Research on Active/Passive Hybrid IRS Assisted Communication Method Based on Deep Learning

Chenguang He; Yuchuan Ma; Shengxian Huang; Jing Li

doi:10.1109/APCC55198.2022.9943646

Research on Active/Passive Hybrid IRS Assisted Communication Method Based on Deep Learning

Chenguang He^*
, Yuchuan Ma
, Shengxian Huang
, Jing Li

^*Corresponding author for this work

School of Electronics and Information Engineering, Harbin Institute of Technology

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

3 Scopus citations

Abstract

With the rapid development of mobile communication technology, wireless communication systems have higher and higher requirements for spectral efficiency and energy efficiency. However, in the optimization process of many technologies, the wireless communication environment is still an uncontrollable factor, and is increasingly becoming a bottleneck for improving communication quality. Intelligent Reflecting Surface can reflect incident signals through a large number of low-cost reflective units, thereby improving the wireless communication environment. This paper introduces a solution based on deep learning method with the goal of maximizing the achievable rate of the system under the condition of intelligent reflecting surface hardware architecture of hybrid active/passive units. Firstly, the performance of communication system with intelligent reflecting surface and relay is compared. After that, the hardware architecture of intelligent reflecting surface with hybrid active/passive units is introduced, and the research scheme of intelligent reflecting surface based on deep learning is designed and simulated. The results show that the proposed scheme can approach the upper limit of the achievable rate of the system as much as possible while reducing the overhead of beam training.

Original language	English
Title of host publication	APCC 2022 - 27th Asia-Pacific Conference on Communications
Subtitle of host publication	Creating Innovative Communication Technologies for Post-Pandemic Era
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	483-487
Number of pages	5
ISBN (Electronic)	9781665499279
DOIs	https://doi.org/10.1109/APCC55198.2022.9943646
State	Published - 2022
Externally published	Yes
Event	27th Asia-Pacific Conference on Communications, APCC 2022 - Jeju Island, Korea, Republic of Duration: 19 Oct 2022 → 21 Oct 2022

Publication series

Name	APCC 2022 - 27th Asia-Pacific Conference on Communications: Creating Innovative Communication Technologies for Post-Pandemic Era

Conference

Conference	27th Asia-Pacific Conference on Communications, APCC 2022
Country/Territory	Korea, Republic of
City	Jeju Island
Period	19/10/22 → 21/10/22

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

deep learning
intelligent reflecting surface
wireless communication

Access to Document

10.1109/APCC55198.2022.9943646

Cite this

He, C., Ma, Y., Huang, S., & Li, J. (2022). Research on Active/Passive Hybrid IRS Assisted Communication Method Based on Deep Learning. In APCC 2022 - 27th Asia-Pacific Conference on Communications: Creating Innovative Communication Technologies for Post-Pandemic Era (pp. 483-487). (APCC 2022 - 27th Asia-Pacific Conference on Communications: Creating Innovative Communication Technologies for Post-Pandemic Era). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/APCC55198.2022.9943646

He, Chenguang ; Ma, Yuchuan ; Huang, Shengxian et al. / Research on Active/Passive Hybrid IRS Assisted Communication Method Based on Deep Learning. APCC 2022 - 27th Asia-Pacific Conference on Communications: Creating Innovative Communication Technologies for Post-Pandemic Era. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 483-487 (APCC 2022 - 27th Asia-Pacific Conference on Communications: Creating Innovative Communication Technologies for Post-Pandemic Era).

@inproceedings{64532fea28f84bc49313065915417026,

title = "Research on Active/Passive Hybrid IRS Assisted Communication Method Based on Deep Learning",

abstract = "With the rapid development of mobile communication technology, wireless communication systems have higher and higher requirements for spectral efficiency and energy efficiency. However, in the optimization process of many technologies, the wireless communication environment is still an uncontrollable factor, and is increasingly becoming a bottleneck for improving communication quality. Intelligent Reflecting Surface can reflect incident signals through a large number of low-cost reflective units, thereby improving the wireless communication environment. This paper introduces a solution based on deep learning method with the goal of maximizing the achievable rate of the system under the condition of intelligent reflecting surface hardware architecture of hybrid active/passive units. Firstly, the performance of communication system with intelligent reflecting surface and relay is compared. After that, the hardware architecture of intelligent reflecting surface with hybrid active/passive units is introduced, and the research scheme of intelligent reflecting surface based on deep learning is designed and simulated. The results show that the proposed scheme can approach the upper limit of the achievable rate of the system as much as possible while reducing the overhead of beam training.",

keywords = "deep learning, intelligent reflecting surface, wireless communication",

author = "Chenguang He and Yuchuan Ma and Shengxian Huang and Jing Li",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 27th Asia-Pacific Conference on Communications, APCC 2022 ; Conference date: 19-10-2022 Through 21-10-2022",

year = "2022",

doi = "10.1109/APCC55198.2022.9943646",

language = "英语",

series = "APCC 2022 - 27th Asia-Pacific Conference on Communications: Creating Innovative Communication Technologies for Post-Pandemic Era",

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

pages = "483--487",

booktitle = "APCC 2022 - 27th Asia-Pacific Conference on Communications",

address = "美国",

}

He, C, Ma, Y, Huang, S & Li, J 2022, Research on Active/Passive Hybrid IRS Assisted Communication Method Based on Deep Learning. in APCC 2022 - 27th Asia-Pacific Conference on Communications: Creating Innovative Communication Technologies for Post-Pandemic Era. APCC 2022 - 27th Asia-Pacific Conference on Communications: Creating Innovative Communication Technologies for Post-Pandemic Era, Institute of Electrical and Electronics Engineers Inc., pp. 483-487, 27th Asia-Pacific Conference on Communications, APCC 2022, Jeju Island, Korea, Republic of, 19/10/22. https://doi.org/10.1109/APCC55198.2022.9943646

Research on Active/Passive Hybrid IRS Assisted Communication Method Based on Deep Learning. / He, Chenguang; Ma, Yuchuan; Huang, Shengxian et al.
APCC 2022 - 27th Asia-Pacific Conference on Communications: Creating Innovative Communication Technologies for Post-Pandemic Era. Institute of Electrical and Electronics Engineers Inc., 2022. p. 483-487 (APCC 2022 - 27th Asia-Pacific Conference on Communications: Creating Innovative Communication Technologies for Post-Pandemic Era).

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

TY - GEN

T1 - Research on Active/Passive Hybrid IRS Assisted Communication Method Based on Deep Learning

AU - He, Chenguang

AU - Ma, Yuchuan

AU - Huang, Shengxian

AU - Li, Jing

PY - 2022

Y1 - 2022

N2 - With the rapid development of mobile communication technology, wireless communication systems have higher and higher requirements for spectral efficiency and energy efficiency. However, in the optimization process of many technologies, the wireless communication environment is still an uncontrollable factor, and is increasingly becoming a bottleneck for improving communication quality. Intelligent Reflecting Surface can reflect incident signals through a large number of low-cost reflective units, thereby improving the wireless communication environment. This paper introduces a solution based on deep learning method with the goal of maximizing the achievable rate of the system under the condition of intelligent reflecting surface hardware architecture of hybrid active/passive units. Firstly, the performance of communication system with intelligent reflecting surface and relay is compared. After that, the hardware architecture of intelligent reflecting surface with hybrid active/passive units is introduced, and the research scheme of intelligent reflecting surface based on deep learning is designed and simulated. The results show that the proposed scheme can approach the upper limit of the achievable rate of the system as much as possible while reducing the overhead of beam training.

AB - With the rapid development of mobile communication technology, wireless communication systems have higher and higher requirements for spectral efficiency and energy efficiency. However, in the optimization process of many technologies, the wireless communication environment is still an uncontrollable factor, and is increasingly becoming a bottleneck for improving communication quality. Intelligent Reflecting Surface can reflect incident signals through a large number of low-cost reflective units, thereby improving the wireless communication environment. This paper introduces a solution based on deep learning method with the goal of maximizing the achievable rate of the system under the condition of intelligent reflecting surface hardware architecture of hybrid active/passive units. Firstly, the performance of communication system with intelligent reflecting surface and relay is compared. After that, the hardware architecture of intelligent reflecting surface with hybrid active/passive units is introduced, and the research scheme of intelligent reflecting surface based on deep learning is designed and simulated. The results show that the proposed scheme can approach the upper limit of the achievable rate of the system as much as possible while reducing the overhead of beam training.

KW - deep learning

KW - intelligent reflecting surface

KW - wireless communication

UR - https://www.scopus.com/pages/publications/85143063887

U2 - 10.1109/APCC55198.2022.9943646

DO - 10.1109/APCC55198.2022.9943646

M3 - 会议稿件

AN - SCOPUS:85143063887

T3 - APCC 2022 - 27th Asia-Pacific Conference on Communications: Creating Innovative Communication Technologies for Post-Pandemic Era

SP - 483

EP - 487

BT - APCC 2022 - 27th Asia-Pacific Conference on Communications

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 27th Asia-Pacific Conference on Communications, APCC 2022

Y2 - 19 October 2022 through 21 October 2022

ER -

He C, Ma Y, Huang S, Li J. Research on Active/Passive Hybrid IRS Assisted Communication Method Based on Deep Learning. In APCC 2022 - 27th Asia-Pacific Conference on Communications: Creating Innovative Communication Technologies for Post-Pandemic Era. Institute of Electrical and Electronics Engineers Inc. 2022. p. 483-487. (APCC 2022 - 27th Asia-Pacific Conference on Communications: Creating Innovative Communication Technologies for Post-Pandemic Era). doi: 10.1109/APCC55198.2022.9943646

Research on Active/Passive Hybrid IRS Assisted Communication Method Based on Deep Learning

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this