Random early detection gateways for congestion avoidance
IEEE/ACM Transactions on Networking (TON)
Proceedings of the 2004 conference on Applications, technologies, architectures, and protocols for computer communications
Nonlinear instabilities in TCP-RED
IEEE/ACM Transactions on Networking (TON)
Detailed analysis of Skype traffic
IEEE Transactions on Multimedia
Router buffer sizing for TCP traffic and the role of the output/input capacity ratio
IEEE/ACM Transactions on Networking (TON)
Dynamic adaptive streaming over HTTP --: standards and design principles
MMSys '11 Proceedings of the second annual ACM conference on Multimedia systems
A test-bed for the dynamic adaptive streaming over HTTP featuring session mobility
MMSys '11 Proceedings of the second annual ACM conference on Multimedia systems
Bufferbloat: dark buffers in the internet
Communications of the ACM
Dynamic adaptive streaming over HTTP dataset
Proceedings of the 3rd Multimedia Systems Conference
What happens when HTTP adaptive streaming players compete for bandwidth?
Proceedings of the 22nd international workshop on Network and Operating System Support for Digital Audio and Video
Towards network-wide QoE fairness using openflow-assisted adaptive video streaming
Proceedings of the 2013 ACM SIGCOMM workshop on Future human-centric multimedia networking
Performance Evaluation of Congestion Window Validation for DASH Transport
Proceedings of Network and Operating System Support on Digital Audio and Video Workshop
| Hi-index | 0.00 |
HTTP adaptive video streaming is an emerging technology that aims to deliver video quality to clients in a manner that accommodates available bandwidth and its fluctuations. In this scheme, a video stream is split at the server into small video files encoded at multiple bitrates. The video is composed at the client by downloading these files over HTTP and TCP. Although there are some efforts to standardize media representation for this technology, adaptation techniques remain an open area for development. Recently, an alarm was raised by a study about the interaction between TCP congestion control algorithms and large buffers on the Internet. Queuing delays when these buffers are full can reach several hundreds of milliseconds in a phenomenon that was dubbed buffer bloat. In this paper we use measurements on a testbed to demonstrate and quantify the buffer bloat effect of HTTP adaptive streaming. We show that in a typical residential setting a single video stream can easily cause queuing delays up to one second and even more hence seriously degrading the performance of other applications sharing the home network. We develop SABRE (Smooth Adaptive Bit RatE), a scheme that can be implemented by the client to mitigate this problem. We implemented SABRE in the VLC player. Using our testbed, we show that our technique can reduce buffer occupancy and significantly diminish the buffer bloat effect without affecting the experience of the video viewer.