Multi-Agent Deep Reinforcement Learning for Distributed Resource Management in Wirelessly Powered Communication Networks

Sangwon Hwang; Hanjin Kim; Hoon Lee; Inkyu Lee

doi:10.1109/TVT.2020.3029609

Multi-Agent Deep Reinforcement Learning for Distributed Resource Management in Wirelessly Powered Communication Networks

Sangwon Hwang, Hanjin Kim, Hoon Lee, Inkyu Lee

Research output: Contribution to journal › Article › peer-review

29 Citations (Scopus)

Abstract

This paper studies multi-agent deep reinforcement learning (MADRL) based resource allocation methods for multi-cell wireless powered communication networks (WPCNs) where multiple hybrid access points (H-APs) wirelessly charge energy-limited users to collect data from them. We design a distributed reinforcement learning strategy where H-APs individually determine time and power allocation variables. Unlike traditional centralized optimization algorithms which require global information collected at a central unit, the proposed MADRL technique models an H-AP as an agent producing its action based only on its own locally observable states. Numerical results verify that the proposed approach can achieve comparable performance of the centralized algorithms.

Original language	English
Article number	9217951
Pages (from-to)	14055-14060
Number of pages	6
Journal	IEEE Transactions on Vehicular Technology
Volume	69
Issue number	11
DOIs	https://doi.org/10.1109/TVT.2020.3029609
Publication status	Published - 2020 Nov

Bibliographical note

Funding Information:
Manuscript received August 28, 2020; revised September 29, 2020; accepted September 30, 2020. Date of publication October 8, 2020; date of current version November 12, 2020. This work was supported in part by the National Research Foundation (NRF) through the Ministry of Science, ICT, and Future Planning (MSIP), Korea Government under Grant 2017R1A2B3012316 and in part by the NRF through the Ministry of Science, ICT (MSIT), Korea Government under Grant 2019R1F1A1060648. The review of this article was coordinated by Dr. Zubair Fadlullah. (Corresponding author: Inkyu Lee.) Sangwon Hwang and Inkyu Lee are with the School of Electrical Engineering, Korea University, Seoul 02841, Korea (e-mail: [email protected]; [email protected]).

Publisher Copyright:
© 1967-2012 IEEE.

Keywords

Wireless powered communication networks
actor-critic method
multi-agent deep reinforcement learning

ASJC Scopus subject areas

Automotive Engineering
Aerospace Engineering
Electrical and Electronic Engineering
Applied Mathematics

Access to Document

10.1109/TVT.2020.3029609

Cite this

@article{eec2e94addec4f619bc571893e70996c,

title = "Multi-Agent Deep Reinforcement Learning for Distributed Resource Management in Wirelessly Powered Communication Networks",

abstract = "This paper studies multi-agent deep reinforcement learning (MADRL) based resource allocation methods for multi-cell wireless powered communication networks (WPCNs) where multiple hybrid access points (H-APs) wirelessly charge energy-limited users to collect data from them. We design a distributed reinforcement learning strategy where H-APs individually determine time and power allocation variables. Unlike traditional centralized optimization algorithms which require global information collected at a central unit, the proposed MADRL technique models an H-AP as an agent producing its action based only on its own locally observable states. Numerical results verify that the proposed approach can achieve comparable performance of the centralized algorithms.",

keywords = "Wireless powered communication networks, actor-critic method, multi-agent deep reinforcement learning",

author = "Sangwon Hwang and Hanjin Kim and Hoon Lee and Inkyu Lee",

note = "Funding Information: Manuscript received August 28, 2020; revised September 29, 2020; accepted September 30, 2020. Date of publication October 8, 2020; date of current version November 12, 2020. This work was supported in part by the National Research Foundation (NRF) through the Ministry of Science, ICT, and Future Planning (MSIP), Korea Government under Grant 2017R1A2B3012316 and in part by the NRF through the Ministry of Science, ICT (MSIT), Korea Government under Grant 2019R1F1A1060648. The review of this article was coordinated by Dr. Zubair Fadlullah. (Corresponding author: Inkyu Lee.) Sangwon Hwang and Inkyu Lee are with the School of Electrical Engineering, Korea University, Seoul 02841, Korea (e-mail: [email protected]; [email protected]). Publisher Copyright: {\textcopyright} 1967-2012 IEEE.",

year = "2020",

month = nov,

doi = "10.1109/TVT.2020.3029609",

language = "English",

volume = "69",

pages = "14055--14060",

journal = "IEEE Transactions on Vehicular Technology",

issn = "0018-9545",

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

number = "11",

}

TY - JOUR

T1 - Multi-Agent Deep Reinforcement Learning for Distributed Resource Management in Wirelessly Powered Communication Networks

AU - Hwang, Sangwon

AU - Kim, Hanjin

AU - Lee, Hoon

AU - Lee, Inkyu

N1 - Funding Information: Manuscript received August 28, 2020; revised September 29, 2020; accepted September 30, 2020. Date of publication October 8, 2020; date of current version November 12, 2020. This work was supported in part by the National Research Foundation (NRF) through the Ministry of Science, ICT, and Future Planning (MSIP), Korea Government under Grant 2017R1A2B3012316 and in part by the NRF through the Ministry of Science, ICT (MSIT), Korea Government under Grant 2019R1F1A1060648. The review of this article was coordinated by Dr. Zubair Fadlullah. (Corresponding author: Inkyu Lee.) Sangwon Hwang and Inkyu Lee are with the School of Electrical Engineering, Korea University, Seoul 02841, Korea (e-mail: [email protected]; [email protected]). Publisher Copyright: © 1967-2012 IEEE.

PY - 2020/11

Y1 - 2020/11

N2 - This paper studies multi-agent deep reinforcement learning (MADRL) based resource allocation methods for multi-cell wireless powered communication networks (WPCNs) where multiple hybrid access points (H-APs) wirelessly charge energy-limited users to collect data from them. We design a distributed reinforcement learning strategy where H-APs individually determine time and power allocation variables. Unlike traditional centralized optimization algorithms which require global information collected at a central unit, the proposed MADRL technique models an H-AP as an agent producing its action based only on its own locally observable states. Numerical results verify that the proposed approach can achieve comparable performance of the centralized algorithms.

AB - This paper studies multi-agent deep reinforcement learning (MADRL) based resource allocation methods for multi-cell wireless powered communication networks (WPCNs) where multiple hybrid access points (H-APs) wirelessly charge energy-limited users to collect data from them. We design a distributed reinforcement learning strategy where H-APs individually determine time and power allocation variables. Unlike traditional centralized optimization algorithms which require global information collected at a central unit, the proposed MADRL technique models an H-AP as an agent producing its action based only on its own locally observable states. Numerical results verify that the proposed approach can achieve comparable performance of the centralized algorithms.

KW - Wireless powered communication networks

KW - actor-critic method

KW - multi-agent deep reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=85096222511&partnerID=8YFLogxK

U2 - 10.1109/TVT.2020.3029609

DO - 10.1109/TVT.2020.3029609

M3 - Article

AN - SCOPUS:85096222511

SN - 0018-9545

VL - 69

SP - 14055

EP - 14060

JO - IEEE Transactions on Vehicular Technology

JF - IEEE Transactions on Vehicular Technology

IS - 11

M1 - 9217951

ER -

Multi-Agent Deep Reinforcement Learning for Distributed Resource Management in Wirelessly Powered Communication Networks

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this