Genetic algorithm based rainbow network flow optimization for multiple description coding in lossy network
Hüseyin Kusetoğulları, Amir Yavariabdi, Mark Stephen Leeson, Evor L. Hines · International Conference for Internet Technology and Secured Transactions · 2010
In this paper, multi-path optimization using genetic algorithm (GA) and rainbow network flow (RNF) for maximizing the received multiple description coding (MDCs) in a lossy network model is proposed. The network flow of multiple description codes (MDCs) is considered and the idea of routing as finding paths for a rainbow of colours (rainbow network flow or RNF) incorporated. The GA is used to find the optimum disjoint paths between source node and the destination node to optimize the amount of outgoing MDC packets. The MDCs are generated by applying the Discrete Wavelet Transform (DWT) and provide maximal performance of the bandwidth capacity of every single route for image transmission across the network. The GA based method finds the optimum solution and the effects of variations in GA parameters are investigated.