Energy-efficient Train Timetable Optimization For Metro Based On Short-term Passenger Flow Prediction

With the popularity of private cars,the problem of road traffic congestion is becoming more and more serious,and the urban traffic pressure is increasing.The development of urban rail transit relieves the pressure of road traffic.With the rapid growth of subway construction,its accessibility is greatly enhanced,and the passenger volume keeps growing.Compared with private cars and public buses,urban rail transit is more energy efficient and environmentally friendly with the same capacity.However,with the rapid growth of passenger volume and operating mileage,the total energy consumption of urban rail transit is huge and increasing rapidly.Among them,the energy consumption of train operation accounts for about 50% of the total energy consumption of rail transit.Therefore,the study on how to reduce the energy consumption of trains while meeting the demand of passenger flow has attracted wide attention,which has important research value and practical significance.This paper focuses on three aspects: short-term passenger flow prediction,urban rail transit operation diagram compilation,and energy-efficient optimization of train operation diagram based on short-term passenger flow prediction of urban rail transit.Specific research contents are as follows:(1)Based on the temporal and spatial characteristics of passenger flow,a combined model for short-term passenger flow prediction in urban rail transit based on convolutional neural network and long-short term memory neural network is constructed.Using the actual passenger flow data as training samples,the prediction effect of the model is proved to be reliable and reasonable,which can be used as the basis for the optimization of urban rail transit operation diagram.(2)Make a theoretical analysis of the basic principles and methods for the compilation of urban rail transit train timetabling and discusses the situation and calculation methods in train operations.In addition,the train control strategy is analyzed.On this basis,analyze and discuss the influence of train timetable on energy consumption and the method of energy saving optimization of train timetable.(3)Based on the short-term passenger flow prediction results,the train departure interval and stop time were determined based on the maximum section passenger flow of the train and the number of passengers getting on and off at each station,and a train timetable was preliminarily drawn up to meet the passenger flow demand.Aiming at the minimum total energy consumption of the train and the minimum travel time on train of passengers,a new energy saving optimization method of the train timetable considering the change of the total mass of the train caused by the change of the train load is proposed,and the optimal solution is found by using the genetic algorithm based on elite strategy.At last,based on the historical passenger flow data of Shanghai metro line 2 as the training sample,the combined prediction model proposed in this paper is used to obtain the passenger flow situation of the next period,and then based on the actual line data of this line,the optimization method of the energy-efficient train operation is simulated and verified.