Large-scale measurement experiments of P2P-TV systems insights on fairness and locality

Thomas Silverston, Loránd Jakab, Albert Cabellos-Aparicio, Olivier Fourmaux, Kavé Salamatian, Kenjiro Cho

Research output: Contribution to journalArticlepeer-review

13 Citations (Scopus)


P2P-TV is an emerging alternative to classical television broadcast systems. Leveraging possibilities offered by the Internet, several companies offer P2P-TV services to their customers. The overwhelming majority of these systems, however, is of closed nature, offering little insight on their traffic properties. For a better understanding of the P2P-TV landscape, we performed measurement experiments in France, Japan, Spain, and Romania, using different commercial applications. By using multiple measurement points in different locations of the world, our results can paint a global picture of the measured networks, inferring their main properties. More precisely, we focus on the level of collaboration between peers, their location and the effect of the traffic on the networks. Our results show that there is no fairness between peers and that is an important issue for the scalability of P2P-TV systems. Moreover, hundreds of Autonomous Systems are involved in the P2P-TV traffic and it points out the lack of locality-aware mechanisms for these systems. The geographic location of peers testifies the wide spread of these applications in Asia and highlights their worldwide usage.

Original languageEnglish
Pages (from-to)327-338
Number of pages12
JournalSignal Processing: Image Communication
Issue number7
Publication statusPublished - 2011 Aug
Externally publishedYes


  • Measurement experiment
  • Peer-to-Peer
  • Traffic analysis
  • Video live streaming

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering


Dive into the research topics of 'Large-scale measurement experiments of P2P-TV systems insights on fairness and locality'. Together they form a unique fingerprint.

Cite this