Intelligent Reflecting Surface Optimization for MIMO Communication Using Deep Reinforcement Learning

Kenneth Ikeagu; Yuan Ding; Chaoyun Song; Muhammad Khandaker

doi:10.1109/telfor59449.2023.10372753

Intelligent Reflecting Surface Optimization for MIMO Communication Using Deep Reinforcement Learning

Kenneth Ikeagu^*, Yuan Ding, Chaoyun Song, Muhammad Khandaker

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

82 Downloads (Pure)

Abstract

This paper focuses on the optimization of the phase shifts of an intelligent reflecting surface (IRS) for an IRS-aided multiple input multiple output (MIMO) communication system. Motivated by the massive success of deep reinforcement learning (DRL) algorithms in handling high-dimensional continuous action spaces and tackling non-convex optimization problems, we propose a deep deterministic policy gradient (DDPG) framework for solving the formulated non-convex optimization problem. Numerical simulations demonstrate the robustness and efficiency of the proposed model in terms of spectral efficiency and algorithm run time when compared to a state-of-the-art scheme.

Original language	English
Title of host publication	31st Telecommunications Forum (TELFOR)
Publisher	IEEE
ISBN (Electronic)	9798350303131
DOIs	https://doi.org/10.1109/telfor59449.2023.10372753
Publication status	Published - 1 Jan 2024
Event	31st Telecommunications Forum 2023 - Belgrade, Serbia Duration: 21 Nov 2023 → 22 Nov 2023

Conference

Conference	31st Telecommunications Forum 2023
Abbreviated title	TELFOR 2023
Country/Territory	Serbia
City	Belgrade
Period	21/11/23 → 22/11/23

Keywords

Deep Reinforcement Learning
Intelligent Reflecting Surfaces
MIMO
Passive Beamforming

ASJC Scopus subject areas

Safety, Risk, Reliability and Quality
Signal Processing
Hardware and Architecture
Computer Networks and Communications

Access to Document

10.1109/telfor59449.2023.10372753

Download pdf
© 2023 IEEE.
Accepted author manuscript, 790 KBLicence: CC BY

Cite this

@inproceedings{155869d8250045cda776d9cbf7600816,

title = "Intelligent Reflecting Surface Optimization for MIMO Communication Using Deep Reinforcement Learning",

abstract = "This paper focuses on the optimization of the phase shifts of an intelligent reflecting surface (IRS) for an IRS-aided multiple input multiple output (MIMO) communication system. Motivated by the massive success of deep reinforcement learning (DRL) algorithms in handling high-dimensional continuous action spaces and tackling non-convex optimization problems, we propose a deep deterministic policy gradient (DDPG) framework for solving the formulated non-convex optimization problem. Numerical simulations demonstrate the robustness and efficiency of the proposed model in terms of spectral efficiency and algorithm run time when compared to a state-of-the-art scheme.",

keywords = "Deep Reinforcement Learning, Intelligent Reflecting Surfaces, MIMO, Passive Beamforming",

author = "Kenneth Ikeagu and Yuan Ding and Chaoyun Song and Muhammad Khandaker",

note = "Funding Information: This work was supported by the School PhD scholarship from Heriot-Watt University and by the Engineering and Physical Sciences Research Council (EPSRC), UK, under Grant number EP/V002635/1. Publisher Copyright: {\textcopyright} 2023 IEEE.; 31st Telecommunications Forum 2023, TELFOR 2023 ; Conference date: 21-11-2023 Through 22-11-2023",

year = "2024",

month = jan,

day = "1",

doi = "10.1109/telfor59449.2023.10372753",

language = "English",

booktitle = "31st Telecommunications Forum (TELFOR)",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Intelligent Reflecting Surface Optimization for MIMO Communication Using Deep Reinforcement Learning

AU - Ikeagu, Kenneth

AU - Ding, Yuan

AU - Song, Chaoyun

AU - Khandaker, Muhammad

N1 - Funding Information: This work was supported by the School PhD scholarship from Heriot-Watt University and by the Engineering and Physical Sciences Research Council (EPSRC), UK, under Grant number EP/V002635/1. Publisher Copyright: © 2023 IEEE.

PY - 2024/1/1

Y1 - 2024/1/1

N2 - This paper focuses on the optimization of the phase shifts of an intelligent reflecting surface (IRS) for an IRS-aided multiple input multiple output (MIMO) communication system. Motivated by the massive success of deep reinforcement learning (DRL) algorithms in handling high-dimensional continuous action spaces and tackling non-convex optimization problems, we propose a deep deterministic policy gradient (DDPG) framework for solving the formulated non-convex optimization problem. Numerical simulations demonstrate the robustness and efficiency of the proposed model in terms of spectral efficiency and algorithm run time when compared to a state-of-the-art scheme.

AB - This paper focuses on the optimization of the phase shifts of an intelligent reflecting surface (IRS) for an IRS-aided multiple input multiple output (MIMO) communication system. Motivated by the massive success of deep reinforcement learning (DRL) algorithms in handling high-dimensional continuous action spaces and tackling non-convex optimization problems, we propose a deep deterministic policy gradient (DDPG) framework for solving the formulated non-convex optimization problem. Numerical simulations demonstrate the robustness and efficiency of the proposed model in terms of spectral efficiency and algorithm run time when compared to a state-of-the-art scheme.

KW - Deep Reinforcement Learning

KW - Intelligent Reflecting Surfaces

KW - MIMO

KW - Passive Beamforming

UR - http://www.scopus.com/inward/record.url?scp=85183471329&partnerID=8YFLogxK

U2 - 10.1109/telfor59449.2023.10372753

DO - 10.1109/telfor59449.2023.10372753

M3 - Conference contribution

BT - 31st Telecommunications Forum (TELFOR)

PB - IEEE

T2 - 31st Telecommunications Forum 2023

Y2 - 21 November 2023 through 22 November 2023

ER -

Intelligent Reflecting Surface Optimization for MIMO Communication Using Deep Reinforcement Learning

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this