Designing Network Topology Using Data Envelopment Analysis

The topology of a network seriously affects its cost, reliability, throughput, and traffic pattern, etc, so we need to simultaneously consider these multiple criteria, which have different units, when evaluating network topologies. However, ordinary methods of network topology design considered only a single criterion. DEA (data envelopment analysis) enables us to simultaneously evaluate multiple criteria, and it has been widely used when evaluating the efficiency of a business or a project. DEA derives the optimality of each candidate by emphasizing strong criteria in its evaluation. In this paper, we apply DEA to network topology design, and we numerically show that it enables us to effectively focus on a small number of desirable topology candidates. We also compare the results of DEA with those obtained by the generic algorithm (GA).