Driver- and situation-specific impact factors for the energy prediction of EVs based on crowd-sourced speed profiles

This paper presents a system for the prediction of the necessary energy for selected trips of electric vehicles (EVs), which can be used for various EV assistants like range estimation. We use statistical features extracted from crowd-sourced speed profiles for the energy prediction, since they consider the varying impact factors of the individual driving style and the prevailing traffic condition. A statistical prediction model uses these features in order to predict the deviation from the mean energy consumption of the EV. Hence, the model predicts the variance of energy consumption caused for example by individual driving behavior. The results show an improvement of the energy prediction by 5.4 percentage points if the statistical features are considered. The prediction of the propulsion energy for EVs before the start of a given route has a relative mean error of 6.8%.