Rate oscillation breaks in HTTP on-off distributions: a DASH framework
by Koffka Khan; Wayne Goodridge
International Journal of Autonomous and Adaptive Communications Systems (IJAACS), Vol. 13, No. 3, 2020

Abstract: The chances of multiple video players sharing a bottleneck link becomes increasingly likely as dynamic adaptive streaming over HTTP (DASH) remains popular. Multi-player DASH scenarios across bottleneck links pose many user-perceived quality of experience (QoE) challenges. Existing solutions still do not address the adequate sharing of network resources. We present a rate oscillation breaks in HTTP on-off distributions (ROBIN-HOOD) framework for DASH. A streaming approach implementing this framework allows player(s) receiving high bitrates to demand lower quality video segments, while the player receiving the lowest bitrate demands higher quality video segments. This mechanism allows the weaker players to improve their share of available network resources. The result is better user-QoE for players. Two approaches implementing the framework, B-DASH (heuristic) and S-MDP (stochastic), are compared in live internet experiments. It is shown that Robin-Hood improves user-QoE. In addition, the MDP stochastic S-MDP Robin-Hood approach outperforms the heuristic B-DASH Robin-Hood approach.

Online publication date: Wed, 28-Oct-2020

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Autonomous and Adaptive Communications Systems (IJAACS):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com