ARIMA-based demand forecasting method considering probabilistic model of electric vehicles' parking lots

Abstract

Electric transportation is one of the key elements of the future power systems since conventional power networks are rapidly evolving towards smart grids. This transition creates the need for systematic utilization of electric vehicles (EV) in order to avoid unpredictable effects on the power systems. An accurate and efficient method for demand forecasting of EVs is needed to perform a feasible scheduling of resources in order to supply the predicted load sufficiently. This paper presents a method for electricity demand forecasting considering EV parking lots' charging demand using historical load data. The method is based on auto-regressive integrated moving average (ARIMA) model for medium-term demand forecasting. The proposed approach improves the forecasting accuracy. Probabilistic hierarchical EVs' parking lot demand modeling is used to estimate the expected load for each parking lots' daily charging demand. In order to evaluate the effectiveness of the proposed approach, it is implemented on PJM historical load data. The simulation results show the high accuracy of the proposed method for electricity demand forecasting.