Deep Learning-based Joint Transmit and Reflective Beamforming Design for IRS-Aided MISO Multiuser Systems Under Statistical CSI

Wenwen Guan; Jiawen Tian; Theodoros A. Tsiftsis; Cunhua Pan

doi:10.1109/ICCC57788.2023.10233381

Deep Learning-based Joint Transmit and Reflective Beamforming Design for IRS-Aided MISO Multiuser Systems Under Statistical CSI

Wenwen Guan, Jiawen Tian, Theodoros A. Tsiftsis, Cunhua Pan

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

Abstract

In this paper, we study the joint design of the transmit beamforming and reflective beamforming for an intelligent reflective surface (IRS)-aided multiple-input single-output (MISO) multiuser communication system. Particularly, we maximize the minimum achievable rate per user by jointly designing the phase shifts of IRS and active beamforming at the base station on the basis of the statistical channel state information (CSI). More important, we use the twin delayed deep deterministic policy gradient (TD3) algorithm with either traditional experience replay or priority experience replay (PER) to solve the optimization problem. Simulation results reveal that the TD3 achieves higher minimum average user data rate than the deep deterministic policy gradient algorithm. Additionally, the PER-TD3 algorithm based on statistical CSI has much lower computational complexity compared to the instantaneous one.

Original language	English
Title of host publication	2023 IEEE/CIC International Conference on Communications in China, ICCC 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350345384
DOIs	https://doi.org/10.1109/ICCC57788.2023.10233381
Publication status	Published - 2023
Externally published	Yes
Event	2023 IEEE/CIC International Conference on Communications in China, ICCC 2023 - Dalian, China Duration: 10 Aug 2023 → 12 Aug 2023

Publication series

Name	2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

Conference

Conference	2023 IEEE/CIC International Conference on Communications in China, ICCC 2023
Country/Territory	China
City	Dalian
Period	10/08/23 → 12/08/23

Keywords

Deep reinforcement learning (DRL)
intelligent reflecting surface (IRS)
statistical channel state information (CSI)
twin delayed deep deterministic policy gradient (TD3)

ASJC Scopus subject areas

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

Access to Document

10.1109/ICCC57788.2023.10233381

Cite this

Guan, W., Tian, J., Tsiftsis, T. A., & Pan, C. (2023). Deep Learning-based Joint Transmit and Reflective Beamforming Design for IRS-Aided MISO Multiuser Systems Under Statistical CSI. In 2023 IEEE/CIC International Conference on Communications in China, ICCC 2023 (2023 IEEE/CIC International Conference on Communications in China, ICCC 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCC57788.2023.10233381

Guan, Wenwen ; Tian, Jiawen ; Tsiftsis, Theodoros A. et al. / Deep Learning-based Joint Transmit and Reflective Beamforming Design for IRS-Aided MISO Multiuser Systems Under Statistical CSI. 2023 IEEE/CIC International Conference on Communications in China, ICCC 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 IEEE/CIC International Conference on Communications in China, ICCC 2023).

@inproceedings{c3309d218de7416ea5620708a8dfe8a5,

title = "Deep Learning-based Joint Transmit and Reflective Beamforming Design for IRS-Aided MISO Multiuser Systems Under Statistical CSI",

abstract = "In this paper, we study the joint design of the transmit beamforming and reflective beamforming for an intelligent reflective surface (IRS)-aided multiple-input single-output (MISO) multiuser communication system. Particularly, we maximize the minimum achievable rate per user by jointly designing the phase shifts of IRS and active beamforming at the base station on the basis of the statistical channel state information (CSI). More important, we use the twin delayed deep deterministic policy gradient (TD3) algorithm with either traditional experience replay or priority experience replay (PER) to solve the optimization problem. Simulation results reveal that the TD3 achieves higher minimum average user data rate than the deep deterministic policy gradient algorithm. Additionally, the PER-TD3 algorithm based on statistical CSI has much lower computational complexity compared to the instantaneous one.",

keywords = "Deep reinforcement learning (DRL), intelligent reflecting surface (IRS), statistical channel state information (CSI), twin delayed deep deterministic policy gradient (TD3)",

author = "Wenwen Guan and Jiawen Tian and Tsiftsis, \{Theodoros A.\} and Cunhua Pan",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE/CIC International Conference on Communications in China, ICCC 2023 ; Conference date: 10-08-2023 Through 12-08-2023",

year = "2023",

doi = "10.1109/ICCC57788.2023.10233381",

language = "English",

series = "2023 IEEE/CIC International Conference on Communications in China, ICCC 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2023 IEEE/CIC International Conference on Communications in China, ICCC 2023",

address = "United States",

}

Guan, W, Tian, J, Tsiftsis, TA & Pan, C 2023, Deep Learning-based Joint Transmit and Reflective Beamforming Design for IRS-Aided MISO Multiuser Systems Under Statistical CSI. in 2023 IEEE/CIC International Conference on Communications in China, ICCC 2023. 2023 IEEE/CIC International Conference on Communications in China, ICCC 2023, Institute of Electrical and Electronics Engineers Inc., 2023 IEEE/CIC International Conference on Communications in China, ICCC 2023, Dalian, China, 10/08/23. https://doi.org/10.1109/ICCC57788.2023.10233381

Deep Learning-based Joint Transmit and Reflective Beamforming Design for IRS-Aided MISO Multiuser Systems Under Statistical CSI. / Guan, Wenwen; Tian, Jiawen; Tsiftsis, Theodoros A. et al.
2023 IEEE/CIC International Conference on Communications in China, ICCC 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 IEEE/CIC International Conference on Communications in China, ICCC 2023).

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Deep Learning-based Joint Transmit and Reflective Beamforming Design for IRS-Aided MISO Multiuser Systems Under Statistical CSI

AU - Guan, Wenwen

AU - Tian, Jiawen

AU - Tsiftsis, Theodoros A.

AU - Pan, Cunhua

PY - 2023

Y1 - 2023

N2 - In this paper, we study the joint design of the transmit beamforming and reflective beamforming for an intelligent reflective surface (IRS)-aided multiple-input single-output (MISO) multiuser communication system. Particularly, we maximize the minimum achievable rate per user by jointly designing the phase shifts of IRS and active beamforming at the base station on the basis of the statistical channel state information (CSI). More important, we use the twin delayed deep deterministic policy gradient (TD3) algorithm with either traditional experience replay or priority experience replay (PER) to solve the optimization problem. Simulation results reveal that the TD3 achieves higher minimum average user data rate than the deep deterministic policy gradient algorithm. Additionally, the PER-TD3 algorithm based on statistical CSI has much lower computational complexity compared to the instantaneous one.

AB - In this paper, we study the joint design of the transmit beamforming and reflective beamforming for an intelligent reflective surface (IRS)-aided multiple-input single-output (MISO) multiuser communication system. Particularly, we maximize the minimum achievable rate per user by jointly designing the phase shifts of IRS and active beamforming at the base station on the basis of the statistical channel state information (CSI). More important, we use the twin delayed deep deterministic policy gradient (TD3) algorithm with either traditional experience replay or priority experience replay (PER) to solve the optimization problem. Simulation results reveal that the TD3 achieves higher minimum average user data rate than the deep deterministic policy gradient algorithm. Additionally, the PER-TD3 algorithm based on statistical CSI has much lower computational complexity compared to the instantaneous one.

KW - Deep reinforcement learning (DRL)

KW - intelligent reflecting surface (IRS)

KW - statistical channel state information (CSI)

KW - twin delayed deep deterministic policy gradient (TD3)

UR - https://www.scopus.com/pages/publications/85172995897

U2 - 10.1109/ICCC57788.2023.10233381

DO - 10.1109/ICCC57788.2023.10233381

M3 - Conference contribution

AN - SCOPUS:85172995897

T3 - 2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

BT - 2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

Y2 - 10 August 2023 through 12 August 2023

ER -

Guan W, Tian J, Tsiftsis TA, Pan C. Deep Learning-based Joint Transmit and Reflective Beamforming Design for IRS-Aided MISO Multiuser Systems Under Statistical CSI. In 2023 IEEE/CIC International Conference on Communications in China, ICCC 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (2023 IEEE/CIC International Conference on Communications in China, ICCC 2023). doi: 10.1109/ICCC57788.2023.10233381

Deep Learning-based Joint Transmit and Reflective Beamforming Design for IRS-Aided MISO Multiuser Systems Under Statistical CSI

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this