La titularidad de los derechos patrimoniales de esta obra pertenece a las instituciones editoras. Su uso se rige por una licencia Creative Commons BY-NC 4.0 Internacional, https://creativecommons.org/licenses/by-nc/4.0/legalcode.es, para un uso diferente consultar al responsable jurídico del repositorio por medio del correo electrónico editora@atmosfera.unam.mx.
Ver términos de la licencia
Instituto de Ciencias de la Atmósfera y Cambio Climático, UNAM
Revista
Repositorio
Contacto
Revistas UNAM. Dirección General de Publicaciones y Fomento Editorial, UNAM en revistas@unam.mx
Diaz-esteban, Yanet, et al. (2024). Using a hybrid approach for wind power forecasting in Northwestern Mexico. Atmósfera; Vol. 38, 2024; 263-288. Recuperado de https://repositorio.unam.mx/contenidos/4152348
Autor(es)
Diaz-esteban, Yanet; López-villalobos, Carlos Alberto; Ochoa Moya, Carlos Abraham; Romero-centeno, Rosario; Quintanar, Ignacio Arturo
Tipo
Artículo de Investigación
Área del conocimiento
Físico Matemáticas y Ciencias de la Tierra
Título
Using a hybrid approach for wind power forecasting in Northwestern Mexico
Fecha
2023-10-30
Resumen
Wind energy is an important renewable source that has been considerably developed recently. In order to obtain successful 24-h lead-time wind power forecasts for operational and commercial uses, a combination of physical and statistical models is desirable. In this paper, a hybrid methodology that employs a numerical weather prediction model (Weather Research and Forecasting) and a neural network (NN) algorithm is proposed and assessed. The methodology is applied to a wind farm in northwestern Mexico, a region with high wind potential where complex geography adds large uncertainty to wind energy forecasts. The energy forecasts are then evaluated against actual on-site power generation over one year and compared with two reference models: decision trees (DT) and support vector regression (SVR). The proposed method exhibits a better performance with respect to the reference methods, showing an hourly normalized mean absolute percentage error of 6.97%, which represents 6 and 13 percentage points less error in wind power forecasts than with DT and SVR methods, respectively. Under strong synoptic forcing, the NN wind power forecast is not very accurate, and novel approaches such as hierarchical algorithms should be employed instead. Overall, the proposed model is capable of producing high-quality wind power forecasts for most weather conditions prevailing in this region and demonstrates a good performance with respect to similar models for medium-term wind power forecasts.
Tema
wind power forecast; neural network; multi-layer perceptron; numerical weather prediction; wind forecast; Mexico
Idioma
eng
ISSN
ISSN electrónico: 2395-8812; ISSN impreso: 0187-6236
DOI
https://doi.org/10.20937/ATM.53258
