Contextual Multi-Armed Bandit based Beam Allocation in mmWave V2X Communication under Blockage

Abdulkadir Kose; Haeyoung Lee; Chuan Heng Foh

doi:10.1109/VTC2023-Spring57618.2023.10200248

Contextual Multi-Armed Bandit based Beam Allocation in mmWave V2X Communication under Blockage

Abdulkadir Kose, Haeyoung Lee, Chuan Heng Foh

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

17 Downloads (Pure)

Abstract

Due to its low latency and high data rates support, mmWave communication has been an important player for vehicular communication. However, this carries some disadvantages such as lower transmission distances and inability to transmit through obstacles. This work presents a Contextual Multi-Armed Bandit Algorithm based beam selection to improve connection stability in next generation communications for vehicular networks. The algorithm, through machine learning (ML), learns about the mobility contexts of the vehicles (location and route) and helps the base station make decisions on which of its beam sectors will provide connection to a vehicle. In addition, the proposed algorithm also smartly extends, via relay vehicles, beam coverage to outage vehicles which are either in NLOS condition due to blockages or not served any available beam. Through a set of experiments on the city map, the effectiveness of the algorithm is demonstrated, and the best possible solution is presented.

Original language	English
Title of host publication	2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring) - Proceedings
Place of Publication	USA
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Number of pages	6
ISBN (Electronic)	9798350311143
DOIs	https://doi.org/10.1109/VTC2023-Spring57618.2023.10200248
Publication status	Published - 14 Aug 2023
Event	2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring) - Florence, Italy Duration: 20 Jun 2023 → 23 Jun 2023 Conference number: 97 https://ieeexplore.ieee.org/xpl/conhome/10199114/proceeding

Publication series

Name	IEEE Vehicular Technology Conference
Volume	2023-June
ISSN (Print)	1550-2252
ISSN (Electronic)	2577-2465

Conference

Conference	2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring)
Abbreviated title	VTC2023
Country/Territory	Italy
City	Florence
Period	20/06/23 → 23/06/23
Internet address	https://ieeexplore.ieee.org/xpl/conhome/10199114/proceeding

Keywords

V2X
beam allocation
mmWave networks

Access to Document

10.1109/VTC2023-Spring57618.2023.10200248Licence: Unspecified

Accepted_Manuscript
© 2023, IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. This is the accepted manuscript version of a conference paper which has been published in final form at https://doi.org/10.1109/VTC2023-Spring57618.2023.10200248
Accepted author manuscript, 494 KBLicence: Unspecified

Cite this

Kose, A., Lee, H., & Foh, C. H. (2023). Contextual Multi-Armed Bandit based Beam Allocation in mmWave V2X Communication under Blockage. In 2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring) - Proceedings Article 10200248 (IEEE Vehicular Technology Conference; Vol. 2023-June). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/VTC2023-Spring57618.2023.10200248

@inproceedings{fd38e3afa9c74c25b0c553332128d64b,

title = "Contextual Multi-Armed Bandit based Beam Allocation in mmWave V2X Communication under Blockage",

abstract = "Due to its low latency and high data rates support, mmWave communication has been an important player for vehicular communication. However, this carries some disadvantages such as lower transmission distances and inability to transmit through obstacles. This work presents a Contextual Multi-Armed Bandit Algorithm based beam selection to improve connection stability in next generation communications for vehicular networks. The algorithm, through machine learning (ML), learns about the mobility contexts of the vehicles (location and route) and helps the base station make decisions on which of its beam sectors will provide connection to a vehicle. In addition, the proposed algorithm also smartly extends, via relay vehicles, beam coverage to outage vehicles which are either in NLOS condition due to blockages or not served any available beam. Through a set of experiments on the city map, the effectiveness of the algorithm is demonstrated, and the best possible solution is presented.",

keywords = "V2X, beam allocation, mmWave networks",

author = "Abdulkadir Kose and Haeyoung Lee and Foh, {Chuan Heng}",

note = "{\textcopyright} 2023, IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. This is the accepted manuscript version of a conference paper which has been published in final form at https://doi.org/10.1109/VTC2023-Spring57618.2023.10200248; 2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring), VTC2023 ; Conference date: 20-06-2023 Through 23-06-2023",

year = "2023",

month = aug,

day = "14",

doi = "10.1109/VTC2023-Spring57618.2023.10200248",

language = "English",

series = "IEEE Vehicular Technology Conference",

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

booktitle = "2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring) - Proceedings",

address = "United States",

url = "https://ieeexplore.ieee.org/xpl/conhome/10199114/proceeding",

}

Kose, A, Lee, H & Foh, CH 2023, Contextual Multi-Armed Bandit based Beam Allocation in mmWave V2X Communication under Blockage. in 2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring) - Proceedings., 10200248, IEEE Vehicular Technology Conference, vol. 2023-June, Institute of Electrical and Electronics Engineers (IEEE), USA, 2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring), Florence, Italy, 20/06/23. https://doi.org/10.1109/VTC2023-Spring57618.2023.10200248

Contextual Multi-Armed Bandit based Beam Allocation in mmWave V2X Communication under Blockage. / Kose, Abdulkadir; Lee, Haeyoung; Foh, Chuan Heng.
2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring) - Proceedings. USA: Institute of Electrical and Electronics Engineers (IEEE), 2023. 10200248 (IEEE Vehicular Technology Conference; Vol. 2023-June).

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

TY - GEN

T1 - Contextual Multi-Armed Bandit based Beam Allocation in mmWave V2X Communication under Blockage

AU - Kose, Abdulkadir

AU - Lee, Haeyoung

AU - Foh, Chuan Heng

N1 - Conference code: 97

PY - 2023/8/14

Y1 - 2023/8/14

N2 - Due to its low latency and high data rates support, mmWave communication has been an important player for vehicular communication. However, this carries some disadvantages such as lower transmission distances and inability to transmit through obstacles. This work presents a Contextual Multi-Armed Bandit Algorithm based beam selection to improve connection stability in next generation communications for vehicular networks. The algorithm, through machine learning (ML), learns about the mobility contexts of the vehicles (location and route) and helps the base station make decisions on which of its beam sectors will provide connection to a vehicle. In addition, the proposed algorithm also smartly extends, via relay vehicles, beam coverage to outage vehicles which are either in NLOS condition due to blockages or not served any available beam. Through a set of experiments on the city map, the effectiveness of the algorithm is demonstrated, and the best possible solution is presented.

AB - Due to its low latency and high data rates support, mmWave communication has been an important player for vehicular communication. However, this carries some disadvantages such as lower transmission distances and inability to transmit through obstacles. This work presents a Contextual Multi-Armed Bandit Algorithm based beam selection to improve connection stability in next generation communications for vehicular networks. The algorithm, through machine learning (ML), learns about the mobility contexts of the vehicles (location and route) and helps the base station make decisions on which of its beam sectors will provide connection to a vehicle. In addition, the proposed algorithm also smartly extends, via relay vehicles, beam coverage to outage vehicles which are either in NLOS condition due to blockages or not served any available beam. Through a set of experiments on the city map, the effectiveness of the algorithm is demonstrated, and the best possible solution is presented.

KW - V2X

KW - beam allocation

KW - mmWave networks

UR - http://www.scopus.com/inward/record.url?scp=85169840833&partnerID=8YFLogxK

U2 - 10.1109/VTC2023-Spring57618.2023.10200248

DO - 10.1109/VTC2023-Spring57618.2023.10200248

M3 - Conference contribution

T3 - IEEE Vehicular Technology Conference

BT - 2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring) - Proceedings

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - USA

T2 - 2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring)

Y2 - 20 June 2023 through 23 June 2023

ER -

Contextual Multi-Armed Bandit based Beam Allocation in mmWave V2X Communication under Blockage

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this