Super Local Models for Wind Power Detection

• María Barroso ^[1] ; Ángela Fernández ^[1]
  1. [1] Universidad Autónoma de Madrid

     Universidad Autónoma de Madrid

     Madrid, España

     
• Localización: Hybrid Artificial Intelligent Systems: 16th International Conference, HAIS 2021. Bilbao, Spain. September 22–24, 2021. Proceedings / coord. por Hugo Sanjurjo González, Iker Pastor López, Pablo García Bringas, Héctor Quintián Pardo, Emilio Santiago Corchado Rodríguez, 2021, ISBN 978-3-030-86271-8, págs. 343-354
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • Local models can be a useful, necessary tool when dealing with problems with high variance. In particular, wind power forecasting can be benefited from this approach. In this work, we propose a local regression method that defines a particular model for each point of the test set based on its neighborhood. Applying this approach for wind energy prediction, and especially for linear methods, we achieve accurate models that are not dominated by low wind samples, and that implies an improvement also in computational terms. Moreover it will be shown that using linear models allows interpretability, gaining insight on the tackled problem.