IEEE/ACM Transactions on Networking (TON)
Can internet video-on-demand be profitable?
Proceedings of the 2007 conference on Applications, technologies, architectures, and protocols for computer communications
I tube, you tube, everybody tubes: analyzing the world's largest user generated content video system
Proceedings of the 7th ACM SIGCOMM conference on Internet measurement
Measurement, Modeling, and Analysis of Internet Video Sharing Site Workload: A Case Study
ICWS '08 Proceedings of the 2008 IEEE International Conference on Web Services
Computer Networks: The International Journal of Computer and Telecommunications Networking
Workload generation for YouTube
Multimedia Tools and Applications
Application flow control in YouTube video streams
ACM SIGCOMM Computer Communication Review
Hi-index | 0.01 |
This work attempts to characterize network traffic flows originating from large-scale video sharing services such as YouTube. The key technical contributions of this paper are twofold. We first present a simple and effective methodology that identifies traffic flows originating from video hosting servers. The key idea behind our approach is to leverage the addressing/naming conventions used in large-scale server farms. Next, using the identified video flows, we investigate the characteristics of network traffic flows of video sharing services from a network service provider view. Our study reveals the intrinsic characteristics of the flow size distributions of video sharing services. The origin of the intrinsic characteristics is rooted on the differentiated service provided for free and premium membership of the video sharing services. We also investigate temporal characteristics of video traffic flows.