Authors: Tein-Yaw Chung, Miao-En Chien, Yu-Lun Shih, Chung-Yu Hsu, Fong-Ching Yuan
With the emerging diversified online video service, the P2PTV, which is gradually emerging as a potential alternative to well known client-server applications such as IPTV, Video-on-Demand (VoD) and other real-time TV services, has been one of the most important systems in Internet TV. Quality of Service (QoS) and Quality of Experience (QoE) are the two major factors which need to be ensured in order to achieve P2PTV customer satisfaction, where channel switching delay has been the major problem. However, most of the peer selection strategies (PSS) consider merely one aspect of effective factors. In this paper, we focus on peer selection strategies to reduce channel switching delay in P2PTV system, and propose an Efficient Peer Selection Algorithm (EPSA), which gives consideration not only to start-up
delay, channel switching delay and streaming quality, but also network conglomeration. Finally, we use OMNeT++ to simulate the EPSA model and compare with random PSS model. The results show that the EPSA model performs non-negligible enhancement on both start-up time and channel switching time. We believe that these techniques will also benefit the service quality in other P2P live streaming applications.
Keywords: P2PTV; Internet TV; channel switching time; peer selection strategy