Research On The Electric Bus Operational Reliability Based On Arrival Time Prediction

The reliability of bus travel time is not only one of the important indicators for evaluating the operation state of urban public transport but also an important factors passengers will consider when they choosing traffic mode.The existing research on bus reliability are most focuses on fuel bus,natural gas bus and hybrid bus.There are great differences between electric bus reliability and fuel bus reliability.Therefore,it is necessary to study the reliability of pure electric bus to provide real-time bus running time information for passengers and improve their travel time reliability.In this paper,electric bus is taken as the research object.Firstly,with the analysis of the influencing factors of the arrival time of electric bus,the Back Propagation(BP)Neural Network arrival time prediction model optimized by Firefly Algorithm is established by selecting vehicle type,SOC value,battery age and time as input conditions.The model is trained and tested with real bus operation data.The Root Mean Square Error of Kalman filter model is 35.1%,that of BP neural network model is 5.9%,and that of BP Neural Network optimized by firefly algorithm is 4.0%.The result shows that the model in this paper effectively improves the prediction accuracy and has good reliability and feasibility.Secondly,the passenger’s travel process is analyzed.From passenger’s point of view,the reliability bus passenger’s travel time is divided into two parts: waiting time reliability and riding time reliability.The probability distribution fitting of the time distribution of bus passengers arriving at bus stops and the unit distance running time of bus intervals is carried out respectively,then the reliability models of waiting time and riding time are established.Analytic Hierarchy Process is used to determine the index weight of coefficient,and a comprehensive evaluation model of travel time reliability of electric bus is established.The comprehensive evaluation model is validated by using the operation data of Fuzhou 321 electric bus.The result shows that the reliability of bus passenger travel time is 0.845 in peak time and 0.687 in peak time.The calculation results are in good agreement with the actual situation,which shows that the proposed passenger perception reliability evaluation model of bus travel time is feasible and reasonable.Finally,an optimal scheduling model of pure electric bus operation reliability is established,which is constrained by vehicle capacity rate,departure interval,the running range of vehicle and charging time of pure electric bus.The objective of the model is to minimize passenger travel cost and maximize the operating revenue of bus enterprises.The Genetic-Simulated Annealing Algorithm is used to solve the model.The model is validated by a specific example.The result shows that the scheduling model constructed in this paper is reasonable and can be used to solve the optimization problem of the departure schedule of electric bus.