Seasonality Effect Analysis and Recognition of Charging Behaviors of Electric Vehicles: A Data Science Approach

Abstract

Electric vehicles (EVs) presence in the power grid can bring about pivotal concerns regarding their energy requirements. EVs charging behaviors can be affected by several aspects including socio-economics, psychological, seasonal among others. This work proposes a case study to analyze seasonal effects on charging patterns, using a public real-world based dataset that contains information from the aggregated load of the total charging stations of Boulder, Colorado. Our approach targets to forecast and recognize EVs demand considering seasonal factors. Principal component analysis (PCA) was used to provide a visual representation of the variables and their contribution and the correlation among them. Then, twelve classification models were trained and tested to discriminate among seasons the charging load of electric vehicles. Later, a benchmark stage is presented for regression as well as for classification results. For regression models, examined through Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE), the random Forest provides better prediction than quasi-Poisson model widely. However, it was observed that for large variations in electric vehicles’ charging load, quasi-Poisson fits better than random forest. For the classification models, evaluated through Accuracy and the Area under the Curve, the Lasso and elastic-net regularized generalized linear (GLMNET) model provided the best global performance with accuracy up to 100% when evaluated on the test dataset. The results of this work offer great insights for enhancing demand response strategies that involve PEV charging regarding charging habits across seasons.

Optimization Schedule Schemes for Charging Electric Vehicles: Overview, Challenges, and Solutions

“…RF is an ensemble method that relies on multiple decision trees. According to [64], several studies have revealed that RF can produce more stable and accurate results than SVMs in load prediction, indicating its effectiveness in forecasting electrical load. In general, SL algorithms can be applied to EV charging, from learning of instances to predicting optimal charging schedules.…”

Surrogate Model-Based Calibration of a Flying Satellite Battery Digital Twin

“…The basic parameters usually considered to develop a simulation model of a battery are the capacity , voltage , current , temperature , state of charge , load and internal resistance , to mention a few (Acharya et al, 2019). Notice that, among the various configurable parameters of the above mathematical models, the capacity, , is usually considered of particular interest for its ability to drive the battery behaviour and being associated to its degradation (Dominguez-Jimenez et al, 2020). For such reasons, in this work, the capacity, , is the parameter to be calibrated by the proposed approach.…”

Photovoltaic Power

“…Finally, from the point of view of new applications and upright ideas that can be carried out thanks to PV power systems, in this Special Issue has published papers related to the pumping in urban water pressurized networks, nano-grids to road lighting systems, charging of electric vehicles, and virtual power plants (Contributions [14][15][16][17]. All the contributions in this collection of articles consider solutions to current problems that are worth revising.…”