Ph.D. Thesis Proposal Announcement
Title: Network and end-host support for HTTP adaptive video streaming

Ahmed Mansy
School of Computer Science
College of Computing
Georgia Institute of Technology
 
Date: November 5th, Monday, 2012
Time: 12:00 pm – 2:00 pm
Location: KACB 3402
 
Committee:

•  Dr. Mostafa Ammar (Advisor, School of Computer Science, Georgia Tech)

• Dr. Ellen Zegura (School of Computer Science, Georgia Tech)

• Dr. Constantine Dovrolis (School of Computer Science, Georgia Tech)

• Dr. Ling Liu (School of Computer Science, Georgia Tech)

• Dr. Ali Begen (Cisco)

Abstract:
Video streaming is widely recognized as the next Internet killer application. This is partly because broadband Internet services are becoming cheaper and more available to Internet users. In addition, people are continuously shifting from watching traditional TV channels to watching recorded or live video on many video sharing websites. This shift is expected to continue and video traffic is expected to grow larger in the next years.

Video streaming was not one of the Internet’s original target applications and its protocols (TCP in particular) were tuned mainly for efficient bulk file transfer. As a result, a significant effort has focused on the development of special protocols for streaming multi-media on the Internet. These protocols were generally based on UDP and reliability and congestion control, when needed, were implemented at the application layer. Recently, there has been a shift in video streaming from UDP to TCP, and specifically to HTTP. HTTP streaming provides a very attractive platform for video distribution on the Internet mainly because it can utilize all the current Internet infrastructure. For example, existing Content Distribution Networks (CDNs) and proxy servers can be used to distribute and cache HTTP video content.

In this thesis we make the argument that the marriage between HTTP streaming and the current Internet infrastructure can create many problems and inefficiencies. In order to solve these issues, we provide a set of techniques and protocols that can help both the network and the end-hosts to make better decisions to improve video streaming quality. We expect the thesis to provide the following contributions:

1. An analysis of adaptive streaming for a hybrid P2P/CDN live video system. The purpose of this analysis is to provide guidelines for operating such systems efficiently.
2. A client based approach for mitigating the buffer bloat effect of adaptive video flows.
3. Caching techniques that can improve the performance of HTTP adaptive streaming as compared to traditional web cache servers.
4. A protocol than enables residential gateways to communicate with adaptive video players. Users playing adaptive video should be able to learn about other users on the same network. This should help video players to pick the best video bitrate efficiently.