DDPG-based radio resource management for user interactive mobile edge networks

Po Chen Chen; Yen Chen Chen; Wei Hsiang Huang; Chih Wei Huang; Olav Tirkkonen

doi:10.1109/6GSUMMIT49458.2020.9083926

DDPG-based radio resource management for user interactive mobile edge networks

Po Chen Chen, Yen Chen Chen, Wei Hsiang Huang, Chih Wei Huang, Olav Tirkkonen

Department of Communication Engineering

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

7 Scopus citations

Abstract

The development of the fifth-generation (5G) system on capability and flexibility enables emerging applications with stringent requirements, such as ultra-high-resolution video streaming and online interactive virtual reality (VR) gaming. Hence, the resource management problem becomes more complicated than in the past, and machine learning can be a powerful tool to provide solutions. In this article, the Deep Deterministic Policy Gradient (DDPG) is used to schedule resources in an edge network environment. We integrate a 3D radio resource structure with componentized Markov decision process (MDP) actions to work on user interactivity-based groups. From the simulation results, we can see that more users are satisfied with DDPG-based radio resource management, especially in bandwidth and latency demanding situations.

Original language	English
Title of host publication	2nd 6G Wireless Summit 2020
Subtitle of host publication	Gain Edge for the 6G Era, 6G SUMMIT 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728160474
DOIs	https://doi.org/10.1109/6GSUMMIT49458.2020.9083926
State	Published - Mar 2020
Event	2nd 6G Wireless Summit, 6G SUMMIT 2020 - Levi, Lapland, Finland Duration: 17 Mar 2020 → 20 Mar 2020

Publication series

Name	2nd 6G Wireless Summit 2020: Gain Edge for the 6G Era, 6G SUMMIT 2020

Conference

Conference	2nd 6G Wireless Summit, 6G SUMMIT 2020
Country/Territory	Finland
City	Levi, Lapland
Period	17/03/20 → 20/03/20

Keywords

Deep Deterministic Policy Gradient (DDPG)
Machine learning
Mobile edge network
Radio resource management
Reinforcement learning
Virtual reality

Access to Document

10.1109/6GSUMMIT49458.2020.9083926

Cite this

Chen, P. C., Chen, Y. C., Huang, W. H., Huang, C. W., & Tirkkonen, O. (2020). DDPG-based radio resource management for user interactive mobile edge networks. In 2nd 6G Wireless Summit 2020: Gain Edge for the 6G Era, 6G SUMMIT 2020 Article 9083926 (2nd 6G Wireless Summit 2020: Gain Edge for the 6G Era, 6G SUMMIT 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/6GSUMMIT49458.2020.9083926

@inproceedings{e44a0a55735647d0821cee229d2b3e9b,

title = "DDPG-based radio resource management for user interactive mobile edge networks",

abstract = "The development of the fifth-generation (5G) system on capability and flexibility enables emerging applications with stringent requirements, such as ultra-high-resolution video streaming and online interactive virtual reality (VR) gaming. Hence, the resource management problem becomes more complicated than in the past, and machine learning can be a powerful tool to provide solutions. In this article, the Deep Deterministic Policy Gradient (DDPG) is used to schedule resources in an edge network environment. We integrate a 3D radio resource structure with componentized Markov decision process (MDP) actions to work on user interactivity-based groups. From the simulation results, we can see that more users are satisfied with DDPG-based radio resource management, especially in bandwidth and latency demanding situations.",

keywords = "Deep Deterministic Policy Gradient (DDPG), Machine learning, Mobile edge network, Radio resource management, Reinforcement learning, Virtual reality",

author = "Chen, {Po Chen} and Chen, {Yen Chen} and Huang, {Wei Hsiang} and Huang, {Chih Wei} and Olav Tirkkonen",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2nd 6G Wireless Summit, 6G SUMMIT 2020 ; Conference date: 17-03-2020 Through 20-03-2020",

year = "2020",

month = mar,

doi = "10.1109/6GSUMMIT49458.2020.9083926",

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

series = "2nd 6G Wireless Summit 2020: Gain Edge for the 6G Era, 6G SUMMIT 2020",

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

booktitle = "2nd 6G Wireless Summit 2020",

}

Chen, PC, Chen, YC, Huang, WH, Huang, CW & Tirkkonen, O 2020, DDPG-based radio resource management for user interactive mobile edge networks. in 2nd 6G Wireless Summit 2020: Gain Edge for the 6G Era, 6G SUMMIT 2020., 9083926, 2nd 6G Wireless Summit 2020: Gain Edge for the 6G Era, 6G SUMMIT 2020, Institute of Electrical and Electronics Engineers Inc., 2nd 6G Wireless Summit, 6G SUMMIT 2020, Levi, Lapland, Finland, 17/03/20. https://doi.org/10.1109/6GSUMMIT49458.2020.9083926

DDPG-based radio resource management for user interactive mobile edge networks. / Chen, Po Chen; Chen, Yen Chen; Huang, Wei Hsiang et al.
2nd 6G Wireless Summit 2020: Gain Edge for the 6G Era, 6G SUMMIT 2020. Institute of Electrical and Electronics Engineers Inc., 2020. 9083926 (2nd 6G Wireless Summit 2020: Gain Edge for the 6G Era, 6G SUMMIT 2020).

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

TY - GEN

T1 - DDPG-based radio resource management for user interactive mobile edge networks

AU - Chen, Po Chen

AU - Chen, Yen Chen

AU - Huang, Wei Hsiang

AU - Huang, Chih Wei

AU - Tirkkonen, Olav

PY - 2020/3

Y1 - 2020/3

N2 - The development of the fifth-generation (5G) system on capability and flexibility enables emerging applications with stringent requirements, such as ultra-high-resolution video streaming and online interactive virtual reality (VR) gaming. Hence, the resource management problem becomes more complicated than in the past, and machine learning can be a powerful tool to provide solutions. In this article, the Deep Deterministic Policy Gradient (DDPG) is used to schedule resources in an edge network environment. We integrate a 3D radio resource structure with componentized Markov decision process (MDP) actions to work on user interactivity-based groups. From the simulation results, we can see that more users are satisfied with DDPG-based radio resource management, especially in bandwidth and latency demanding situations.

AB - The development of the fifth-generation (5G) system on capability and flexibility enables emerging applications with stringent requirements, such as ultra-high-resolution video streaming and online interactive virtual reality (VR) gaming. Hence, the resource management problem becomes more complicated than in the past, and machine learning can be a powerful tool to provide solutions. In this article, the Deep Deterministic Policy Gradient (DDPG) is used to schedule resources in an edge network environment. We integrate a 3D radio resource structure with componentized Markov decision process (MDP) actions to work on user interactivity-based groups. From the simulation results, we can see that more users are satisfied with DDPG-based radio resource management, especially in bandwidth and latency demanding situations.

KW - Deep Deterministic Policy Gradient (DDPG)

KW - Machine learning

KW - Mobile edge network

KW - Radio resource management

KW - Reinforcement learning

KW - Virtual reality

UR - http://www.scopus.com/inward/record.url?scp=85086309182&partnerID=8YFLogxK

U2 - 10.1109/6GSUMMIT49458.2020.9083926

DO - 10.1109/6GSUMMIT49458.2020.9083926

M3 - 會議論文篇章

AN - SCOPUS:85086309182

T3 - 2nd 6G Wireless Summit 2020: Gain Edge for the 6G Era, 6G SUMMIT 2020

BT - 2nd 6G Wireless Summit 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd 6G Wireless Summit, 6G SUMMIT 2020

Y2 - 17 March 2020 through 20 March 2020

ER -

Chen PC, Chen YC, Huang WH, Huang CW, Tirkkonen O. DDPG-based radio resource management for user interactive mobile edge networks. In 2nd 6G Wireless Summit 2020: Gain Edge for the 6G Era, 6G SUMMIT 2020. Institute of Electrical and Electronics Engineers Inc. 2020. 9083926. (2nd 6G Wireless Summit 2020: Gain Edge for the 6G Era, 6G SUMMIT 2020). doi: 10.1109/6GSUMMIT49458.2020.9083926

DDPG-based radio resource management for user interactive mobile edge networks

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this