Deep Reinforcement Learning based Access Control for Disaster Response Networks

Hang Zhou; Xiaoyan Wang; Masahiro Umehira; Xianfu Chen; Celimuge Wu; Yusheng Ji

doi:10.1109/GLOBECOM42002.2020.9322553

Deep Reinforcement Learning based Access Control for Disaster Response Networks

Hang Zhou, Xiaoyan Wang, Masahiro Umehira, Xianfu Chen, Celimuge Wu, Yusheng Ji

BA6401 Connectivity solutions

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

4 Citations (Scopus)

Abstract

After a disaster occurred, it is extremely important to reconstruct the network and provide the communication services to the victims immediately. Deploying MDRU (Movable and Deployable Resource Unit) in the disaster area, along with multiple access points to extend the service area of MDRU is a very promising solution. In this kind of heterogeneous disaster response networks, it is of great importance to minimize the packet delay from user terminals by performing optimal radio access control. In this paper, we propose a deep reinforcement learning based radio access control mechanism, which enables the smart relay selection and transmitting power control. We evaluate the performance by extensive simulations, and validate the superiority of the proposed mechanism by comparing with baseline schemes.

Original language	English
Title of host publication	2020 IEEE Global Communications Conference, GLOBECOM 2020
Subtitle of host publication	Proceedings
Publisher	IEEE Institute of Electrical and Electronic Engineers
Number of pages	6
ISBN (Electronic)	978-1-7281-8298-8
ISBN (Print)	978-1-7281-8299-5
DOIs	https://doi.org/10.1109/GLOBECOM42002.2020.9322553
Publication status	Published - Dec 2020
MoE publication type	A4 Article in a conference publication
Event	IEEE Global Communications Conference, GLOBECOM 2020: Online - Virtual, Taipei, Taiwan, Province of China Duration: 7 Dec 2020 → 11 Dec 2020

Publication series

Series	Globecom
ISSN	1930-529X

Conference

Conference	IEEE Global Communications Conference, GLOBECOM 2020
Country/Territory	Taiwan, Province of China
City	Taipei
Period	7/12/20 → 11/12/20

Funding

This research was supported in part by the JSPS Grant-in-Aid for Scientific Research (C) 20K11764, ROIS NII Open Collaborative Research 2020-20FA01, and The Telecommunications Advancement Foundation.

Keywords

Deep reinforcement learning
disaster response network

Access to Document

10.1109/GLOBECOM42002.2020.9322553

Cite this

@inproceedings{6d1f27dc401c40a2a6a2f23955da1e78,

title = "Deep Reinforcement Learning based Access Control for Disaster Response Networks",

abstract = "After a disaster occurred, it is extremely important to reconstruct the network and provide the communication services to the victims immediately. Deploying MDRU (Movable and Deployable Resource Unit) in the disaster area, along with multiple access points to extend the service area of MDRU is a very promising solution. In this kind of heterogeneous disaster response networks, it is of great importance to minimize the packet delay from user terminals by performing optimal radio access control. In this paper, we propose a deep reinforcement learning based radio access control mechanism, which enables the smart relay selection and transmitting power control. We evaluate the performance by extensive simulations, and validate the superiority of the proposed mechanism by comparing with baseline schemes.",

keywords = "Deep reinforcement learning, disaster response network",

author = "Hang Zhou and Xiaoyan Wang and Masahiro Umehira and Xianfu Chen and Celimuge Wu and Yusheng Ji",

note = "Funding Information: This research was supported in part by the JSPS Grant-in-Aid for Scientific Research (C) 20K11764, ROIS NII Open Collaborative Research 2020-20FA01, and The Telecommunications Advancement Foundation. Publisher Copyright: {\textcopyright} 2020 IEEE. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.; IEEE Global Communications Conference, GLOBECOM 2020 : Online ; Conference date: 07-12-2020 Through 11-12-2020",

year = "2020",

month = dec,

doi = "10.1109/GLOBECOM42002.2020.9322553",

language = "English",

isbn = "978-1-7281-8299-5",

series = "Globecom",

publisher = "IEEE Institute of Electrical and Electronic Engineers",

booktitle = "2020 IEEE Global Communications Conference, GLOBECOM 2020",

address = "United States",

}

Zhou, H, Wang, X, Umehira, M, Chen, X, Wu, C & Ji, Y 2020, Deep Reinforcement Learning based Access Control for Disaster Response Networks. in 2020 IEEE Global Communications Conference, GLOBECOM 2020: Proceedings., 9322553, IEEE Institute of Electrical and Electronic Engineers, Globecom, IEEE Global Communications Conference, GLOBECOM 2020, Taipei, Taiwan, Province of China, 7/12/20. https://doi.org/10.1109/GLOBECOM42002.2020.9322553

Deep Reinforcement Learning based Access Control for Disaster Response Networks. / Zhou, Hang; Wang, Xiaoyan; Umehira, Masahiro et al.
2020 IEEE Global Communications Conference, GLOBECOM 2020: Proceedings. IEEE Institute of Electrical and Electronic Engineers, 2020. 9322553 (Globecom).

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

TY - GEN

T1 - Deep Reinforcement Learning based Access Control for Disaster Response Networks

AU - Zhou, Hang

AU - Wang, Xiaoyan

AU - Umehira, Masahiro

AU - Chen, Xianfu

AU - Wu, Celimuge

AU - Ji, Yusheng

N1 - Funding Information: This research was supported in part by the JSPS Grant-in-Aid for Scientific Research (C) 20K11764, ROIS NII Open Collaborative Research 2020-20FA01, and The Telecommunications Advancement Foundation. Publisher Copyright: © 2020 IEEE. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.

PY - 2020/12

Y1 - 2020/12

N2 - After a disaster occurred, it is extremely important to reconstruct the network and provide the communication services to the victims immediately. Deploying MDRU (Movable and Deployable Resource Unit) in the disaster area, along with multiple access points to extend the service area of MDRU is a very promising solution. In this kind of heterogeneous disaster response networks, it is of great importance to minimize the packet delay from user terminals by performing optimal radio access control. In this paper, we propose a deep reinforcement learning based radio access control mechanism, which enables the smart relay selection and transmitting power control. We evaluate the performance by extensive simulations, and validate the superiority of the proposed mechanism by comparing with baseline schemes.

AB - After a disaster occurred, it is extremely important to reconstruct the network and provide the communication services to the victims immediately. Deploying MDRU (Movable and Deployable Resource Unit) in the disaster area, along with multiple access points to extend the service area of MDRU is a very promising solution. In this kind of heterogeneous disaster response networks, it is of great importance to minimize the packet delay from user terminals by performing optimal radio access control. In this paper, we propose a deep reinforcement learning based radio access control mechanism, which enables the smart relay selection and transmitting power control. We evaluate the performance by extensive simulations, and validate the superiority of the proposed mechanism by comparing with baseline schemes.

KW - Deep reinforcement learning

KW - disaster response network

UR - http://www.scopus.com/inward/record.url?scp=85100431880&partnerID=8YFLogxK

U2 - 10.1109/GLOBECOM42002.2020.9322553

DO - 10.1109/GLOBECOM42002.2020.9322553

M3 - Conference article in proceedings

AN - SCOPUS:85100431880

SN - 978-1-7281-8299-5

T3 - Globecom

BT - 2020 IEEE Global Communications Conference, GLOBECOM 2020

PB - IEEE Institute of Electrical and Electronic Engineers

T2 - IEEE Global Communications Conference, GLOBECOM 2020

Y2 - 7 December 2020 through 11 December 2020

ER -

Deep Reinforcement Learning based Access Control for Disaster Response Networks

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

MISSION: Mission-Critical Internet of Things Applications over Fog Networks

Cite this

Deep Reinforcement Learning based Access Control for Disaster Response Networks

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Projects

MISSION: Mission-Critical Internet of Things Applications over Fog Networks

Cite this