Abstract :
Network topology seriously affects network cost, path length, distribution of link load, and reliability, for example, so we need to consider these multiple criteria with different units simultaneously when designing network topology. The analytic hierarchy process (AHP) is a way to make a rational decision considering multiple criteria. Using AHP, we can reflect the relative importance of each criterion on the evaluation result, so we have applied it to network topology evaluation. When evaluating network topologies using AHP, we need to construct the set of topology candidates prior to the evaluation. However, the time required to construct this set greatly increases as the network size grows. In this paper, we propose to apply a binary partition approach for constructing a topology candidate set with dramatically reduced calculation time. To reduce the calculation time, we introduce an upper limit for the total link length. Although the results of AHP are affected by introducing the upper limit of total link length, we show that desirable topologies are still selected in AHP.
