Driving range estimation for electric bus based on atomic orbital search and back propagation neural network

Abstract

As urbanization and transportation demands continue to increase, electric buses play an important role in sustainable urban development thanks to their advantages of emission reduction, noise and pollution reduction. However, electric buses still face some challenges, in which, range anxiety is one of the main factors limiting its popularization. To solve this problem, an accurate estimation method for the driving range of electric buses based on atomic orbital search (AOS) algorithm and back propagation neural network (BPNN) was used, in which a long-term bus operation dataset under different driving conditions is utilized to train BPNN, and then weight and bias are taken as the first generation provided for AOS approach to find a more appropriate parameter combination. Simulation and experimental analysis show that the algorithm introduced in this paper has higher prediction accuracy and efficiency compared to the traditional machine learning algorithms, that compared with BPNN, AOSBP reduced MAE, RMSE and MAPE by 85.6%, 50.9% and 64.6%, respectively, which effectively relieves range anxiety, and ensures the normal operation of the electric bus fleet.