Optimizing and synchronizing timetables in an urban subway network considering trains’ speed profiles and skip-stop strategy

This research aims to introduce a mathematical model capable of producing an optimal and coordinated timetable for the entire urban rail network to minimize passengers’ travel times and the trains’ energy consumption. The proposed model focuses on different speed profiles and a skip-stop strategy while considering the stochastic nature of passengers’ arrival and departure rates. This novel model can generate an optimal real-time schedule under variations in passenger demand. The implementation of a multi-agent deep deterministic policy gradient has been described, and it has been compared with a genetic algorithm. Eventually, this methodology is implemented on lines 1, 2, and 4 of Tehran’s metro network as a case study. The results indicate that using the skip-stop strategy and optimizing trains’ speed profiles along their paths can reduce the networks’ costs, including passengers’ waiting costs and the trains’ energy consumption costs, by 2.9% and 14.9%, respectively.