Author(s)

Adrian-Nicolae Buturache¹, Stelian Stancu²

¹Economic Cybernetics and Statistics Doctoral School, Bucharest University of Economic Studies, Bucharest, Romania.
²Informatics and Economic Cybernetics Department, Bucharest University of Economic Studies, Bucharest, Romania.

Wind energy prediction represents an important and active field in the renewable energy sector. Since renewable energy sources are integrated into existing grids and combined with traditional sources, knowing the amount of energy that will be produced is key in minimizing the operational cost of the wind farm and safe operation of the power grid. In this context, we propose a comparative and comprehensive study of artificial neural networks, support vector regression, random trees, and random forest, and present the pros and cons of implementing the aforementioned techniques. A step-by-step approach based on the CRISP-DM data mining framework reveals the thought process end-to-end, including feature engineering, metrics selection, model selection, or hyperparameter tuning. Using the selected metrics for model evaluation, we provide a summary highlighting the optimal results and the trade-off between performance and the resources expended to achieve these results. This research is also intended to provide guidance for wind energy professionals, filling the gap between purely academic research and real-world business use cases, providing the exact architectures and selected hyperparameters.

Artificial Neural Networks, Support Vector Machine, Regression Tree, Random Forest, Hyperparameter Tuning, Renewable Energy, Data-Driven Decision

Buturache, A. and Stancu, S. (2021) Wind Energy Prediction Using Machine Learning. Low Carbon Economy, 12, 1-21. doi: 10.4236/lce.2021.121001.