On-Demand Media Streaming Over the Internet

Peer-to-peer (P2P) systems are gaining increasing attention in research as well as industrial communities. In this paper, we propose a new model for on-demand media streaming centered around the P2P paradigm. The proposed P2P model can support a large number of clients with a modest overall system cost. The P2P model allows for peers to share some of their resources with the system and in return, they get some incentives or rewards. We propose two architectures to realize (or deploy) the proposed model. One architecture relies on a special entity, an index, to facilitate locating the peers in the system. The second architecture is a pure P2P and builds an overlay layer over the participating peers. For each architecture, we present new dispersion algorithms (for disseminating the media files into the system) and searching algorithms (for locating peers with the required objects). In addition, we conduct a cost-profit analysis of a media streaming service built on top of a P2P infrastructure. The analysis shows that with the appropriate incentives for the participating peers, the service provider achieves more profit. The analysis also shows how the service provider can maximize its revenue by controlling the amount of incentives offered to peers. By comparing the economics of the P2P and the conventional client/server media streaming architectures, we show that with a relatively small initial investment, the P2P model can realize a large-scale media streaming service. Finally, we demonstrate the potential of the P2P model as an infrastructure for a large-scale on-demand media streaming service through an extensive simulation study on large, Internet-like, topologies. We evaluate several performance measures of the proposed model under different client arrival patterns such as constant rate arrivals, flash crowd arrivals, and Poisson arrivals.