The rising adoption of electric vehicles (EVs), driven by carbon neutrality goals, has prompted the need for accurate forecasting of EVs’ charging behavior. However, this task presents several challenges due to the dynamic nature of EVs’ usage patterns, including fluctuating demand and unpredictable charging durations. In response to these challenges and different from previous works, this paper presents a novel and holistic methodology for day-ahead forecasting of EVs’ plugged-in status and power consumption in charging stations (CSs). The proposed framework encompasses data analysis, pre-processing, feature engineering, feature selection, the use and comparison of diverse machine learning forecasting algorithms, and validation. A real-world dataset from a CS in Boulder City is employed to evaluate the framework’s effectiveness, and the results demonstrate its proficiency in predicting the EVs’ plugged-in status, with XGBoost’s classifier achieving remarkable accuracy with an F1-score of 0.97. Furthermore, an in-depth evaluation of six regression methods highlighted the supremacy of gradient boosting algorithms in forecasting the EVs’ power consumption, with LightGBM emerging as the most effective method due to its optimal balance between prediction accuracy with a 4.22% normalized root-mean-squared error (NRMSE) and computational efficiency with 5 s of execution time. The proposed framework equips power system operators with strategic tools to anticipate and adapt to the evolving EV landscape.
Due to the intermittent and variable nature of wind, Wind Power Generation Forecast (WPGF) has become an essential task for power system operators who are looking for reliable wind penetration into the electric grid. Since there is a need to forecast wind power generation accurately, the main contribution of this paper is the development, implementation, and comparison of WPGF methods in a framework to be used by distribution system operators (DSOs). The methodology applied comprised five stages: pre-processing, feature selection, forecasting models, post-processing, and validation, using the historical wind power generation data (measured at secondary substations) of 20 wind farms connected to the medium voltage (MV) distribution network in Portugal. After comparing the accuracy of eight different models in terms of their relative root mean square error (RRMSE), extreme gradient boosting (XGBOOST) appeared as the best-suited forecasting method for wind power generation. The best average RRMSE achieved by the proposed XGBOOST model for 1-year training (January–December of 2020) and 6 months forecast (January–June of 2021) corresponds to 13.48%, outperforming the predictions of the Portuguese DSO by 20%.