Performance Evaluation of WebRTC-based video conferencing

Journal Article (2017)
Author(s)

Bart Jansen (Student TU Delft)

Timothy Goodwin (Columbia University)

Varun Gupta (Columbia University)

F.A. Kuipers (TU Delft - Embedded Systems)

Gil Zussman (Columbia University)

Research Group
Embedded Systems
Copyright
© 2017 Bart Jansen, Timothy Goodwin, Varun Gupta, F.A. Kuipers, Gil Zussman
DOI related publication
https://doi.org/10.1145/3199524.3199534
More Info
expand_more
Publication Year
2017
Language
English
Copyright
© 2017 Bart Jansen, Timothy Goodwin, Varun Gupta, F.A. Kuipers, Gil Zussman
Research Group
Embedded Systems
Issue number
3
Volume number
45
Pages (from-to)
56-68
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

WebRTC has quickly become popular as a video conferencing platform, partly due to the fact that many browsers support it. WebRTC utilizes the Google Congestion Control (GCC) algorithm to provide congestion control for realtime communications over UDP. The performance during a WebRTC call may be influenced by several factors, including the underlying WebRTC implementation, the device and network characteristics, and the network topology. In this paper, we perform a thorough performance evaluation of WebRTC both in emulated synthetic network conditions as well as in real wired and wireless networks. Our evaluation shows that WebRTC streams have a slightly higher priority than TCP flows when competing with cross traffic. In general, while in several of the considered scenarios WebRTC performed as expected, we observed important cases where there is room for improvement. These include the wireless domain and the newly added support for the video codecs VP9 and H.264 that does not perform as expected.

Files

WebRTC.pdf
(pdf | 1.84 Mb)
License info not available