Hierarchical distributed system network design with cost-performance tradeoffs

Design of a large distributed system (DS) is becoming increasing important and with its added popularity, it is crucial to define its topology based on some objective function. This paper introduces a reliability-based systematic approach for defining the topology of a DS network in a hierarchical form, given the traffic requirements, a set of cluster topologies and the cost constraints. The authors scheme first identifies a group of permissible inter-cluster links which yields the maximum network reliability to cost ratio and then selects the gateways within each cluster for balancing the traffic through the inter-cluster links and the node degrees within each cluster. The usefulness of their method lies in a simultaneous consideration of the cost and the network reliability. Some examples are included to illustrate their design procedure.<>