Advanced search
2 files | 1.09 MB Add to list

Design and optimisation of a (FA)Q-learning-based HTTP adaptive streaming client

Maxim Claeys (UGent) , Steven Latré (UGent) , Jeroen Famaey (UGent) , TY Wu, W Van Leekwijck and Filip De Turck (UGent)
Author
Organization
Abstract
In recent years, HTTP (Hypertext Transfer Protocol) adaptive streaming (HAS) has become the de facto standard for adaptive video streaming services. A HAS video consists of multiple segments, encoded at multiple quality levels. State-of-the-art HAS clients employ deterministic heuristics to dynamically adapt the requested quality level based on the perceived network conditions. Current HAS client heuristics are, however, hardwired to fit specific network configurations, making them less flexible to fit a vast range of settings. In this article, a (frequency adjusted) Q-learning HAS client is proposed. In contrast to existing heuristics, the proposed HAS client dynamically learns the optimal behaviour corresponding to the current network environment in order to optimise the quality of experience. Furthermore, the client has been optimised both in terms of global performance and convergence speed. Thorough evaluations show that the proposed client can outperform deterministic algorithms by 11-18% in terms of mean opinion score in a wide range of network configurations.
Keywords
RESOURCE-ALLOCATION, IBCN, NETWORK MANAGEMENT, REINFORCEMENT, COMMUNICATION, MULTIMEDIA, quality of experience, HTTP adaptive streaming, reinforcement learning, agent systems

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 484.86 KB
  • 5898 i.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 602.50 KB

Citation

Please use this url to cite or link to this publication:

MLA
Claeys, Maxim et al. “Design and Optimisation of a (FA)Q-learning-based HTTP Adaptive Streaming Client.” CONNECTION SCIENCE 26.1 (2014): n. pag. Print.
APA
Claeys, Maxim, Latré, S., Famaey, J., Wu, T., Van Leekwijck, W., & De Turck, F. (2014). Design and optimisation of a (FA)Q-learning-based HTTP adaptive streaming client. CONNECTION SCIENCE, 26(1).
Chicago author-date
Claeys, Maxim, Steven Latré, Jeroen Famaey, TY Wu, W Van Leekwijck, and Filip De Turck. 2014. “Design and Optimisation of a (FA)Q-learning-based HTTP Adaptive Streaming Client.” Connection Science 26 (1).
Chicago author-date (all authors)
Claeys, Maxim, Steven Latré, Jeroen Famaey, TY Wu, W Van Leekwijck, and Filip De Turck. 2014. “Design and Optimisation of a (FA)Q-learning-based HTTP Adaptive Streaming Client.” Connection Science 26 (1).
Vancouver
1.
Claeys M, Latré S, Famaey J, Wu T, Van Leekwijck W, De Turck F. Design and optimisation of a (FA)Q-learning-based HTTP adaptive streaming client. CONNECTION SCIENCE. 2014;26(1).
IEEE
[1]
M. Claeys, S. Latré, J. Famaey, T. Wu, W. Van Leekwijck, and F. De Turck, “Design and optimisation of a (FA)Q-learning-based HTTP adaptive streaming client,” CONNECTION SCIENCE, vol. 26, no. 1, 2014.
@article{4401956,
  abstract     = {In recent years, HTTP (Hypertext Transfer Protocol) adaptive streaming (HAS) has become the de facto standard for adaptive video streaming services. A HAS video consists of multiple segments, encoded at multiple quality levels. State-of-the-art HAS clients employ deterministic heuristics to dynamically adapt the requested quality level based on the perceived network conditions. Current HAS client heuristics are, however, hardwired to fit specific network configurations, making them less flexible to fit a vast range of settings. In this article, a (frequency adjusted) Q-learning HAS client is proposed. In contrast to existing heuristics, the proposed HAS client dynamically learns the optimal behaviour corresponding to the current network environment in order to optimise the quality of experience. Furthermore, the client has been optimised both in terms of global performance and convergence speed. Thorough evaluations show that the proposed client can outperform deterministic algorithms by 11-18% in terms of mean opinion score in a wide range of network configurations.},
  author       = {Claeys, Maxim and Latré, Steven and Famaey, Jeroen and Wu, TY and Van Leekwijck, W and De Turck, Filip},
  issn         = {0954-0091},
  journal      = {CONNECTION SCIENCE},
  keywords     = {RESOURCE-ALLOCATION,IBCN,NETWORK MANAGEMENT,REINFORCEMENT,COMMUNICATION,MULTIMEDIA,quality of experience,HTTP adaptive streaming,reinforcement learning,agent systems},
  language     = {eng},
  number       = {1},
  pages        = {22},
  title        = {Design and optimisation of a (FA)Q-learning-based HTTP adaptive streaming client},
  url          = {http://dx.doi.org/10.1080/09540091.2014.885273},
  volume       = {26},
  year         = {2014},
}

Altmetric
View in Altmetric
Web of Science
Times cited: