Modeling a robust wind-speed forecasting to apply to wind-energy production

• Published in: Neural computing & applications Vol. 31; no. 11; pp. 7891 - 7905
• Main Authors: Hernández-Travieso, José Gustavo, Travieso-González, Carlos M., Alonso-Hernández, Jesús B., Canino-Rodríguez, José Miguel, Ravelo-García, Antonio G.
• Format: Journal Article
• Language: English
• Published: London Springer London 01-11-2019; Springer Nature B.V
• Subjects: Airport siting; Airports; Artificial Intelligence; Artificial neural networks; Clean energy; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Data Mining and Knowledge Discovery; Economic forecasting; Image Processing and Computer Vision; Original Article; Probability and Statistics in Computer Science; Renewable energy; Turbines; Weather; Wind; Wind power; Wind speed; Green energy; Modeling; Wind-speed prediction; Artificial neural networks
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-018-3619-6

To obtain green energy, it is important to know, in advance, an estimation of the weather conditions. In case of wind energy, another important factor is to determine the right moment to stop the turbine in case of strong winds to avoid its damage. This research introduces a tool, not only to increase green energy generation from wind, reducing CO
2
emissions, but also to prevent failures in turbines that is especially interesting for manufacturers. Using Artificial Neural Networks and data from meteorological stations located in Gran Canaria airport and Tenerife Sur airport (both in Canary Islands, Spain), a robust prediction system able to determine wind speed with a mean absolute error of 0.29 m per second is presented.