Performance analysis of optimization techniques in peer-to-peer video streaming systems with tree/forest topology

Peer-to-peer video streaming systems are overlay networks used to distribute, among other types of content, live video content to large sets of users by relying on network and computing resources directly provided by users that are receiving the video stream. In this paper, we analyze the impact of two optimization techniques that can be adopted in peer-to-peer video streaming systems, with tree or forest topology, to cope with the negative effects of user's leaves. We carry out a performance analysis of these systems, analyzing their sensitivity to the most critical system parameters, when nearly-permanent nodes, i.e., peers with a smaller-than-average leave rate, are used to optimize the overlay topology.