Evaluation of Evolutionary Algorithms for Multi-objective Train Schedule Optimization


Evolutionary computation techniques have been used widely to solve various optimization and learning problems. This paper describes the application of evolutionary computation techniques to a real world complex train schedule multiobjective problem. Three established algorithms (Genetic Algorithm GA, Particle Swarm Optimization PSO, and Differential Evolution DE) were proposed to solve the scheduling problem. Comparative studies were done on various performance indices. Simulation results are presented which demonstrates that DE is the best approach for this scheduling problem.