Multiuser video streaming rate adaptation: A physical layer resource-Aware deep reinforcement learning approach

Kexin Tang; Nuowen Kan; Junni Zou; Xiao Fu; Mingyi Hong; Hongkai Xiong

doi:10.1109/VCIP47243.2019.8965912

Multiuser video streaming rate adaptation: A physical layer resource-Aware deep reinforcement learning approach

Kexin Tang
, Nuowen Kan
, Junni Zou
, Xiao Fu
, Mingyi Hong
, Hongkai Xiong

Electrical and Computer Engineering

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

1 Scopus citations

Abstract

In this paper, we propose a cross-layer decision framework for multiuser adaptive video delivery over time-varying and mutually interfering wireless cellular network. The key idea is to synthetically design the physical-layer optimization-based beamforming scheme (performed at the base stations) and the application-layer deep reinforcement learning (DRL)-based rate adaptation scheme (performed at the user terminals), so that a very complex multi-user overall fair long-Term quality of experience (QoE) maximization problem can be decomposed to two layers and solved effectively. Extensive simulations show that the proposed cross-layer design is effective and promising.

Original language	English (US)
Title of host publication	2019 IEEE International Conference on Visual Communications and Image Processing, VCIP 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728137230
DOIs	https://doi.org/10.1109/VCIP47243.2019.8965912
State	Published - Dec 2019
Event	34th IEEE International Conference on Visual Communications and Image Processing, VCIP 2019 - Sydney, Australia Duration: Dec 1 2019 → Dec 4 2019

Publication series

Name	2019 IEEE International Conference on Visual Communications and Image Processing, VCIP 2019

Conference

Conference	34th IEEE International Conference on Visual Communications and Image Processing, VCIP 2019
Country/Territory	Australia
City	Sydney
Period	12/1/19 → 12/4/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

Wireless video streaming
beamforming
cross-layer design
deep reinforcement learning
rate adaptation

Publisher link

10.1109/VCIP47243.2019.8965912

Find It

Find It at U of M Libraries

Cite this

Tang, K., Kan, N., Zou, J., Fu, X., Hong, M., & Xiong, H. (2019). Multiuser video streaming rate adaptation: A physical layer resource-Aware deep reinforcement learning approach. In 2019 IEEE International Conference on Visual Communications and Image Processing, VCIP 2019 Article 8965912 (2019 IEEE International Conference on Visual Communications and Image Processing, VCIP 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/VCIP47243.2019.8965912

Multiuser video streaming rate adaptation: A physical layer resource-Aware deep reinforcement learning approach. / Tang, Kexin; Kan, Nuowen; Zou, Junni et al.
2019 IEEE International Conference on Visual Communications and Image Processing, VCIP 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8965912 (2019 IEEE International Conference on Visual Communications and Image Processing, VCIP 2019).

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

Tang, K, Kan, N, Zou, J, Fu, X, Hong, M & Xiong, H 2019, Multiuser video streaming rate adaptation: A physical layer resource-Aware deep reinforcement learning approach. in 2019 IEEE International Conference on Visual Communications and Image Processing, VCIP 2019., 8965912, 2019 IEEE International Conference on Visual Communications and Image Processing, VCIP 2019, Institute of Electrical and Electronics Engineers Inc., 34th IEEE International Conference on Visual Communications and Image Processing, VCIP 2019, Sydney, Australia, 12/1/19. https://doi.org/10.1109/VCIP47243.2019.8965912

Tang K, Kan N, Zou J, Fu X, Hong M, Xiong H. Multiuser video streaming rate adaptation: A physical layer resource-Aware deep reinforcement learning approach. In 2019 IEEE International Conference on Visual Communications and Image Processing, VCIP 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8965912. (2019 IEEE International Conference on Visual Communications and Image Processing, VCIP 2019). doi: 10.1109/VCIP47243.2019.8965912

Tang, Kexin ; Kan, Nuowen ; Zou, Junni et al. / Multiuser video streaming rate adaptation : A physical layer resource-Aware deep reinforcement learning approach. 2019 IEEE International Conference on Visual Communications and Image Processing, VCIP 2019. Institute of Electrical and Electronics Engineers Inc., 2019. (2019 IEEE International Conference on Visual Communications and Image Processing, VCIP 2019).

@inproceedings{cd7a6e7bd100436b859aaa874e0c4e0b,

title = "Multiuser video streaming rate adaptation: A physical layer resource-Aware deep reinforcement learning approach",

abstract = "In this paper, we propose a cross-layer decision framework for multiuser adaptive video delivery over time-varying and mutually interfering wireless cellular network. The key idea is to synthetically design the physical-layer optimization-based beamforming scheme (performed at the base stations) and the application-layer deep reinforcement learning (DRL)-based rate adaptation scheme (performed at the user terminals), so that a very complex multi-user overall fair long-Term quality of experience (QoE) maximization problem can be decomposed to two layers and solved effectively. Extensive simulations show that the proposed cross-layer design is effective and promising.",

keywords = "Wireless video streaming, beamforming, cross-layer design, deep reinforcement learning, rate adaptation",

author = "Kexin Tang and Nuowen Kan and Junni Zou and Xiao Fu and Mingyi Hong and Hongkai Xiong",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 34th IEEE International Conference on Visual Communications and Image Processing, VCIP 2019 ; Conference date: 01-12-2019 Through 04-12-2019",

year = "2019",

month = dec,

doi = "10.1109/VCIP47243.2019.8965912",

language = "English (US)",

series = "2019 IEEE International Conference on Visual Communications and Image Processing, VCIP 2019",

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

booktitle = "2019 IEEE International Conference on Visual Communications and Image Processing, VCIP 2019",

}

TY - GEN

T1 - Multiuser video streaming rate adaptation

T2 - 34th IEEE International Conference on Visual Communications and Image Processing, VCIP 2019

AU - Tang, Kexin

AU - Kan, Nuowen

AU - Zou, Junni

AU - Fu, Xiao

AU - Hong, Mingyi

AU - Xiong, Hongkai

PY - 2019/12

Y1 - 2019/12

N2 - In this paper, we propose a cross-layer decision framework for multiuser adaptive video delivery over time-varying and mutually interfering wireless cellular network. The key idea is to synthetically design the physical-layer optimization-based beamforming scheme (performed at the base stations) and the application-layer deep reinforcement learning (DRL)-based rate adaptation scheme (performed at the user terminals), so that a very complex multi-user overall fair long-Term quality of experience (QoE) maximization problem can be decomposed to two layers and solved effectively. Extensive simulations show that the proposed cross-layer design is effective and promising.

AB - In this paper, we propose a cross-layer decision framework for multiuser adaptive video delivery over time-varying and mutually interfering wireless cellular network. The key idea is to synthetically design the physical-layer optimization-based beamforming scheme (performed at the base stations) and the application-layer deep reinforcement learning (DRL)-based rate adaptation scheme (performed at the user terminals), so that a very complex multi-user overall fair long-Term quality of experience (QoE) maximization problem can be decomposed to two layers and solved effectively. Extensive simulations show that the proposed cross-layer design is effective and promising.

KW - Wireless video streaming

KW - beamforming

KW - cross-layer design

KW - deep reinforcement learning

KW - rate adaptation

UR - https://www.scopus.com/pages/publications/85079242265

UR - https://www.scopus.com/pages/publications/85079242265#tab=citedBy

U2 - 10.1109/VCIP47243.2019.8965912

DO - 10.1109/VCIP47243.2019.8965912

M3 - Conference contribution

AN - SCOPUS:85079242265

T3 - 2019 IEEE International Conference on Visual Communications and Image Processing, VCIP 2019

BT - 2019 IEEE International Conference on Visual Communications and Image Processing, VCIP 2019

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 1 December 2019 through 4 December 2019

ER -

Multiuser video streaming rate adaptation: A physical layer resource-Aware deep reinforcement learning approach

Abstract

Publication series

Conference

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this