RIS configurations to be tested to find the optimal one. We formulate the problem as a stochastic shortest path problem, and use Q-Learning to solve it.

Original languageEnglish
Title of host publication2025 IEEE Wireless Communications and Networking Conference, WCNC 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350368369
DOIs
Publication statusPublished - 1 Jan 2025
Event2025 IEEE Wireless Communications and Networking Conference, WCNC 2025 - Milan, Italy
Duration: 24 Mar 202527 Mar 2025

Publication series

NameIEEE Wireless Communications and Networking Conference, WCNC
ISSN (Print)1525-3511

Conference

Conference2025 IEEE Wireless Communications and Networking Conference, WCNC 2025
Country/TerritoryItaly
CityMilan
Period24/03/2527/03/25

Keywords

  • Bayesian Inference
  • Q Learning
  • Reconfigurable Intelligent Surfaces (RIS)

Fingerprint

Dive into the research topics of 'Adaptive Passive Beamforming in RIS-Aided Communications with Q-Learning'. Together they form a unique fingerprint.

Cite this