A distributed utility-based scheduling for peer-to-peer video streaming over wireless networks

Interactive multimedia applications such as peer-to-peer (P2P) video services over the Internet have gained increasing popularity during the past few years. However, the adopted Internet-based P2P overlay network architecture hides the underlying network topology, assuming that channel quality is always in perfect condition. Because of the time-varying nature of wireless channels, this hardly meets the user-perceived video quality requirement when used in wireless environments. Considering the tightly coupled relationship between P2P overlay networks and the underlying networks, we propose a distributed utility-based scheduling algorithm on the basis of a quality-driven cross-layer design framework to jointly optimize the parameters of different network layers to achieve highly improved video quality for P2P video streaming services in wireless networks. In this paper, the quality-driven P2P scheduling algorithm is formulated into a distributed utility-based distortion-delay optimization problem, where the expected video distortion is minimized under the constraint of a given packet playback deadline to select the optimal combination of system parameters residing in different network layers. Specifically, encoding behaviors, network congestion, Automatic Repeat Request/Query (ARQ), and modulation and coding are jointly considered. Then, we provide the algorithmic solution to the formulated problem. The distributed optimization running on each peer node adopted in the proposed scheduling algorithm greatly reduces the computational intensity. Extensive experimental results also demonstrate 4-14dB quality enhancement in terms of peak signal-to-noise ratio by using the proposed scheduling algorithm. Copyright (c) 2015 John Wiley & Sons, Ltd.