Hierarchical Clustering of Message Flows in a Multicast Data Dissemination System

A large-scale data dissemination application is characterized by a large number of information flows and information consumers. Consumers are interested in different, yet overlapping, subsets of the flows. Multicast is used to deliver subsets of the flows to subsets of the consumers. Since multicast groups are a limited resource, each consumer must filter out a large number of unneeded flows. We alleviate the end-node filtering load by using hierarchical clustering of flows to transport-layer sessions, and clustering of sessions to network-layer multicast groups. This scheme allows for hierarchical filtering of flows at the receivers. We formulate a cost function that models and emphasizes the filtering process, and propose algorithms for the solution of the hierarchical mapping problem. Performance evaluation indicates a significant reduction of endnode filtering cost compared to a non-hierarchic approach.