High Speed Train Rescheduling Based on a Cooperative Particle Swarm Optimization Algorithm

Abstract

To solve the high speed train rescheduling problem, a mathematical model is constructed and a cooperative particle swarm optimization algorithm is proposed. The train rescheduling model takes the on-schedule rate and total delayed time of all the trains’ arrival at the related stations in the railway dispatching section as the optimization objectives. Minimal intervals between arrivals and departures, arrival and departure tracks, minimal running time in the railway sub-section are considered as the operation constraints. We design two swarms to ensure the global optimum and local optimum respectively when improving the computing performance of particle swarm optimization algorithm. The computing case is based on the actual data from Shanghai-Hangzhou high speed railway. Computing results validate the model and confirm the efficiency of the algorithm. The method proposed in this paper can improve the on-schedule rate of the trains and reduce the total delayed time when rescheduling trains on railway dispatching sections, which can be embedded in the novel train dispatching system.