“Dust in the Wind...”, Deep Learning Application to Wind Energy Time Series Forecasting

• Published in: Energies (Basel) Vol. 12; no. 12; p. 2385
• Main Authors: Manero, Jaume, Béjar, Javier, Cortés, Ulises
• Format: Journal Article Publication
• Language: English
• Published: Basel MDPI AG 21.06.2019
• Subjects: Algorithms; Aprenentatge automàtic; Artificial intelligence; Atmospheric pressure; Clean energy; CNN; Deep learning; Electricity; Energia eòlica; Energies; Energy; Error analysis; Gas oil; Genetic transformation; Ground level; Information processing; Informàtica; Intel·ligència artificial; Machine learning; MLP; Multi-step forecasting; Multilayers; Neural networks; Optimization; Pressure; Previsió del temps; Recurrent neural networks; RNN; Standard error; Temperature; Time series; Turbines; Universal time; Uranium; Weather forecasting; Wind direction; Wind energy forecasting; Wind measurement; Wind power; Wind speed; Wind speed forecasting; Wind time series; Àrees temàtiques de la UPC; United States > US; Germany; Spain
• ISSN: 1996-1073; 1996-1073
• DOI: 10.3390/en12122385

To balance electricity production and demand, it is required to use different prediction techniques extensively. Renewable energy, due to its intermittency, increases the complexity and uncertainty of forecasting, and the resulting accuracy impacts all the different players acting around the electricity systems around the world like generators, distributors, retailers, or consumers. Wind forecasting can be done under two major approaches, using meteorological numerical prediction models or based on pure time series input. Deep learning is appearing as a new method that can be used for wind energy prediction. This work develops several deep learning architectures and shows their performance when applied to wind time series. The models have been tested with the most extensive wind dataset available, the National Renewable Laboratory Wind Toolkit, a dataset with 126,692 wind points in North America. The architectures designed are based on different approaches, Multi-Layer Perceptron Networks (MLP), Convolutional Networks (CNN), and Recurrent Networks (RNN). These deep learning architectures have been tested to obtain predictions in a 12-h ahead horizon, and the accuracy is measured with the coefficient of determination, the R² method. The application of the models to wind sites evenly distributed in the North America geography allows us to infer several conclusions on the relationships between methods, terrain, and forecasting complexity. The results show differences between the models and confirm the superior capabilities on the use of deep learning techniques for wind speed forecasting from wind time series data.