An Efficient Learning Algorithm for Phase Shift Optimization in RIS-Aided MISO Wireless Systems

Jiawen Tian; Wenwen Guan; Xiao Li; Theodoros A. Tsiftsis; Hongwu Liu

doi:10.1109/WCSP58612.2023.10404084

An Efficient Learning Algorithm for Phase Shift Optimization in RIS-Aided MISO Wireless Systems

Jiawen Tian, Wenwen Guan, Xiao Li, Theodoros A. Tsiftsis, Hongwu Liu

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

Abstract

Due to dynamic change of the wireless environment, devising the local phase shift matrix for reconfigurable intelligent surface (RIS) can be a thought-provoking task. Therefore, in this paper, we come up with a deep reinforcement learning (DRL)-based beamforming optimization algorithm for RIS-aided multiple-input single-output communication systems. To be precise, we exploit a DRL-based structure based on twin-delayed-deep-deterministic-policy-gradient (TD3) algorithm to automatically adjust the phase shift of each unit at RIS to maximize the downlink received signal-to-noise ratio (SNR). Simulation results show that the raised TD3 algorithm performs a higher received SNR than the conventional DRL algorithm with a reduced running time.

Original language	English
Title of host publication	2023 IEEE 15th International Conference on Wireless Communications and Signal Processing, WCSP 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1014-1019
Number of pages	6
ISBN (Electronic)	9798350324662
DOIs	https://doi.org/10.1109/WCSP58612.2023.10404084
Publication status	Published - 2023
Externally published	Yes
Event	15th IEEE International Conference on Wireless Communications and Signal Processing, WCSP 2023 - Hangzhou, China Duration: 2 Nov 2023 → 4 Nov 2023

Publication series

Name	2023 IEEE 15th International Conference on Wireless Communications and Signal Processing, WCSP 2023

Conference

Conference	15th IEEE International Conference on Wireless Communications and Signal Processing, WCSP 2023
Country/Territory	China
City	Hangzhou
Period	2/11/23 → 4/11/23

Keywords

Deep reinforcement learning (DRL)
passive phase shift design
reconfigurable intelligent surface (RIS)
TD3 algorithm

ASJC Scopus subject areas

Media Technology
Artificial Intelligence
Computer Networks and Communications
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/WCSP58612.2023.10404084

Cite this

Tian, J., Guan, W., Li, X., Tsiftsis, T. A., & Liu, H. (2023). An Efficient Learning Algorithm for Phase Shift Optimization in RIS-Aided MISO Wireless Systems. In 2023 IEEE 15th International Conference on Wireless Communications and Signal Processing, WCSP 2023 (pp. 1014-1019). (2023 IEEE 15th International Conference on Wireless Communications and Signal Processing, WCSP 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WCSP58612.2023.10404084

Tian, Jiawen ; Guan, Wenwen ; Li, Xiao et al. / An Efficient Learning Algorithm for Phase Shift Optimization in RIS-Aided MISO Wireless Systems. 2023 IEEE 15th International Conference on Wireless Communications and Signal Processing, WCSP 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 1014-1019 (2023 IEEE 15th International Conference on Wireless Communications and Signal Processing, WCSP 2023).

@inproceedings{6cbf6a8d701f4e039bf6eb357519fc3a,

title = "An Efficient Learning Algorithm for Phase Shift Optimization in RIS-Aided MISO Wireless Systems",

abstract = "Due to dynamic change of the wireless environment, devising the local phase shift matrix for reconfigurable intelligent surface (RIS) can be a thought-provoking task. Therefore, in this paper, we come up with a deep reinforcement learning (DRL)-based beamforming optimization algorithm for RIS-aided multiple-input single-output communication systems. To be precise, we exploit a DRL-based structure based on twin-delayed-deep-deterministic-policy-gradient (TD3) algorithm to automatically adjust the phase shift of each unit at RIS to maximize the downlink received signal-to-noise ratio (SNR). Simulation results show that the raised TD3 algorithm performs a higher received SNR than the conventional DRL algorithm with a reduced running time.",

keywords = "Deep reinforcement learning (DRL), passive phase shift design, reconfigurable intelligent surface (RIS), TD3 algorithm",

author = "Jiawen Tian and Wenwen Guan and Xiao Li and Tsiftsis, \{Theodoros A.\} and Hongwu Liu",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 15th IEEE International Conference on Wireless Communications and Signal Processing, WCSP 2023 ; Conference date: 02-11-2023 Through 04-11-2023",

year = "2023",

doi = "10.1109/WCSP58612.2023.10404084",

language = "English",

series = "2023 IEEE 15th International Conference on Wireless Communications and Signal Processing, WCSP 2023",

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

pages = "1014--1019",

booktitle = "2023 IEEE 15th International Conference on Wireless Communications and Signal Processing, WCSP 2023",

address = "United States",

}

Tian, J, Guan, W, Li, X, Tsiftsis, TA & Liu, H 2023, An Efficient Learning Algorithm for Phase Shift Optimization in RIS-Aided MISO Wireless Systems. in 2023 IEEE 15th International Conference on Wireless Communications and Signal Processing, WCSP 2023. 2023 IEEE 15th International Conference on Wireless Communications and Signal Processing, WCSP 2023, Institute of Electrical and Electronics Engineers Inc., pp. 1014-1019, 15th IEEE International Conference on Wireless Communications and Signal Processing, WCSP 2023, Hangzhou, China, 2/11/23. https://doi.org/10.1109/WCSP58612.2023.10404084

An Efficient Learning Algorithm for Phase Shift Optimization in RIS-Aided MISO Wireless Systems. / Tian, Jiawen; Guan, Wenwen; Li, Xiao et al.
2023 IEEE 15th International Conference on Wireless Communications and Signal Processing, WCSP 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 1014-1019 (2023 IEEE 15th International Conference on Wireless Communications and Signal Processing, WCSP 2023).

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

TY - GEN

T1 - An Efficient Learning Algorithm for Phase Shift Optimization in RIS-Aided MISO Wireless Systems

AU - Tian, Jiawen

AU - Guan, Wenwen

AU - Li, Xiao

AU - Tsiftsis, Theodoros A.

AU - Liu, Hongwu

PY - 2023

Y1 - 2023

N2 - Due to dynamic change of the wireless environment, devising the local phase shift matrix for reconfigurable intelligent surface (RIS) can be a thought-provoking task. Therefore, in this paper, we come up with a deep reinforcement learning (DRL)-based beamforming optimization algorithm for RIS-aided multiple-input single-output communication systems. To be precise, we exploit a DRL-based structure based on twin-delayed-deep-deterministic-policy-gradient (TD3) algorithm to automatically adjust the phase shift of each unit at RIS to maximize the downlink received signal-to-noise ratio (SNR). Simulation results show that the raised TD3 algorithm performs a higher received SNR than the conventional DRL algorithm with a reduced running time.

AB - Due to dynamic change of the wireless environment, devising the local phase shift matrix for reconfigurable intelligent surface (RIS) can be a thought-provoking task. Therefore, in this paper, we come up with a deep reinforcement learning (DRL)-based beamforming optimization algorithm for RIS-aided multiple-input single-output communication systems. To be precise, we exploit a DRL-based structure based on twin-delayed-deep-deterministic-policy-gradient (TD3) algorithm to automatically adjust the phase shift of each unit at RIS to maximize the downlink received signal-to-noise ratio (SNR). Simulation results show that the raised TD3 algorithm performs a higher received SNR than the conventional DRL algorithm with a reduced running time.

KW - Deep reinforcement learning (DRL)

KW - passive phase shift design

KW - reconfigurable intelligent surface (RIS)

KW - TD3 algorithm

UR - https://www.scopus.com/pages/publications/85185782754

U2 - 10.1109/WCSP58612.2023.10404084

DO - 10.1109/WCSP58612.2023.10404084

M3 - Conference contribution

AN - SCOPUS:85185782754

T3 - 2023 IEEE 15th International Conference on Wireless Communications and Signal Processing, WCSP 2023

SP - 1014

EP - 1019

BT - 2023 IEEE 15th International Conference on Wireless Communications and Signal Processing, WCSP 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 15th IEEE International Conference on Wireless Communications and Signal Processing, WCSP 2023

Y2 - 2 November 2023 through 4 November 2023

ER -

Tian J, Guan W, Li X, Tsiftsis TA, Liu H. An Efficient Learning Algorithm for Phase Shift Optimization in RIS-Aided MISO Wireless Systems. In 2023 IEEE 15th International Conference on Wireless Communications and Signal Processing, WCSP 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 1014-1019. (2023 IEEE 15th International Conference on Wireless Communications and Signal Processing, WCSP 2023). doi: 10.1109/WCSP58612.2023.10404084

An Efficient Learning Algorithm for Phase Shift Optimization in RIS-Aided MISO Wireless Systems

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this