Session level analysis of p2p television traces

  • Authors:
  • Arkadiusz Biernacki;Udo R. Krieger

  • Affiliations:
  • Institute of Computer Science, Silesian University of Technology, Gliwice, Poland;Dep. of Information Systems and Applied Computer Science, Otto-Friedrich University Bamberg, Bamberg, Germany

  • Venue:
  • FMN'10 Proceedings of the Third international conference on Future Multimedia Networking
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this study we examine statistical properties of traffic generated by the popular P2P IPTV application SopCast. The analysis aims at a better understanding of the mechanisms used by such applications and their impact on the network. Since the most popular P2P IPTV applications use proprietary unpublished protocols, we look directly at the generated traffic focusing on a single session analysis, which is the major contribution of our work. We present a basic characterisation of the traffic profile generated by SopCast during every separate session in terms of the intensity, the burstiness, the distribution of the packet sizes and the correlation. We show that some of these statistical properties of the analysed traffic may be quite different depending on the particular session.