Optimizing mass transit systems electrical infrastructure by application of the particle swarm optimization algorithm

Abstract

This paper presents an MTS electrical infrastructure optimizer which is based on the particle swarm optimization (PSO) algorithm. The goal of the optimizer consists of finding the optimal locations and sizes of a set of reversible power substations that will make it possible to have more energy-efficient MTSs. The optimization model includes detailed traffic and cost models to obtain reliable results for the MTS operator from the investment standpoint. The careful design of the PSO parameters leads to an optimized trade-off between exploration and exploitation of the infrastructure improvement search space. As a result, the optimizer is able to reach good infrastructure improvement solutions supported by a vast volume of traffic scenarios in a reasonable time.