Abstract :
In multimedia applications such as IPTV, it is natural to accommodate multiple coexisting peer-to-peer streaming overlays, corresponding to channels of programming. With coexisting streaming overlays, one wonders how these overlays may efficiently share the available upload bandwidth on peers. In order to satisfy the required streaming rate in each overlay, as well as to minimize streaming costs. In this paper, we seek to design simple, effective and decentralized strategies to resolve conflicts among coexisting streaming overlays. Since such strategies of conflict are game theoretic in nature, we characterize them as a decentralized collection of dynamic auction games, in which downstream peers submit bids for bandwidth at the upstream peers. With extensive theoretical analysis and performance evaluation, we show that the outcome of these local games is an optimal topology for each overlay that minimizes streaming costs. These overlay topologies evolve and adapt to peer dynamics, fairly share peer upload bandwidth, and can be prioritized.
Keywords :
media streaming; peer-to-peer computing; coexisting streaming overlays; decentralized strategies; dynamic auction games; multimedia applications; peer-to-peer streaming overlays; upload bandwidth; Application software; Bandwidth; Communications Society; Cost function; Game theory; Network servers; Peer to peer computing; Performance analysis; Streaming media; Topology;