LAUSR

One of the current issues in the peer-to-peer streaming systems is to supply sufficient upload bandwidth for continuous streaming of high-quality video channels. The helpers as upload bandwidth boosters can improve the streaming capacity of system, so that the imbalance of upload bandwidth between different video channel overlays is compensated. With the deployment of helpers as an intermediate level between server and peers, building and maintaining the optimal peer-helper topology becomes a challenging task since the one-directional nature of video streaming from the helpers to users makes the well-known reciprocity-based algorithms useless. Because of selfish behavior of peers and lack of a central authority among them, selection of helpers requires implicit coordination. In this paper, we design a decentralized, stochastic approximation helper selection mechanism which is adaptable to supply and demand pattern of various video channels. Our regret-tracking-based solution for allowing peers to strategically exploit their shared resources is guaranteed to converge to the correlated equilibria (CE) among the helper selection strategies. Online convergence to the set of CE is achieved through the regret-tracking algorithm which tracks the equilibrium in the presence of stochastic dynamics of helpers’ bandwidth. The resulting CE can help to select proper cooperation policies. Simulation results demonstrate that our algorithm achieves good convergence, load distribution on helpers and sustainable streaming rates for peers.