Deep Learning Based Passive Beamforming for IRS-Assisted Monostatic Backscatter Systems (Invited Paper)

Sahar Idrees; Xiaolun Jia; Saud Khan; Salman Durrani; Xiangyun Zhou

doi:10.1109/ICASSP43922.2022.9746747

Deep Learning Based Passive Beamforming for IRS-Assisted Monostatic Backscatter Systems (Invited Paper)

Sahar Idrees^*, Xiaolun Jia^*, Saud Khan^*, Salman Durrani^*, Xiangyun Zhou^*

^*Corresponding author for this work

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

8 Citations (Scopus)

Abstract

Intelligent reflecting surfaces (IRS) can improve the performance of backscatter communication systems by employing reconfigurable phase shifts (or passive beamforming) to favorably configure the wireless propagation medium. However, the design of optimal IRS phase shifts requires channel state information (CSI), which is hard to acquire in a multireflection channel. In this paper, we propose a deep learning based framework that learns the desired IRS phase shifts without knowing the channels, to assist the communication of a passive backscatter tag. This is achieved by parameterizing the mapping from the received pilots to the desired configuration of IRS by training a deep neural network (DNN) BIRS-Net on a sufficiently large dataset covering a variety of channel realizations and possible power splitting ratios at the backscatter tag. Simulation results show that the proposed DNN based solution can efficiently learn to maximize the SNR of backscatter transmission and exhibits near optimal performance.

Original language	English
Title of host publication	ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	8652-8656
Number of pages	5
ISBN (Electronic)	978-1-6654-0540-9
ISBN (Print)	978-1-6654-0541-6
DOIs	https://doi.org/10.1109/ICASSP43922.2022.9746747
Publication status	Published - 2022
Event	47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - , Singapore Duration: 22 May 2022 → 27 May 2022 Conference number: 47 https://2022.ieeeicassp.org/ (Conference Website) https://doi.org/10.1109/ICASSP43922.2022 (Conference Proceedings)

Publication series

Name	IEEE International Conference on Acoustics, Speech and Signal Processing Proceedings
Volume	2022-May
ISSN (Print)	1520-6149
ISSN (Electronic)	2379-190X

Conference

Conference	47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022
Abbreviated title	ICASSP 2022
Country/Territory	Singapore
Period	22/05/22 → 27/05/22
Other	The International Conference on Acoustics, Speech, & Signal Processing (ICASSP), is the IEEE Signal Processing Society’s flagship conference on signal processing and its applications. The 47th edition of ICASSP will be held in Singapore. The programme will include keynotes by pre-eminent international speakers, cutting-edge tutorial topics, and forward-looking special sessions.
Internet address	https://2022.ieeeicassp.org/ (Conference Website) https://doi.org/10.1109/ICASSP43922.2022 (Conference Proceedings)

Access to Document

10.1109/ICASSP43922.2022.9746747

Cite this

Idrees, S., Jia, X., Khan, S., Durrani, S., & Zhou, X. (2022). Deep Learning Based Passive Beamforming for IRS-Assisted Monostatic Backscatter Systems (Invited Paper). In ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Proceedings (pp. 8652-8656). (IEEE International Conference on Acoustics, Speech and Signal Processing Proceedings; Vol. 2022-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP43922.2022.9746747

Idrees, Sahar ; Jia, Xiaolun ; Khan, Saud et al. / Deep Learning Based Passive Beamforming for IRS-Assisted Monostatic Backscatter Systems (Invited Paper). ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 8652-8656 (IEEE International Conference on Acoustics, Speech and Signal Processing Proceedings).

@inproceedings{2d7bc00546574475bd547d22d0aa0c64,

title = "Deep Learning Based Passive Beamforming for IRS-Assisted Monostatic Backscatter Systems (Invited Paper)",

abstract = "Intelligent reflecting surfaces (IRS) can improve the performance of backscatter communication systems by employing reconfigurable phase shifts (or passive beamforming) to favorably configure the wireless propagation medium. However, the design of optimal IRS phase shifts requires channel state information (CSI), which is hard to acquire in a multireflection channel. In this paper, we propose a deep learning based framework that learns the desired IRS phase shifts without knowing the channels, to assist the communication of a passive backscatter tag. This is achieved by parameterizing the mapping from the received pilots to the desired configuration of IRS by training a deep neural network (DNN) BIRS-Net on a sufficiently large dataset covering a variety of channel realizations and possible power splitting ratios at the backscatter tag. Simulation results show that the proposed DNN based solution can efficiently learn to maximize the SNR of backscatter transmission and exhibits near optimal performance.",

keywords = "Backscatter communication, deep learning, energy harvesting, intelligent reflecting surface, passive beamforming",

author = "Sahar Idrees and Xiaolun Jia and Saud Khan and Salman Durrani and Xiangyun Zhou",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE; 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022, ICASSP 2022 ; Conference date: 22-05-2022 Through 27-05-2022",

year = "2022",

doi = "10.1109/ICASSP43922.2022.9746747",

language = "English",

isbn = "978-1-6654-0541-6",

series = "IEEE International Conference on Acoustics, Speech and Signal Processing Proceedings",

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

pages = "8652--8656",

booktitle = "ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Proceedings",

address = "United States",

url = "https://2022.ieeeicassp.org/, https://doi.org/10.1109/ICASSP43922.2022",

}

Idrees, S, Jia, X, Khan, S, Durrani, S & Zhou, X 2022, Deep Learning Based Passive Beamforming for IRS-Assisted Monostatic Backscatter Systems (Invited Paper). in ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Proceedings. IEEE International Conference on Acoustics, Speech and Signal Processing Proceedings, vol. 2022-May, Institute of Electrical and Electronics Engineers Inc., pp. 8652-8656, 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022, Singapore, 22/05/22. https://doi.org/10.1109/ICASSP43922.2022.9746747

Deep Learning Based Passive Beamforming for IRS-Assisted Monostatic Backscatter Systems (Invited Paper). / Idrees, Sahar; Jia, Xiaolun; Khan, Saud et al.
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2022. p. 8652-8656 (IEEE International Conference on Acoustics, Speech and Signal Processing Proceedings; Vol. 2022-May).

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

TY - GEN

T1 - Deep Learning Based Passive Beamforming for IRS-Assisted Monostatic Backscatter Systems (Invited Paper)

AU - Idrees, Sahar

AU - Jia, Xiaolun

AU - Khan, Saud

AU - Durrani, Salman

AU - Zhou, Xiangyun

N1 - Conference code: 47

PY - 2022

Y1 - 2022

N2 - Intelligent reflecting surfaces (IRS) can improve the performance of backscatter communication systems by employing reconfigurable phase shifts (or passive beamforming) to favorably configure the wireless propagation medium. However, the design of optimal IRS phase shifts requires channel state information (CSI), which is hard to acquire in a multireflection channel. In this paper, we propose a deep learning based framework that learns the desired IRS phase shifts without knowing the channels, to assist the communication of a passive backscatter tag. This is achieved by parameterizing the mapping from the received pilots to the desired configuration of IRS by training a deep neural network (DNN) BIRS-Net on a sufficiently large dataset covering a variety of channel realizations and possible power splitting ratios at the backscatter tag. Simulation results show that the proposed DNN based solution can efficiently learn to maximize the SNR of backscatter transmission and exhibits near optimal performance.

AB - Intelligent reflecting surfaces (IRS) can improve the performance of backscatter communication systems by employing reconfigurable phase shifts (or passive beamforming) to favorably configure the wireless propagation medium. However, the design of optimal IRS phase shifts requires channel state information (CSI), which is hard to acquire in a multireflection channel. In this paper, we propose a deep learning based framework that learns the desired IRS phase shifts without knowing the channels, to assist the communication of a passive backscatter tag. This is achieved by parameterizing the mapping from the received pilots to the desired configuration of IRS by training a deep neural network (DNN) BIRS-Net on a sufficiently large dataset covering a variety of channel realizations and possible power splitting ratios at the backscatter tag. Simulation results show that the proposed DNN based solution can efficiently learn to maximize the SNR of backscatter transmission and exhibits near optimal performance.

KW - Backscatter communication

KW - deep learning

KW - energy harvesting

KW - intelligent reflecting surface

KW - passive beamforming

UR - https://www.scopus.com/pages/publications/85131241333

U2 - 10.1109/ICASSP43922.2022.9746747

DO - 10.1109/ICASSP43922.2022.9746747

M3 - Conference Paper

SN - 978-1-6654-0541-6

T3 - IEEE International Conference on Acoustics, Speech and Signal Processing Proceedings

SP - 8652

EP - 8656

BT - ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022

Y2 - 22 May 2022 through 27 May 2022

ER -

Idrees S, Jia X, Khan S, Durrani S , Zhou X. Deep Learning Based Passive Beamforming for IRS-Assisted Monostatic Backscatter Systems (Invited Paper). In ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2022. p. 8652-8656. (IEEE International Conference on Acoustics, Speech and Signal Processing Proceedings). doi: 10.1109/ICASSP43922.2022.9746747

Deep Learning Based Passive Beamforming for IRS-Assisted Monostatic Backscatter Systems (Invited Paper)

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this