Generating desirable network topologies using multiagent system

Abstract

Designing network topologies requires simultaneous consideration of multiple criteria, such as network cost and reliability. So, the author applied the analytic hierarchy process, a way to make a rational decision considering multiple criteria, to network topology evaluation. However, the time required to construct the candidate topology set greatly increases as the network scale grows. Therefore, the author proposed to generate candidate topologies within a practical time frame for large-scale networks by limiting the positions for putting links to a small set of candidates. However, the diversity of the obtained candidate set is limited because the links are always put at certain link positions and are never put at a majority of the other link positions in all the candidate topologies generated. Therefore, this paper proposes to use of a multiagent system, in which each agent autonomously behaves to maximize each criterion, for generating a candidate topology set with high diversity within a practical time frame for large-scale networks.