Q-Learning Based Quality Selection Algorithm for Dynamic Adaptive Streaming Over HTTP 


Vol. 47,  No. 1, pp. 39-47, Jan.  2022
10.7840/kics.2022.47.1.39


PDF
  Abstract

Efficient control of video streaming in wireless networks has emerged as an important issue with increasing wireless devices and video traffic. Traditional HTTP adaptive streaming techniques are tailored to specific formats, which do not effectively respond to unpredictable network environments, and despite their very similar techniques, there are incompatible problems. In response, MPEG proposed Dynamic Adaptive Streaming over HTTP (DASH), which would become the standard, and is now used as an international standard. To solve the problem, this paper proposes a video quality selection algorithm based on Q-Learning in DASH. Since the main goal is to meet QoE, which is the quality users feel practically, we construct Q-Value as the reward item of Q-Learning to maximize QoE. Simulation results confirm improved performance over Microsoft"s MSS and other proposed methods in other papers, and show improved results in more complex environments than conventional methods, demonstrating the need for improvement in quality selection algorithms.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

J. Park and S. S. Choi, "Q-Learning Based Quality Selection Algorithm for Dynamic Adaptive Streaming Over HTTP," The Journal of Korean Institute of Communications and Information Sciences, vol. 47, no. 1, pp. 39-47, 2022. DOI: 10.7840/kics.2022.47.1.39.

[ACM Style]

Ji-Wung Park and Seung Sik Choi. 2022. Q-Learning Based Quality Selection Algorithm for Dynamic Adaptive Streaming Over HTTP. The Journal of Korean Institute of Communications and Information Sciences, 47, 1, (2022), 39-47. DOI: 10.7840/kics.2022.47.1.39.

[KICS Style]

Ji-Wung Park and Seung Sik Choi, "Q-Learning Based Quality Selection Algorithm for Dynamic Adaptive Streaming Over HTTP," The Journal of Korean Institute of Communications and Information Sciences, vol. 47, no. 1, pp. 39-47, 1. 2022. (https://doi.org/10.7840/kics.2022.47.1.39)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880