Hierarchical clustering with topology databases

Abstract

Dynamic routing in networks helps to provide efficient utilization of network resources. However, when networks are too large, the overhead introduced by dynamic routing consumes too much of network resources (processing, transmission capacity, and storage). To overcome this, researchers have investigated techniques to hierarchically organize networks and thereby reduce overhead. This paper introduces a new technique to organize routing information in large networks. A "radius database" provides optimal routing between frequent communicators. The combination of a "cluster database", and a backbone, allows reasonable routing to all nodes. The paper details the information maintained at each node, describes distributed update algorithms to allow dynamic maintenance of the information, and indicates how to cluster networks to take advantage of this techniques. Simulation results support the efficacy of the technique. © 1988.