Self-adaptive power control with deep reinforcement learning for millimeter-wave Internet-of-vehicles video caching

Dohyun Kwon; Joongheon Kim; David A. Mohaisen; Wonjun Lee

doi:10.1109/JCN.2020.000022

Self-adaptive power control with deep reinforcement learning for millimeter-wave Internet-of-vehicles video caching

Dohyun Kwon, Joongheon Kim, David A. Mohaisen, Wonjun Lee

School of Cybersecurity

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

18 Citations (Scopus)

Abstract

Video delivery and caching over the millimeter-wave (mmWave) spectrum is a promising technology for high data rate and efficient frequency utilization in many applications, including distributed vehicular networks. However, due to the short handoff duration, calibrating both optimal power allocation of each base station toward its associated vehicles and cache allocation are challenging for their computational complexity. Heretofore, most video delivery applications were based on on-line or off-line algorithms, and they were limited to compute and optimize high dimensional objectives within low-delay in large scale vehicular networks. On the other hand, deep reinforcement learning is shown for learning such scale of a problem with an optimized policy learning phase. In this paper, we propose deep deterministic policy gradient-based power control of mmWave base station (mBS) and proactive cache allocation toward mBSs in distributed mmWave Internet-of-vehicle (IoV) networks. Simulation results validate the performance of the proposed caching scheme in terms of quality of the provisioned video and playback stall in various scales of IoV networks.

Original language	English
Article number	9194445
Pages (from-to)	326-337
Number of pages	12
Journal	Journal of Communications and Networks
Volume	22
Issue number	4
DOIs	https://doi.org/10.1109/JCN.2020.000022
Publication status	Published - 2020 Aug

Bibliographical note

Funding Information:
This work was supported by Institute for Information & Communications Technology Promotion (IITP) grant funded by the Korea government (MSIT) (No. 2018-0-00170, Virtual Presence in Moving Objects through 5G) and also by the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2020-2017-0-01637) supervised by the IITP (Institute for Information & Communications Technology Promotion). J. Kim, A. Mo-haisen, and W. Lee are the corresponding authors of this paper.

Funding Information:
Manuscript received Nov. 21, 2020; revised June 15, 2020; approved for publication by Tim O’Shea, Guest Editor, July 15, 2020. This research was supported by the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2020-2017-0-01637) supervised by the IITP (Institute for Information & Communications Technology Planning & Evaluation); and also by MSIT, Korea, under ITRC support program (IITP-2018-0-01396) supervised by IITP. D. Kwon is with Hyundai-Autoever, Seoul, Korea, email: [email protected]. J. Kim is with the School of Electrical Engineering, Korea University, Seoul, Korea, e-mail: [email protected]. D. A. Mohaisen is with the Department of Computer Science, University of Central Florida, Orlando, FL, USA, e-mail: [email protected]. W. Lee is with the School of Cybersecurity, Korea University, Seoul, Korea, e-mail: [email protected]. J. Kim, D.A. Mohaisen, and W. Lee are corresponding authors. Digital Object Identifier: 10.1109/JCN.2020.000022 Fig. 1. Considered power-cache aware video caching scheme in distributed IoV networks.

Publisher Copyright:
© 2011 KICS.

Keywords

Deep reinforcement learning
Internet-of-vehicle caching
video caching

ASJC Scopus subject areas

Information Systems
Computer Networks and Communications

Access to Document

10.1109/JCN.2020.000022

Cite this

@article{f75f418adc96411d96d37b26907db71b,

title = "Self-adaptive power control with deep reinforcement learning for millimeter-wave Internet-of-vehicles video caching",

abstract = "Video delivery and caching over the millimeter-wave (mmWave) spectrum is a promising technology for high data rate and efficient frequency utilization in many applications, including distributed vehicular networks. However, due to the short handoff duration, calibrating both optimal power allocation of each base station toward its associated vehicles and cache allocation are challenging for their computational complexity. Heretofore, most video delivery applications were based on on-line or off-line algorithms, and they were limited to compute and optimize high dimensional objectives within low-delay in large scale vehicular networks. On the other hand, deep reinforcement learning is shown for learning such scale of a problem with an optimized policy learning phase. In this paper, we propose deep deterministic policy gradient-based power control of mmWave base station (mBS) and proactive cache allocation toward mBSs in distributed mmWave Internet-of-vehicle (IoV) networks. Simulation results validate the performance of the proposed caching scheme in terms of quality of the provisioned video and playback stall in various scales of IoV networks. ",

keywords = "Deep reinforcement learning, Internet-of-vehicle caching, video caching",

author = "Dohyun Kwon and Joongheon Kim and Mohaisen, {David A.} and Wonjun Lee",

note = "Funding Information: This work was supported by Institute for Information & Communications Technology Promotion (IITP) grant funded by the Korea government (MSIT) (No. 2018-0-00170, Virtual Presence in Moving Objects through 5G) and also by the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2020-2017-0-01637) supervised by the IITP (Institute for Information & Communications Technology Promotion). J. Kim, A. Mo-haisen, and W. Lee are the corresponding authors of this paper. Funding Information: Manuscript received Nov. 21, 2020; revised June 15, 2020; approved for publication by Tim O{\textquoteright}Shea, Guest Editor, July 15, 2020. This research was supported by the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2020-2017-0-01637) supervised by the IITP (Institute for Information & Communications Technology Planning & Evaluation); and also by MSIT, Korea, under ITRC support program (IITP-2018-0-01396) supervised by IITP. D. Kwon is with Hyundai-Autoever, Seoul, Korea, email: [email protected]. J. Kim is with the School of Electrical Engineering, Korea University, Seoul, Korea, e-mail: [email protected]. D. A. Mohaisen is with the Department of Computer Science, University of Central Florida, Orlando, FL, USA, e-mail: [email protected]. W. Lee is with the School of Cybersecurity, Korea University, Seoul, Korea, e-mail: [email protected]. J. Kim, D.A. Mohaisen, and W. Lee are corresponding authors. Digital Object Identifier: 10.1109/JCN.2020.000022 Fig. 1. Considered power-cache aware video caching scheme in distributed IoV networks. Publisher Copyright: {\textcopyright} 2011 KICS.",

year = "2020",

month = aug,

doi = "10.1109/JCN.2020.000022",

language = "English",

volume = "22",

pages = "326--337",

journal = "Journal of Communications and Networks",

issn = "1229-2370",

publisher = "Korean Institute of Communication Sciences",

number = "4",

}

TY - JOUR

T1 - Self-adaptive power control with deep reinforcement learning for millimeter-wave Internet-of-vehicles video caching

AU - Kwon, Dohyun

AU - Kim, Joongheon

AU - Mohaisen, David A.

AU - Lee, Wonjun

N1 - Funding Information: This work was supported by Institute for Information & Communications Technology Promotion (IITP) grant funded by the Korea government (MSIT) (No. 2018-0-00170, Virtual Presence in Moving Objects through 5G) and also by the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2020-2017-0-01637) supervised by the IITP (Institute for Information & Communications Technology Promotion). J. Kim, A. Mo-haisen, and W. Lee are the corresponding authors of this paper. Funding Information: Manuscript received Nov. 21, 2020; revised June 15, 2020; approved for publication by Tim O’Shea, Guest Editor, July 15, 2020. This research was supported by the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2020-2017-0-01637) supervised by the IITP (Institute for Information & Communications Technology Planning & Evaluation); and also by MSIT, Korea, under ITRC support program (IITP-2018-0-01396) supervised by IITP. D. Kwon is with Hyundai-Autoever, Seoul, Korea, email: [email protected]. J. Kim is with the School of Electrical Engineering, Korea University, Seoul, Korea, e-mail: [email protected]. D. A. Mohaisen is with the Department of Computer Science, University of Central Florida, Orlando, FL, USA, e-mail: [email protected]. W. Lee is with the School of Cybersecurity, Korea University, Seoul, Korea, e-mail: [email protected]. J. Kim, D.A. Mohaisen, and W. Lee are corresponding authors. Digital Object Identifier: 10.1109/JCN.2020.000022 Fig. 1. Considered power-cache aware video caching scheme in distributed IoV networks. Publisher Copyright: © 2011 KICS.

PY - 2020/8

Y1 - 2020/8

N2 - Video delivery and caching over the millimeter-wave (mmWave) spectrum is a promising technology for high data rate and efficient frequency utilization in many applications, including distributed vehicular networks. However, due to the short handoff duration, calibrating both optimal power allocation of each base station toward its associated vehicles and cache allocation are challenging for their computational complexity. Heretofore, most video delivery applications were based on on-line or off-line algorithms, and they were limited to compute and optimize high dimensional objectives within low-delay in large scale vehicular networks. On the other hand, deep reinforcement learning is shown for learning such scale of a problem with an optimized policy learning phase. In this paper, we propose deep deterministic policy gradient-based power control of mmWave base station (mBS) and proactive cache allocation toward mBSs in distributed mmWave Internet-of-vehicle (IoV) networks. Simulation results validate the performance of the proposed caching scheme in terms of quality of the provisioned video and playback stall in various scales of IoV networks.

AB - Video delivery and caching over the millimeter-wave (mmWave) spectrum is a promising technology for high data rate and efficient frequency utilization in many applications, including distributed vehicular networks. However, due to the short handoff duration, calibrating both optimal power allocation of each base station toward its associated vehicles and cache allocation are challenging for their computational complexity. Heretofore, most video delivery applications were based on on-line or off-line algorithms, and they were limited to compute and optimize high dimensional objectives within low-delay in large scale vehicular networks. On the other hand, deep reinforcement learning is shown for learning such scale of a problem with an optimized policy learning phase. In this paper, we propose deep deterministic policy gradient-based power control of mmWave base station (mBS) and proactive cache allocation toward mBSs in distributed mmWave Internet-of-vehicle (IoV) networks. Simulation results validate the performance of the proposed caching scheme in terms of quality of the provisioned video and playback stall in various scales of IoV networks.

KW - Deep reinforcement learning

KW - Internet-of-vehicle caching

KW - video caching

UR - http://www.scopus.com/inward/record.url?scp=85091536124&partnerID=8YFLogxK

U2 - 10.1109/JCN.2020.000022

DO - 10.1109/JCN.2020.000022

M3 - Article

AN - SCOPUS:85091536124

SN - 1229-2370

VL - 22

SP - 326

EP - 337

JO - Journal of Communications and Networks

JF - Journal of Communications and Networks

IS - 4

M1 - 9194445

ER -

Self-adaptive power control with deep reinforcement learning for millimeter-wave Internet-of-vehicles video caching

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this