Deep Reinforcement-Learning Based Power and Beamforming Coordination for IoT Underlying 5G Networks

Chiapin Wang; Cheng Lin Hsieh; Han Chi Gao

doi:10.1109/ICEIB53692.2021.9686442

Deep Reinforcement-Learning Based Power and Beamforming Coordination for IoT Underlying 5G Networks

Chiapin Wang^*, Cheng Lin Hsieh, Han Chi Gao

^*Corresponding author for this work

Department of Electrical Engineering

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

1 Citation (Scopus)

Abstract

When the Internet of Things (IoT) is employed for Device-to-Device (D2D) communications that underlies 5G cellular networks, cross-tier interferences is introduced without suitable coordination between cellular users and D2D communications. In this study, a power and beamforming coordination method is proposed based on deep reinforcement learning to reduce cross-tier interferences between cellular users and D2D communications to increase the overall network utility. Results from simulation show that the proposed scheme efficiently increases the total system utility for IoT underlying 5G cellular networks when compared with other existing schemes.

Original language	English
Title of host publication	2021 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2021
Editors	Teen-Hang Meen
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	20-22
Number of pages	3
ISBN (Electronic)	9781665437554
DOIs	https://doi.org/10.1109/ICEIB53692.2021.9686442
Publication status	Published - 2021
Event	2021 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2021 - Yilan, Taiwan Duration: 2021 Dec 10 → 2021 Dec 12

Publication series

Name	2021 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2021

Conference

Conference	2021 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2021
Country/Territory	Taiwan
City	Yilan
Period	2021/12/10 → 2021/12/12

Keywords

5G cellular networks
Beamforming
Deep Reinforcement learning
Device-to-Device (D2D) communication
Internet of Things (IoT)
Power control

ASJC Scopus subject areas

Computer Networks and Communications
Computer Science Applications
Hardware and Architecture
Information Systems
Information Systems and Management
Safety, Risk, Reliability and Quality

Access to Document

10.1109/ICEIB53692.2021.9686442

Cite this

Wang, C., Hsieh, C. L., & Gao, H. C. (2021). Deep Reinforcement-Learning Based Power and Beamforming Coordination for IoT Underlying 5G Networks. In T.-H. Meen (Ed.), 2021 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2021 (pp. 20-22). (2021 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICEIB53692.2021.9686442

Deep Reinforcement-Learning Based Power and Beamforming Coordination for IoT Underlying 5G Networks. / Wang, Chiapin; Hsieh, Cheng Lin; Gao, Han Chi.
2021 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2021. ed. / Teen-Hang Meen. Institute of Electrical and Electronics Engineers Inc., 2021. p. 20-22 (2021 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2021).

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

Wang, C, Hsieh, CL & Gao, HC 2021, Deep Reinforcement-Learning Based Power and Beamforming Coordination for IoT Underlying 5G Networks. in T-H Meen (ed.), 2021 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2021. 2021 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2021, Institute of Electrical and Electronics Engineers Inc., pp. 20-22, 2021 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2021, Yilan, Taiwan, 2021/12/10. https://doi.org/10.1109/ICEIB53692.2021.9686442

Wang C, Hsieh CL, Gao HC. Deep Reinforcement-Learning Based Power and Beamforming Coordination for IoT Underlying 5G Networks. In Meen TH, editor, 2021 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2021. Institute of Electrical and Electronics Engineers Inc. 2021. p. 20-22. (2021 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2021). doi: 10.1109/ICEIB53692.2021.9686442

Wang, Chiapin ; Hsieh, Cheng Lin ; Gao, Han Chi. / Deep Reinforcement-Learning Based Power and Beamforming Coordination for IoT Underlying 5G Networks. 2021 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2021. editor / Teen-Hang Meen. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 20-22 (2021 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2021).

@inproceedings{f02743070d864beeb59ee42c670eb38c,

title = "Deep Reinforcement-Learning Based Power and Beamforming Coordination for IoT Underlying 5G Networks",

abstract = "When the Internet of Things (IoT) is employed for Device-to-Device (D2D) communications that underlies 5G cellular networks, cross-tier interferences is introduced without suitable coordination between cellular users and D2D communications. In this study, a power and beamforming coordination method is proposed based on deep reinforcement learning to reduce cross-tier interferences between cellular users and D2D communications to increase the overall network utility. Results from simulation show that the proposed scheme efficiently increases the total system utility for IoT underlying 5G cellular networks when compared with other existing schemes.",

keywords = "5G cellular networks, Beamforming, Deep Reinforcement learning, Device-to-Device (D2D) communication, Internet of Things (IoT), Power control",

author = "Chiapin Wang and Hsieh, {Cheng Lin} and Gao, {Han Chi}",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2021 ; Conference date: 10-12-2021 Through 12-12-2021",

year = "2021",

doi = "10.1109/ICEIB53692.2021.9686442",

language = "English",

series = "2021 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2021",

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

pages = "20--22",

editor = "Teen-Hang Meen",

booktitle = "2021 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2021",

}

TY - GEN

T1 - Deep Reinforcement-Learning Based Power and Beamforming Coordination for IoT Underlying 5G Networks

AU - Wang, Chiapin

AU - Hsieh, Cheng Lin

AU - Gao, Han Chi

PY - 2021

Y1 - 2021

N2 - When the Internet of Things (IoT) is employed for Device-to-Device (D2D) communications that underlies 5G cellular networks, cross-tier interferences is introduced without suitable coordination between cellular users and D2D communications. In this study, a power and beamforming coordination method is proposed based on deep reinforcement learning to reduce cross-tier interferences between cellular users and D2D communications to increase the overall network utility. Results from simulation show that the proposed scheme efficiently increases the total system utility for IoT underlying 5G cellular networks when compared with other existing schemes.

AB - When the Internet of Things (IoT) is employed for Device-to-Device (D2D) communications that underlies 5G cellular networks, cross-tier interferences is introduced without suitable coordination between cellular users and D2D communications. In this study, a power and beamforming coordination method is proposed based on deep reinforcement learning to reduce cross-tier interferences between cellular users and D2D communications to increase the overall network utility. Results from simulation show that the proposed scheme efficiently increases the total system utility for IoT underlying 5G cellular networks when compared with other existing schemes.

KW - 5G cellular networks

KW - Beamforming

KW - Deep Reinforcement learning

KW - Device-to-Device (D2D) communication

KW - Internet of Things (IoT)

KW - Power control

UR - http://www.scopus.com/inward/record.url?scp=85125873009&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85125873009&partnerID=8YFLogxK

U2 - 10.1109/ICEIB53692.2021.9686442

DO - 10.1109/ICEIB53692.2021.9686442

M3 - Conference contribution

AN - SCOPUS:85125873009

T3 - 2021 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2021

SP - 20

EP - 22

BT - 2021 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2021

A2 - Meen, Teen-Hang

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2021

Y2 - 10 December 2021 through 12 December 2021

ER -

Deep Reinforcement-Learning Based Power and Beamforming Coordination for IoT Underlying 5G Networks

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this