A GA-Based Clustering Scheme for Overlay Multicast Topology Optimization

This paper proposed a topology clustering scheme based on genetic algorithm (GACluster) to improve the topology clustering performance in the course of constructing the hierarchical overlay multicast. The scheme firstly constructed the clustering feature space by normalizing the two routing metrics (overlay path delay and overlay node access bandwidth), and then implemented genetic algorithm for the topology clustering operation. The experiments illustrated, compared with the common clustering method HCM, that the proposed scheme performs better in both the clustering performance and the topology optimization.