Prediction of EV Charging Behavior Using Machine Learning

Abstract

As a key pillar of smart transportation in smart city applications, electric vehicles (EVs) are becoming increasingly popular for their contribution in reducing greenhouse gas emissions. One of the key challenges, however, is the strain on power grid infrastructure that comes with large-scale EV deployment. The solution to this lies in utilization of smart scheduling algorithms to manage the growing public charging demand. Using data-driven tools and machine learning algorithms to learn the EV charging behavior can improve scheduling algorithms. Researchers have focused on using historical charging data for predictions of behavior such as departure time and energy needs. However, variables such as weather, traffic, and nearby events, which have been neglected to a large extent, can perhaps add meaningful representations, and provide better predictions. Therefore, in this paper we propose the usage of historical charging data in conjunction with weather, traffic, and events data to predict EV session duration and energy consumption using popular machine learning algorithms including random forest, SVM, XGBoost and deep neural networks. The best predictive performance is achieved by an ensemble learning model, with SMAPE scores of 9.9% and 11.6% for session duration and energy consumptions, respectively, which improves upon the existing works in the literature. In both predictions, we demonstrate a significant improvement compared to previous work on the same dataset and we highlight the importance of traffic and weather information for charging behavior predictions.

The role of asymmetric prediction losses in smart charging of electric vehicles

“…Decision tree-like methods are also the most utilised methods by ensemble approaches [42,31,43]. Numerous studies also applied artificial neural networks to predict EV charging behaviour [41,36,27,37], long short-term memory networks [21] as well as quantile neural networks [23]. Ensemble approaches combine prediction methods, e.g., [36] combined support vector machines, random forest, deep neural network, and XGBoost into voting and stacking ensemble.…”

“…In [33], authors predicted energy demand and charging duration, considering work charging and applied them to study possibilities of load curve smoothing. This work was extended in [35] and [36], while improving the accuracy of predictions. Frendo et al [37] made predictions of EV departure times using regression models trained on historical work charging data.…”

Road Traffic Forecast Based on Meteorological Information through Deep Learning Methods

“…In [7], Deb et al only used RMSE, while Yin et al [8] used MAE, RMSE and MAPE. Shahriar et al [9] used the metrics of RMSE, MAE, SMAPE and the coefficient of determination (R 2 ) to evaluate the performance of the regression models. Generally, small values of RMSE, MAE, and SMAPE demonstrate accurate predictions.…”

“…If the value of the coefficient of determination is equal to one, we have a perfect prediction. Generally, a higher value of the coefficient of determination demonstrates a better performance [9]. Badii et al [10] only used the performance metric mean absolute scaled error (MASE).…”

Learning Assisted Demand Charge Mitigation for Workplace Electric Vehicle Charging

“…The focus of this work is on the load profile of individual charging electric vehicles which directly impacts the load profile of workplace charging infrastructure. Supervised machine learning prediction of charging behaviour includes other categories such as the prediction of EV battery state of charge [9], the prediction of session duration and energy consumption [10], the prediction of future energy needs to meet forecasted EV growth [11], and the prediction of charging speed [12].…”