Abstract | ||
---|---|---|
We address the problem of distributed path selection and rate allocation for media streaming in overlay networks. Under the assumption that each node has only a local view of the network, we propose a distributed algorithm for joint path selection, and rate allocation, in order to minimize the end-to-end media distortion. The distributed algorithm per- forms iteratively, by greedy rate allocation for all incom- ing media flows on the outgoing links at each intermediate node. Our algorithm is shown to converge to the optimal rate allocation solution in a very small number of iterations, and to outperform heuristic distributed rate allocation mech- anisms for a number of random network topologies. Our prior work (2) provides a general framework for the analysis of joint path and rate allocation in multipath streaming, driven by media-specific metrics. We consider a network model composed of multiple flows, and a stream- ing server that can adapt the media source rate to the trans- mission conditions (by scalable coding, or transcoding, for example). Given the knowledge of the network parame- ters, the server computes the optimal set of paths for trans- mission, along their optimal rate allocation. In this paper we release the assumption on network status knowledge at the server, and we propose a distributed path selection and rate allocation algorithm. Previous works in distrib- uted video streaming (3, 7, 5) deal with resource allocation and scheduling on multiple, a priori chosen streaming paths, with the final goal of minimizing the overall distortion per- ceived by the media clients. None of these works address the problem of an optimal choice of streaming paths on an available network graph, and their corresponding rate allo- cation. The rest of this paper is organized as follows. In Sec- tion 2, we identify the streaming scenario under considera- tion and briefly present the optimization problem. Section 3 presents our distributed approach towards solving the op- timization problem. We discuss the performance of our al- gorithm in Section 4 and present the simulation results in Section 5. Finally, we conclude in Section 6. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1109/ICME.2006.262801 | ICME |
Keywords | Field | DocType |
distributed algorithms,iterative methods,media streaming,telecommunication network topology,distributed algorithm,distributed path selection,iterative method,media streaming,overlay network,random network topology,rate allocation | Heuristic,Random graph,Iterative method,Computer science,Computer network,Network topology,Distributed algorithm,Intelligent Network,Overlay network,Encoding (memory) | Conference |
Citations | PageRank | References |
3 | 0.45 | 5 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dan Jurca | 1 | 105 | 8.08 |
Pascal Frossard | 2 | 3015 | 230.41 |