Abstract Markovian Model for Data-Driven P2P Video Streaming Applications

he purpose of this study is to propose a Markovian model to evaluate general P2P streaming applications with the assumption of chunk-delivery approach similar to Bit-Torrent file sharing applications. The state of the system was defined as the number of useful pieces in a peer’s buffer. The model was numerically solved to find out the proba-bility distribution of the number of useful pieces. The central theme of this study revolved around answering the question: what is the probability that a peer can play the stream continuously? This is one of the most important metrics to evaluate the performance of a streaming application. By finding the numerical solution of the Markov chain, we found that increasing the number of neighbours enhances the continuity to a certain threshold, after which the continuity improvement is marginal which complies with empirical results con-ducted with DONet, a data-driven overlay network for media streaming. We also found that increasing the buffer length increases the continuity but there is a trade-off because peers exchange information about the buffer map, hence increasing the buffer length increases the overhead. We discussed the continuity for both homogeneous and heterogeneous peers regarding the uploading bandwidth. Then we discussed the case when the first chunk is downloaded, but not played out because the playtime deadline was missed. We suggested a general approach for freezing and skipping the playback pointer, that can be used to take advantage of the available delay tolerance, finally given a specific configuration we measured the probability of sliding action, that could be used to initiate peers ’ adaptation process