Electric Vehicle User Behavior Prediction Using Hybrid Kernel Density Estimator

Abstract

This paper proposes a hybrid kernel density estimator (HKDE) that uses both Gaussian- and Diffusion-based KDE (GKDE and DKDE) to predict the stay duration and charging demand of electric vehicles (EVs), which are essential parameters for optimizing EV charging schedule. While DKDE has higher accuracy in general, GKDE tends to result in better estimation for users who charge the EV irregularly. Therefore, the HKDE evaluates and categorizes the charging pattern regularity of a user, and determines which KDE to use by a novelty detection method based on the user's historical data. The estimations are then applied to an optimal EV charging algorithm to minimize load variance in an EV charging infrastructure and reduce EV charging cost. Real data is used for the numerical simulation to show the effectiveness of the proposed approach for predicting EV user behavior and scheduling EV charging load.