S4Q: Searching for QoE in P2P streaming neighborhoods

Abstract

In P2P video streaming systems, the neighbor selection algorithm is one of the fundamental components that affects performance. Although a few neighbor selection methodologies have been proposed, none of them takes into consideration QoE metrics reported by peers as a parameter for decisions. In this work, we present a new metric that quantifies the QoE as a function of the number of absences of pieces of a video during playback, referred to as stress level. A peer is stable if its stress level remains constant over a certain interval of time. Then, we propose a new neighbor selection algorithm for P2P streaming. The algorithm promotes exchanges of lists of stable peers, in order to get shorter download times and minimum interruption during video playback. The performance results show that our proposal is competitive against other state-of-the-art algorithms, reducing the number of absences of video pieces during playback by at least 19% and the average stress level by up to 32%.