Joint Active RIS Configuration and User Power Control for Localization: A Neuroevolution-Based Approach

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Stamatelis, George, Chen, Hui, Wymeersch, Henk, Alexandropoulos, George C.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914095969599488
author Stamatelis, George
Chen, Hui
Wymeersch, Henk
Alexandropoulos, George C.
author_facet Stamatelis, George
Chen, Hui
Wymeersch, Henk
Alexandropoulos, George C.
contents This paper studies user localization aided by a Reconfigurable Intelligent Surface (RIS). A feedback link from the Base Station (BS) to the user is adopted to enable dynamic power control of the user pilot transmissions in the uplink. A novel multi-agent algorithm for the joint control of the RIS phase configuration and the user transmit power is presented, which is based on a hybrid approach integrating NeuroEvolution (NE) and supervised learning. The proposed scheme requires only single-bit feedback messages for the uplink power control, supports RIS elements with discrete responses, and is numerically shown to outperform fingerprinting, deep reinforcement learning baselines and backpropagation-based position estimators.
format Preprint
id arxiv_https___arxiv_org_abs_2510_13819
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Joint Active RIS Configuration and User Power Control for Localization: A Neuroevolution-Based Approach
Stamatelis, George
Chen, Hui
Wymeersch, Henk
Alexandropoulos, George C.
Networking and Internet Architecture
Machine Learning
Multiagent Systems
This paper studies user localization aided by a Reconfigurable Intelligent Surface (RIS). A feedback link from the Base Station (BS) to the user is adopted to enable dynamic power control of the user pilot transmissions in the uplink. A novel multi-agent algorithm for the joint control of the RIS phase configuration and the user transmit power is presented, which is based on a hybrid approach integrating NeuroEvolution (NE) and supervised learning. The proposed scheme requires only single-bit feedback messages for the uplink power control, supports RIS elements with discrete responses, and is numerically shown to outperform fingerprinting, deep reinforcement learning baselines and backpropagation-based position estimators.
title Joint Active RIS Configuration and User Power Control for Localization: A Neuroevolution-Based Approach
topic Networking and Internet Architecture
Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2510.13819