A Machine Learning Method for Predicting Driving Range of Battery Electric Vehicles

It is of great significance to improve the driving range prediction accuracy to provide battery electric vehicle users with reliable information. A model built by the conventional multiple linear regression method is feasible to predict the driving range, but the residual errors between -3.6975 km and 3.3865 km are relatively unfaithful for real-world driving. The study is innovative in its application of machine learning method, the gradient boosting decision tree algorithm, on the driving range prediction which includes a very large number of factors that cannot be considered by conventional regression methods. The result of the machine learning method shows that the maximum prediction error is 1.58 km, the minimum prediction error is -1.41 km, and the average prediction error is about 0.7 km. The predictive accuracy of the gradient boosting decision tree is compared against that of the conventional approaches.

[1]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[2]  Jianqiu Li,et al.  A highly accurate predictive-adaptive method for lithium-ion battery remaining discharge energy prediction in electric vehicle applications , 2015 .

[3]  Phil Blythe,et al.  Routing systems to extend the driving range of electric vehicles , 2013 .

[4]  Yanru Zhang,et al.  A gradient boosting method to improve travel time prediction , 2015 .

[5]  Warren S. Vaz,et al.  Electric vehicle range prediction for constant speed trip using multi-objective optimization , 2015 .

[6]  Pavol Bauer,et al.  Generic methodology for driving range estimation of electric vehicle with on-road charging , 2015, 2015 IEEE Transportation Electrification Conference and Expo (ITEC).

[7]  Zbigniew Telec,et al.  Nonparametric statistical analysis for multiple comparison of machine learning regression algorithms , 2012, Int. J. Appl. Math. Comput. Sci..

[8]  Stella Morris,et al.  Simulation of a distance estimator for battery electric vehicle , 2015 .

[9]  Lili Li,et al.  Energy and environmental impact of battery electric vehicle range in China , 2015 .

[10]  Giovanni Pede,et al.  Techniques for estimating the residual range of an electric vehicle , 2001, IEEE Trans. Veh. Technol..

[11]  Keith J. Burnham,et al.  Online Use of the Fuzzy Transform in the Estimation of Electric Vehicle Range , 2013 .

[12]  Thomas Bräunl,et al.  Driving electric vehicles at highway speeds: The effect of higher driving speeds on energy consumption and driving range for electric vehicles in Australia , 2016 .

[13]  Lili Li,et al.  Method for evaluating the real-world driving energy consumptions of electric vehicles , 2017 .

[14]  Ingmar Posner,et al.  Probabilistic attainability maps: Efficiently predicting driver-specific electric vehicle range , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.

[15]  Michael A. Danzer,et al.  Lithium plating in a commercial lithium-ion battery - A low-temperature aging study , 2015 .

[16]  Ying Cao,et al.  Advance and Prospects of AdaBoost Algorithm , 2013, ACTA AUTOMATICA SINICA.

[17]  Kang G. Shin,et al.  Real-time prediction of battery power requirements for electric vehicles , 2013, 2013 ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS).

[18]  Chris Bingham,et al.  Impact of driving characteristics on electric vehicle energy consumption and range , 2012 .

[19]  Angelos Amditis,et al.  Online prediction of an electric vehicle remaining range based on regression analysis , 2014, 2014 IEEE International Electric Vehicle Conference (IEVC).