A multi-objective genetic algorithm based bus vehicle scheduling approach

Vehicle scheduling problem of urban bus line is complex and involves multiple objectives. Currently, existing approaches incorporate those objectives in a linear fashion to form a single objective and then use a single objective optimization approach to solve it. However, these approaches can only produce one solution and it is not easy to assign a proper weight for each objective to get a superior solution that can balance the preferences of different objectives. In this paper, an improved NSGA-II is proposed to create a set of Pareto solutions for this problem. This approach is applied to a real-world vehicle scheduling problem of a bus line. Experiments show that this approach is able to quickly produce satisfactory Pareto solutions, which outperforms the actually used experience-based solution.