Bus Departure Time Optimization with Rail Transportation Transfer Demand Prediction
LIU Qian1,SUN Yu-e1,HUANG He2,DU Yang2
1(School of Rail Transportation,Soochow University,Suzhou 215131,China)2(School of Computer Science and Technology,Soochow University,Suzhou 215006,China)
Abstract:The optimization of passenger transfer between rail transportation and bus is an essential part of improving the public transportation system′s service.This paper aims to optimize bus departure time so that efficient transfer between rail transportation and bus can be achieved when meeting regular passengers′ needs.Thus,this paper first obtains the historical transfer record by mining the passenger trajectories and then trains a multi-layer perceptron neural network to predict the passenger transfer demand for the bus after rail transportation.For each bus line that contains multiple transfer stations,we use a genetic algorithm to compute an optimized bus departure time,which minimizes the waiting time cost for regular passengers and transfer passengers and the bus company′s operating cost.Taking the bus route 770 in Shanghai as an example,we evaluate the performance of the proposed model.Experimental results show that the optimized bus departure time can effectively reduce the waiting time of transfer passengers at transfer stations compared with the original timetable.
刘倩,孙玉娥,黄河,杜扬. 考虑轨道交通换乘需求的公交发车时刻优化模型[J]. 小型微型计算机系统, 2022, 43(2): 430-437.
LIU Qian,SUN Yu-e,HUANG He,DU Yang. Bus Departure Time Optimization with Rail Transportation Transfer Demand Prediction. Journal of Chinese Computer Systems, 2022, 43(2): 430-437.