A Study on the Effect of Phase Shifter Quantization Error on the Spectral Efficiency Using Neural Network

Reza Ghazalian; Sahar Golipoor

doi:10.1109/GPECOM55404.2022.9815775

A Study on the Effect of Phase Shifter Quantization Error on the Spectral Efficiency Using Neural Network

Reza Ghazalian^*
, Sahar Golipoor

^*Corresponding author for this work

Communication Engineering

Babol Noshirvani University of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

91 Downloads (Pure)

Abstract

Beamforming (BF) is the inevitable component of the recent communication systems, especially Millimeter wave (mmWave) systems. Thanks to the radio frequency (RF) and digital technologies, BF techniques are implemented in the both digital and analogue domains by using phase shifters (PS) networks. Adopting the digital PS, which has the finite resolution bits, leads to loss in the spectral efficiency (SE). Accordingly, in this paper, we extract the SE loss in a multi-user multiple inputs single output (MISO) system, which would be useful for practical prospective. To this end, we apply machine learning (ML) to extract the SE loss. Simulation results show that the extracted models have the desirable accuracy in the SE loss prediction.

Original language	English
Title of host publication	Proceedings - 2022 IEEE 4th Global Power, Energy and Communication Conference, GPECOM 2022
Publisher	IEEE
Pages	626-631
Number of pages	6
ISBN (Electronic)	978-1-6654-6925-8
DOIs	https://doi.org/10.1109/GPECOM55404.2022.9815775
Publication status	Published - 11 Jul 2022
MoE publication type	A4 Conference publication
Event	IEEE Global Power, Energy and Communication Conference - Cappadocia, Türkiye Duration: 14 Jun 2022 → 17 Jun 2022

Publication series

Name	Proceedings - IEEE Global Power, Energy and Communication Conference

Conference

Conference	IEEE Global Power, Energy and Communication Conference
Abbreviated title	GPECOM
Country/Territory	Türkiye
City	Cappadocia
Period	14/06/2022 → 17/06/2022

Funding

ACKNOWLEDGMENT This work has been funded in part by Academy of Finland ULTRA (n:o 328215) project.

Keywords

Neural Networks
Phase shifter resolution bits
Spectral efficiency loss model

Access to Document

10.1109/GPECOM55404.2022.9815775

Ghazalian_paperAccepted author manuscript, 1.51 MB

Cite this

Ghazalian, R., & Golipoor, S. (2022). A Study on the Effect of Phase Shifter Quantization Error on the Spectral Efficiency Using Neural Network. In Proceedings - 2022 IEEE 4th Global Power, Energy and Communication Conference, GPECOM 2022 (pp. 626-631). (Proceedings - IEEE Global Power, Energy and Communication Conference). IEEE. https://doi.org/10.1109/GPECOM55404.2022.9815775

@inproceedings{d635d0acd2944340970d22764363cf53,

title = "A Study on the Effect of Phase Shifter Quantization Error on the Spectral Efficiency Using Neural Network",

abstract = "Beamforming (BF) is the inevitable component of the recent communication systems, especially Millimeter wave (mmWave) systems. Thanks to the radio frequency (RF) and digital technologies, BF techniques are implemented in the both digital and analogue domains by using phase shifters (PS) networks. Adopting the digital PS, which has the finite resolution bits, leads to loss in the spectral efficiency (SE). Accordingly, in this paper, we extract the SE loss in a multi-user multiple inputs single output (MISO) system, which would be useful for practical prospective. To this end, we apply machine learning (ML) to extract the SE loss. Simulation results show that the extracted models have the desirable accuracy in the SE loss prediction.",

keywords = "Neural Networks, Phase shifter resolution bits, Spectral efficiency loss model",

author = "Reza Ghazalian and Sahar Golipoor",

note = "Funding Information: ACKNOWLEDGMENT This work has been funded in part by Academy of Finland ULTRA (n:o 328215) project. Publisher Copyright: {\textcopyright} 2022 IEEE.; IEEE Global Power, Energy and Communication Conference, GPECOM ; Conference date: 14-06-2022 Through 17-06-2022",

year = "2022",

month = jul,

day = "11",

doi = "10.1109/GPECOM55404.2022.9815775",

language = "English",

series = "Proceedings - IEEE Global Power, Energy and Communication Conference",

publisher = "IEEE",

pages = "626--631",

booktitle = "Proceedings - 2022 IEEE 4th Global Power, Energy and Communication Conference, GPECOM 2022",

address = "United States",

}

Ghazalian, R & Golipoor, S 2022, A Study on the Effect of Phase Shifter Quantization Error on the Spectral Efficiency Using Neural Network. in Proceedings - 2022 IEEE 4th Global Power, Energy and Communication Conference, GPECOM 2022. Proceedings - IEEE Global Power, Energy and Communication Conference, IEEE, pp. 626-631, IEEE Global Power, Energy and Communication Conference, Cappadocia, Türkiye, 14/06/2022. https://doi.org/10.1109/GPECOM55404.2022.9815775

A Study on the Effect of Phase Shifter Quantization Error on the Spectral Efficiency Using Neural Network. / Ghazalian, Reza; Golipoor, Sahar.
Proceedings - 2022 IEEE 4th Global Power, Energy and Communication Conference, GPECOM 2022. IEEE, 2022. p. 626-631 (Proceedings - IEEE Global Power, Energy and Communication Conference).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - A Study on the Effect of Phase Shifter Quantization Error on the Spectral Efficiency Using Neural Network

AU - Ghazalian, Reza

AU - Golipoor, Sahar

PY - 2022/7/11

Y1 - 2022/7/11

N2 - Beamforming (BF) is the inevitable component of the recent communication systems, especially Millimeter wave (mmWave) systems. Thanks to the radio frequency (RF) and digital technologies, BF techniques are implemented in the both digital and analogue domains by using phase shifters (PS) networks. Adopting the digital PS, which has the finite resolution bits, leads to loss in the spectral efficiency (SE). Accordingly, in this paper, we extract the SE loss in a multi-user multiple inputs single output (MISO) system, which would be useful for practical prospective. To this end, we apply machine learning (ML) to extract the SE loss. Simulation results show that the extracted models have the desirable accuracy in the SE loss prediction.

AB - Beamforming (BF) is the inevitable component of the recent communication systems, especially Millimeter wave (mmWave) systems. Thanks to the radio frequency (RF) and digital technologies, BF techniques are implemented in the both digital and analogue domains by using phase shifters (PS) networks. Adopting the digital PS, which has the finite resolution bits, leads to loss in the spectral efficiency (SE). Accordingly, in this paper, we extract the SE loss in a multi-user multiple inputs single output (MISO) system, which would be useful for practical prospective. To this end, we apply machine learning (ML) to extract the SE loss. Simulation results show that the extracted models have the desirable accuracy in the SE loss prediction.

KW - Neural Networks

KW - Phase shifter resolution bits

KW - Spectral efficiency loss model

UR - https://www.scopus.com/pages/publications/85134880130

U2 - 10.1109/GPECOM55404.2022.9815775

DO - 10.1109/GPECOM55404.2022.9815775

M3 - Conference article in proceedings

AN - SCOPUS:85134880130

T3 - Proceedings - IEEE Global Power, Energy and Communication Conference

SP - 626

EP - 631

BT - Proceedings - 2022 IEEE 4th Global Power, Energy and Communication Conference, GPECOM 2022

PB - IEEE

T2 - IEEE Global Power, Energy and Communication Conference

Y2 - 14 June 2022 through 17 June 2022

ER -

A Study on the Effect of Phase Shifter Quantization Error on the Spectral Efficiency Using Neural Network

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

ULTRA: Ubiquitous Localization, communication, and sensing infrastrucTuRe for Autonomous systems

Cite this

A Study on the Effect of Phase Shifter Quantization Error on the Spectral Efficiency Using Neural Network

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Projects

ULTRA: Ubiquitous Localization, communication, and sensing infrastrucTuRe for Autonomous systems

Cite this