Machine Learning based Beamwidth Adaptation for mmWave Vehicular Communications

Setinder Manic; Chuan Heng Foh; Abdulkadir Kose; Haeyoung Lee; Chee Yen Leow; Klaus Moessner; Chakkaphong Suthaputchakun

doi:10.1109/MICC59384.2023.10419542

Machine Learning based Beamwidth Adaptation for mmWave Vehicular Communications

Setinder Manic, Chuan Heng Foh, Abdulkadir Kose, Haeyoung Lee, Chee Yen Leow, Klaus Moessner, Chakkaphong Suthaputchakun

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

7 Downloads (Pure)

Abstract

The incorporation of mmWave technology in vehicular networks has unlocked a realm of possibilities, propelling the advancement of autonomous vehicles,enhancing interconnectedness, and facilitating communication for intelligent transportation systems (ITS). Despite these strides in connectivity, challenges such as high path-loss have arisen, impacting existing beam management procedures. This work aims to address this issue by improving beam management techniques, specifically focusing on enhancing the service time between vehicles and base stations through adaptive mmWave beamwidth adjustments, accomplished using a Contextual Multi-Armed Bandit Algorithm. By leveraging various conditions to train the ML agent of the Contextual Multi-Armed Bandit Algorithm, it seeks to learn about vehicle mobility profiles and optimize the usage of differentantenna beamwidth settings to maximize seamless connection time. The extensive simulation results showcase the effectiveness of an adaptive beamwidth for mobility profiles, extending the connection time a vehicle experiences with a base station when compared to the existing strategies.

Original language	English
Title of host publication	2023 IEEE 16th Malaysia International Conference on Communication
Subtitle of host publication	Smart Digital Communication for Humanity, MICC 2023 - Proceedings
Editors	Mohd Fais Mansor, Nor Aishah Muhammad
Place of Publication	Kuala Lumpur, Malaysia
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	80-85
Number of pages	6
ISBN (Electronic)	979-8-3503-0434-3
DOIs	https://doi.org/10.1109/MICC59384.2023.10419542
Publication status	Published - 12 Feb 2024
Event	16th IEEE Malaysia International Conference on Communications 2023 (MICC 2023) - Concorde Hotel Kuala Lumpur, Lumpur, Malaysia Duration: 10 Dec 2023 → 12 Dec 2023 Conference number: 16 https://micc2023.mycomvt.info/about-micc2023/

Publication series

Name	2023 IEEE 16th Malaysia International Conference on Communication: Smart Digital Communication for Humanity, MICC 2023 - Proceedings

Conference

Conference	16th IEEE Malaysia International Conference on Communications 2023 (MICC 2023)
Abbreviated title	MICC2023
Country/Territory	Malaysia
City	Lumpur
Period	10/12/23 → 12/12/23
Internet address	https://micc2023.mycomvt.info/about-micc2023/

Keywords

V2X
beamwidth adaptation
mmWave

Access to Document

10.1109/MICC59384.2023.10419542

Accepted_Manuscript
© 2023, IEEE. This is the accepted manuscript version of an article which has been published in final form at https://doi.org/10.1109/MICC59384.2023.10419542
Accepted author manuscript, 268 KBLicence: CC BY

Cite this

Manic, S., Foh, C. H., Kose, A., Lee, H., Leow, C. Y., Moessner, K., & Suthaputchakun, C. (2024). Machine Learning based Beamwidth Adaptation for mmWave Vehicular Communications. In M. F. Mansor, & N. A. Muhammad (Eds.), 2023 IEEE 16th Malaysia International Conference on Communication: Smart Digital Communication for Humanity, MICC 2023 - Proceedings (pp. 80-85). (2023 IEEE 16th Malaysia International Conference on Communication: Smart Digital Communication for Humanity, MICC 2023 - Proceedings). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/MICC59384.2023.10419542

Manic, Setinder ; Foh, Chuan Heng ; Kose, Abdulkadir et al. / Machine Learning based Beamwidth Adaptation for mmWave Vehicular Communications. 2023 IEEE 16th Malaysia International Conference on Communication: Smart Digital Communication for Humanity, MICC 2023 - Proceedings. editor / Mohd Fais Mansor ; Nor Aishah Muhammad. Kuala Lumpur, Malaysia : Institute of Electrical and Electronics Engineers (IEEE), 2024. pp. 80-85 (2023 IEEE 16th Malaysia International Conference on Communication: Smart Digital Communication for Humanity, MICC 2023 - Proceedings).

@inproceedings{15aa463508f245bab9993fa5e0f50685,

title = "Machine Learning based Beamwidth Adaptation for mmWave Vehicular Communications",

abstract = "The incorporation of mmWave technology in vehicular networks has unlocked a realm of possibilities, propelling the advancement of autonomous vehicles,enhancing interconnectedness, and facilitating communication for intelligent transportation systems (ITS). Despite these strides in connectivity, challenges such as high path-loss have arisen, impacting existing beam management procedures. This work aims to address this issue by improving beam management techniques, specifically focusing on enhancing the service time between vehicles and base stations through adaptive mmWave beamwidth adjustments, accomplished using a Contextual Multi-Armed Bandit Algorithm. By leveraging various conditions to train the ML agent of the Contextual Multi-Armed Bandit Algorithm, it seeks to learn about vehicle mobility profiles and optimize the usage of differentantenna beamwidth settings to maximize seamless connection time. The extensive simulation results showcase the effectiveness of an adaptive beamwidth for mobility profiles, extending the connection time a vehicle experiences with a base station when compared to the existing strategies. ",

keywords = "V2X, beamwidth adaptation, mmWave",

author = "Setinder Manic and Foh, {Chuan Heng} and Abdulkadir Kose and Haeyoung Lee and Leow, {Chee Yen} and Klaus Moessner and Chakkaphong Suthaputchakun",

note = "{\textcopyright} 2023, IEEE. This is the accepted manuscript version of an article which has been published in final form at https://doi.org/10.1109/MICC59384.2023.10419542; 16th IEEE Malaysia International Conference on Communications 2023 (MICC 2023), MICC2023 ; Conference date: 10-12-2023 Through 12-12-2023",

year = "2024",

month = feb,

day = "12",

doi = "10.1109/MICC59384.2023.10419542",

language = "English",

series = "2023 IEEE 16th Malaysia International Conference on Communication: Smart Digital Communication for Humanity, MICC 2023 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "80--85",

editor = "Mansor, {Mohd Fais} and Muhammad, {Nor Aishah}",

booktitle = "2023 IEEE 16th Malaysia International Conference on Communication",

address = "United States",

url = "https://micc2023.mycomvt.info/about-micc2023/",

}

Manic, S, Foh, CH, Kose, A, Lee, H, Leow, CY, Moessner, K & Suthaputchakun, C 2024, Machine Learning based Beamwidth Adaptation for mmWave Vehicular Communications. in MF Mansor & NA Muhammad (eds), 2023 IEEE 16th Malaysia International Conference on Communication: Smart Digital Communication for Humanity, MICC 2023 - Proceedings. 2023 IEEE 16th Malaysia International Conference on Communication: Smart Digital Communication for Humanity, MICC 2023 - Proceedings, Institute of Electrical and Electronics Engineers (IEEE), Kuala Lumpur, Malaysia, pp. 80-85, 16th IEEE Malaysia International Conference on Communications 2023 (MICC 2023), Lumpur, Malaysia, 10/12/23. https://doi.org/10.1109/MICC59384.2023.10419542

Machine Learning based Beamwidth Adaptation for mmWave Vehicular Communications. / Manic, Setinder; Foh, Chuan Heng; Kose, Abdulkadir et al.
2023 IEEE 16th Malaysia International Conference on Communication: Smart Digital Communication for Humanity, MICC 2023 - Proceedings. ed. / Mohd Fais Mansor; Nor Aishah Muhammad. Kuala Lumpur, Malaysia: Institute of Electrical and Electronics Engineers (IEEE), 2024. p. 80-85 (2023 IEEE 16th Malaysia International Conference on Communication: Smart Digital Communication for Humanity, MICC 2023 - Proceedings).

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

TY - GEN

T1 - Machine Learning based Beamwidth Adaptation for mmWave Vehicular Communications

AU - Manic, Setinder

AU - Foh, Chuan Heng

AU - Kose, Abdulkadir

AU - Lee, Haeyoung

AU - Leow, Chee Yen

AU - Moessner, Klaus

AU - Suthaputchakun, Chakkaphong

N1 - Conference code: 16

PY - 2024/2/12

Y1 - 2024/2/12

N2 - The incorporation of mmWave technology in vehicular networks has unlocked a realm of possibilities, propelling the advancement of autonomous vehicles,enhancing interconnectedness, and facilitating communication for intelligent transportation systems (ITS). Despite these strides in connectivity, challenges such as high path-loss have arisen, impacting existing beam management procedures. This work aims to address this issue by improving beam management techniques, specifically focusing on enhancing the service time between vehicles and base stations through adaptive mmWave beamwidth adjustments, accomplished using a Contextual Multi-Armed Bandit Algorithm. By leveraging various conditions to train the ML agent of the Contextual Multi-Armed Bandit Algorithm, it seeks to learn about vehicle mobility profiles and optimize the usage of differentantenna beamwidth settings to maximize seamless connection time. The extensive simulation results showcase the effectiveness of an adaptive beamwidth for mobility profiles, extending the connection time a vehicle experiences with a base station when compared to the existing strategies.

AB - The incorporation of mmWave technology in vehicular networks has unlocked a realm of possibilities, propelling the advancement of autonomous vehicles,enhancing interconnectedness, and facilitating communication for intelligent transportation systems (ITS). Despite these strides in connectivity, challenges such as high path-loss have arisen, impacting existing beam management procedures. This work aims to address this issue by improving beam management techniques, specifically focusing on enhancing the service time between vehicles and base stations through adaptive mmWave beamwidth adjustments, accomplished using a Contextual Multi-Armed Bandit Algorithm. By leveraging various conditions to train the ML agent of the Contextual Multi-Armed Bandit Algorithm, it seeks to learn about vehicle mobility profiles and optimize the usage of differentantenna beamwidth settings to maximize seamless connection time. The extensive simulation results showcase the effectiveness of an adaptive beamwidth for mobility profiles, extending the connection time a vehicle experiences with a base station when compared to the existing strategies.

KW - V2X

KW - beamwidth adaptation

KW - mmWave

UR - http://www.scopus.com/inward/record.url?scp=85186122114&partnerID=8YFLogxK

U2 - 10.1109/MICC59384.2023.10419542

DO - 10.1109/MICC59384.2023.10419542

M3 - Conference contribution

T3 - 2023 IEEE 16th Malaysia International Conference on Communication: Smart Digital Communication for Humanity, MICC 2023 - Proceedings

SP - 80

EP - 85

BT - 2023 IEEE 16th Malaysia International Conference on Communication

A2 - Mansor, Mohd Fais

A2 - Muhammad, Nor Aishah

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Kuala Lumpur, Malaysia

T2 - 16th IEEE Malaysia International Conference on Communications 2023 (MICC 2023)

Y2 - 10 December 2023 through 12 December 2023

ER -

Manic S, Foh CH, Kose A, Lee H, Leow CY, Moessner K et al. Machine Learning based Beamwidth Adaptation for mmWave Vehicular Communications. In Mansor MF, Muhammad NA, editors, 2023 IEEE 16th Malaysia International Conference on Communication: Smart Digital Communication for Humanity, MICC 2023 - Proceedings. Kuala Lumpur, Malaysia: Institute of Electrical and Electronics Engineers (IEEE). 2024. p. 80-85. (2023 IEEE 16th Malaysia International Conference on Communication: Smart Digital Communication for Humanity, MICC 2023 - Proceedings). doi: 10.1109/MICC59384.2023.10419542

Machine Learning based Beamwidth Adaptation for mmWave Vehicular Communications

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this