Spectrum Management with Congestion Avoidance for V2X Based on Multi-Agent Reinforcement Learning

Ibrahim Althamary; Jun Yong Lin; Chih Wei Huang

doi:10.1109/GCWkshps50303.2020.9367564

Spectrum Management with Congestion Avoidance for V2X Based on Multi-Agent Reinforcement Learning

Ibrahim Althamary, Jun Yong Lin, Chih Wei Huang

Department of Communication Engineering

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

2 Scopus citations

Abstract

Multi-agent reinforcement learning (MARL) for vehicular communication management is an emerging topic attracting considerable research attention. In this paper, to enhance the system throughput and spectrum efficiency, the vehicular agents can select different transmission modes, power, and sub-channels to maximize the overall system throughput in a decentralized manner. We propose a novel MARL resource allocation algorithm capable of congestion avoidance for vehicular networks with a multi-agent extension of advantage actorcritic (A2C). The cooperative action and congestion avoidance are achieved by global rewards and a unique dump channel respectively. Moreover, comparison with landmark schemes is conducted on the realistic setup. The result shows that the agent achieves favorable performance with the proposed scheme to the environment.

Original language	English
Title of host publication	2020 IEEE Globecom Workshops, GC Wkshps 2020 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728173078
DOIs	https://doi.org/10.1109/GCWkshps50303.2020.9367564
State	Published - Dec 2020
Event	2020 IEEE Globecom Workshops, GC Wkshps 2020 - Virtual, Taipei, Taiwan Duration: 7 Dec 2020 → 11 Dec 2020

Publication series

Name	2020 IEEE Globecom Workshops, GC Wkshps 2020 - Proceedings

Conference

Conference	2020 IEEE Globecom Workshops, GC Wkshps 2020
Country/Territory	Taiwan
City	Virtual, Taipei
Period	7/12/20 → 11/12/20

Keywords

5G
Multi-agent reinforcement learning (MARL)
resource allocation
spectrum management
vehicle-to-everything (V2X)

Access to Document

10.1109/GCWkshps50303.2020.9367564

Cite this

Althamary, I., Lin, J. Y., & Huang, C. W. (2020). Spectrum Management with Congestion Avoidance for V2X Based on Multi-Agent Reinforcement Learning. In 2020 IEEE Globecom Workshops, GC Wkshps 2020 - Proceedings Article 367564 (2020 IEEE Globecom Workshops, GC Wkshps 2020 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GCWkshps50303.2020.9367564

@inproceedings{fb2276f0ddf2482db7461674ad692744,

title = "Spectrum Management with Congestion Avoidance for V2X Based on Multi-Agent Reinforcement Learning",

abstract = "Multi-agent reinforcement learning (MARL) for vehicular communication management is an emerging topic attracting considerable research attention. In this paper, to enhance the system throughput and spectrum efficiency, the vehicular agents can select different transmission modes, power, and sub-channels to maximize the overall system throughput in a decentralized manner. We propose a novel MARL resource allocation algorithm capable of congestion avoidance for vehicular networks with a multi-agent extension of advantage actorcritic (A2C). The cooperative action and congestion avoidance are achieved by global rewards and a unique dump channel respectively. Moreover, comparison with landmark schemes is conducted on the realistic setup. The result shows that the agent achieves favorable performance with the proposed scheme to the environment.",

keywords = "5G, Multi-agent reinforcement learning (MARL), resource allocation, spectrum management, vehicle-to-everything (V2X)",

author = "Ibrahim Althamary and Lin, {Jun Yong} and Huang, {Chih Wei}",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE Globecom Workshops, GC Wkshps 2020 ; Conference date: 07-12-2020 Through 11-12-2020",

year = "2020",

month = dec,

doi = "10.1109/GCWkshps50303.2020.9367564",

language = "???core.languages.en_GB???",

series = "2020 IEEE Globecom Workshops, GC Wkshps 2020 - Proceedings",

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

booktitle = "2020 IEEE Globecom Workshops, GC Wkshps 2020 - Proceedings",

}

Althamary, I, Lin, JY & Huang, CW 2020, Spectrum Management with Congestion Avoidance for V2X Based on Multi-Agent Reinforcement Learning. in 2020 IEEE Globecom Workshops, GC Wkshps 2020 - Proceedings., 367564, 2020 IEEE Globecom Workshops, GC Wkshps 2020 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2020 IEEE Globecom Workshops, GC Wkshps 2020, Virtual, Taipei, Taiwan, 7/12/20. https://doi.org/10.1109/GCWkshps50303.2020.9367564

Spectrum Management with Congestion Avoidance for V2X Based on Multi-Agent Reinforcement Learning. / Althamary, Ibrahim; Lin, Jun Yong; Huang, Chih Wei.
2020 IEEE Globecom Workshops, GC Wkshps 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. 367564 (2020 IEEE Globecom Workshops, GC Wkshps 2020 - Proceedings).

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

TY - GEN

T1 - Spectrum Management with Congestion Avoidance for V2X Based on Multi-Agent Reinforcement Learning

AU - Althamary, Ibrahim

AU - Lin, Jun Yong

AU - Huang, Chih Wei

PY - 2020/12

Y1 - 2020/12

N2 - Multi-agent reinforcement learning (MARL) for vehicular communication management is an emerging topic attracting considerable research attention. In this paper, to enhance the system throughput and spectrum efficiency, the vehicular agents can select different transmission modes, power, and sub-channels to maximize the overall system throughput in a decentralized manner. We propose a novel MARL resource allocation algorithm capable of congestion avoidance for vehicular networks with a multi-agent extension of advantage actorcritic (A2C). The cooperative action and congestion avoidance are achieved by global rewards and a unique dump channel respectively. Moreover, comparison with landmark schemes is conducted on the realistic setup. The result shows that the agent achieves favorable performance with the proposed scheme to the environment.

AB - Multi-agent reinforcement learning (MARL) for vehicular communication management is an emerging topic attracting considerable research attention. In this paper, to enhance the system throughput and spectrum efficiency, the vehicular agents can select different transmission modes, power, and sub-channels to maximize the overall system throughput in a decentralized manner. We propose a novel MARL resource allocation algorithm capable of congestion avoidance for vehicular networks with a multi-agent extension of advantage actorcritic (A2C). The cooperative action and congestion avoidance are achieved by global rewards and a unique dump channel respectively. Moreover, comparison with landmark schemes is conducted on the realistic setup. The result shows that the agent achieves favorable performance with the proposed scheme to the environment.

KW - 5G

KW - Multi-agent reinforcement learning (MARL)

KW - resource allocation

KW - spectrum management

KW - vehicle-to-everything (V2X)

UR - http://www.scopus.com/inward/record.url?scp=85102920504&partnerID=8YFLogxK

U2 - 10.1109/GCWkshps50303.2020.9367564

DO - 10.1109/GCWkshps50303.2020.9367564

M3 - 會議論文篇章

AN - SCOPUS:85102920504

T3 - 2020 IEEE Globecom Workshops, GC Wkshps 2020 - Proceedings

BT - 2020 IEEE Globecom Workshops, GC Wkshps 2020 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 IEEE Globecom Workshops, GC Wkshps 2020

Y2 - 7 December 2020 through 11 December 2020

ER -

Spectrum Management with Congestion Avoidance for V2X Based on Multi-Agent Reinforcement Learning

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this