Skip to Main Content
In this paper, we consider minimum cost lossless source coding for multiple multicast sessions. Each session comprises a set of correlated sources whose information is demanded by a set of sink nodes. We propose a distributed end- to-end algorithm which operates over given multicast trees, and a back-pressure algorithm which optimizes routing and coding over the whole network. Unlike other existing algorithms, the source rates need not be centrally coordinated; the sinks control transmission rates across the sources. With random network coding, the proposed approach yields completely distributed and optimal algorithms for intra-session network coding. We prove the convergence of our proposed algorithms. Some practical considerations are also discussed. Experimental results are provided to complement our theoretical analysis.
Decision and Control, 2007 46th IEEE Conference on
Date of Conference: 12-14 Dec. 2007