ARBITER: Adaptive rate-based intelligent HTTP streaming algorithm

Loading...
Thumbnail Image
Files
4045.pdf(297.03 KB)
Accepted version
Date
2016-07
Authors
Zahran, Ahmed H.
Sreenan, Cormac J.
Journal Title
Journal ISSN
Volume Title
Publisher
IEEE
Research Projects
Organizational Units
Journal Issue
Abstract
Dynamic Adaptive streaming over HTTP (DASH) is widely used by content providers for video delivery and dominates traffic on cellular networks. The inherent variability in both video bitrate and network bandwidth negatively impacts the user Quality of Experience (QoE), motivating the design of better DASH-compliant adaptation algorithms. In this paper we present ARBITER, a novel streaming adaptation algorithm that explicitly integrates the variations in both video and network dynamics in its adaptation decisions. Our simulation-based performance evaluation, using real video content and cellular bandwidth traces, shows that ARBITER achieves an excellent tradeoff among streaming metrics in terms of received video quality, stall count, stall duration, and switching dynamics, leading to a relative improvement of 17-45% in user QoE in comparison to state-of-the-art algorithms.
Description
Keywords
Bandwidth , HTTP , Video streaming , Adaptation algorithms , Adaptation decisions , Content providers , Dynamic Adaptive Streaming over HTTP , Inherent variability , Quality of experience (QoE) , State-of-the-art algorithms , Switching dynamics , Quality of service
Citation
Zahran, A. H. and Sreenan, C. J. (2016) 'ARBITER: Adaptive rate-based intelligent HTTP streaming algorithm', 2016 IEEE International Conference on Multimedia and Expo Workshop (ICMEW), 11-15 July, Seattle, WA, USA. doi: 10.1109/ICMEW.2016.7574709
Link to publisher’s version
Copyright
© 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.