Online rescheduling for mass rapid transit system using evolutionary techniques with fuzzy aggregation of multiple objectives

Abstract

The purpose of this thesis is to present a new on-line rescheduling strategy, in which Differential Evolution (DE) with fuzzy logic is combined for multiple objectives for conflict resolution as well as maintaining optimal overall performance. The proposed strategy divides the study/control period into time windows of equal length, which slides from one time window to another according to a real-time clock. Automatic Train Regulator (ATR) predicts the timing of each inter-station run and other performance indices occurring in the present time window. According to the latest simulation results, ATR executes a DE-optimized train rescheduler to adjust all the train dispatch and dwell times, and train coasting levels of all inter-station runs within each time window for fast and near-optimal solutions. Besides DE, its counterpart, Genetic Algorithm is applied to ATR as a comparative study to prove DEa??s high efficiency on solving the online optimization problems.