Design of optimal coasting speed for saving social cost in Mass Rapid Transit systems

The artificial neural network (ANN) has been proposed in this paper to determine the optimal coasting speed of the train set for a mass rapid transit system to achieve the maximization of social welfare. The energy consumption and the traveling time to complete the journey between stations with various riderships are calculated by executing the train performance simulation to generate the data set for ANN training. The objective function is formulated by considering the cost of energy consumption and the cost of passenger traveling time. The ANN model is obtained after performing the ANN training, which can be applied to solve the optimal coasting speed of train sets according to the distance between stations and the ridership of passengers. To demonstrate the effectiveness of the proposed ANN model, the forecasted annual ridership of train sets for Kaohsiung mass rapid transit (KMRT) system is used to determine the optimal coasting speed of train sets operating between stations for each study years. The corresponding profile of power consumption and the traveling time cost of passengers for the train operation have been solved to illustrate the social cost of MRT systems operation by applying the optimal coasting speed derived.