Simulation-based robust optimization of limited-stop bus service with vehicle overtaking and dynamics: A response surface methodology

We propose a robust optimization model for limited-stop bus service with vehicle overtaking and demand dynamics. Time-dependent stochastic travel time is also considered. The objective is to minimize the total cost (user cost and operation cost) at the planning phase given a target reliability imperative. We further propose a simulation-based optimization framework incorporating response surface methodology to solve the problem efficiently. A real-world application result shows that vehicle overtaking and demand dynamics have significant impacts on the performance of limited-stop service and that the stop patterns are quite distinct when overtaking and demand dynamics are considered.