Modelling Video Traffic from Latest Technology Encoders
Project Background and Aims
According to the latest Cisco estimates, two-thirds of the global mobile traffic in 2018 will be video traffic. The number of videos streamed on YouTube daily is steadily over a billion. This explosive growth calls for new sets of traffic control procedures to be implemented in order for the networks to cope with the bursty new applications, which have strict Quality of Service (QoS) requirements. For Variable Bit Rate (VBR) coded video, statistical source models are needed to design networks which are able to guarantee the strict QoS requirements of the video traffic. Video packet delay requirements are strict, because delays are annoying to a viewer. Whenever the delay experienced by a video packet exceeds the corresponding maximum delay, the packet is dropped, and the video packet dropping requirements are equally strict. Even a low video packet dropping probability may considerably deteriorate the viewer’s quality of experience. Hence, the problem of modelling video traffic, has been extensively studied in the literature, with various degrees of accuracy for videos encoded with different encoding schemes.
In this research project, students will become familiar with well-known modelling approaches for traffic generated by individual video traces and by multiplexed video traces, and they will develop traffic models based on captured videos encoded with the latest (H.264 and H.265) video encoding standards.
Project Skills
The project team will require:- Project management skills
- Knowledge of Matlab or a programming language such as C
- Knowledge about traffic modelling is desirable but can be gained during the project
Initial References
- Marwan Krunz and Satish K. Tripathi. On the characterization of VBR MPEG streams. In Proceedings of ACM SIGMETRICS international conference on Measurement and modeling of computer systems (SIGMETRICS), US, 1997.
- Aggelos Lazaris, Polychronis Koutsakis, and Michael Paterakis. A new model for video traffic originating from multiplexed MPEG-4 videoconference streams. Perform. Eval. 65, 1, 51-70, January 2008.
- Trace Files and Statistics: H.264/AVC Video Trace Library, http://trace.eas.asu.edu/h264/index.html
- MPEG-4 and H.263 Video Traces for Network Performance Evaluation, http://www-tkn.ee.tu-berlin.de/research/trace/trace.html