Thomas Silverston

Traffic analysis of peer-to-peer IPTV communities

The Internet is currently experiencing one of the most important challenges in terms of content distribution since its first uses as a medium for content delivery: users from passive downloaders and browsers are moving towards content producers and publishers. They often distribute and retrieve multimedia contents establishing network communities. This is the case of peer-to-peer IPTV communities. In this work we present a detailed study of P2P IPTV traffic, providing useful insights on both transport- and packet-level properties as well as on the behavior of the peers inside the network. In particular, we provide novel results on the (i) ports and protocols used; (ii) differences between signaling and video traffic; (iii) behavior of the traffic at different time scales; (iv) differences between TCP and UDP traffic; (v) traffic generated and received by peers; (vi) peers neighborhood and session duration. The knowledge gained thanks to this analysis is useful for several tasks, e.g. traffic identification, understanding the performance of different P2P IPTV technologies and the impact of such traffic on network nodes and links, and building more realistic models for simulations.

Towards an Incentive Mechanism for Peer-to-Peer Multimedia Live Streaming Systems

Incentive mechanisms are essential components of peer-to-peer systems for file sharing such as BitTorrent, since they enforce peers to share their resources and to participate. Recent P2P systems that distribute live multimedia streams take their inspiration from BitTorrent, but have not defined incentive mechanisms appropriate to the nature of continuous media. In this article, we uncover the way that the incentive mechanisms in BitTorrent are not well suited to streaming live multimedia, and based on P2P systems that we have measured, we propose a new incentive mechanism designed for distribution of live multimedia streaming over a P2P network.

Socially-Aware Caching Strategy for Content Centric Networking

Content Centric Networking (CCN) emerged as a replacement architecture for the current Internet. CCN resorts to in-network caching to enhance end-user delivery performance. At the same time, Online Social Networks (OSN) have become the common paradigm to exchange information between users. OSNs carry extremely valuable information about their users and their relationships. This knowledge can help to drastically improve the efficiency of CCN. We present a novel caching strategy for CCN based on social information. We conjecture a small number of users - the Influential users - dominate the activity, receive most attention from other users and produce content more likely to be consumed. Our caching strategy privileges the Influential users and cache pro-actively their content in the network. Through extensive simulation experiments based on two social network scenarios, LastFM and Facebook, and substantial number of users in a CCN topology, we demonstrate the value of our approach. We also implemented and deployed our strategy on PlanetLab and it improves drastically the caching performances of CCN.