A hybrid computer simulation genetic algorithm for scheduling optimisation of cargo trains with time and queue limitations

Abstract

This paper presents the scheduling optimisation of cargo trains by hybrid computer simulation (CS) and genetic algorithm. Scheduling cargo trains is based on the timetable of passenger trains that have priority in relation to cargo trains. System modelling is accomplished by Visual SLAM by considering time limitations, queue priority and limited station lines. Time limitations define that a cargo train is permitted to travel from station i to j if scheduled passenger trains have completed the travel from station i to j . Queue priority means that passenger trains have priority over cargo trains. In addition, each station has a limited storage track. In addition, all repair, maintenance, loading and unloading activities are included in the simulation model. The GA is then applied to find a near-optimal schedule based on minimum queue time. The superiority and applicability of the proposed approach is shown based on a specific train route in Iran.