Título: A Methodology For Data Cleaning Of Wind Speed Time Series
Autores: Pessanha, José F. M.; Castellani, Valk L. O.; Conceição, Thatiana J.; Penna, Debora D. J.; Maceira, Maria E. P.
Resumo: The prediction of wind resources is a key item for the safe and economic integration of wind farms in the operation of electrical systems. The accuracy of such predictions depends on the quality of the data. This article presents a methodology for filtering wind speed time series by using fuzzy clustering method (FCM) and local regression (LOESS). The goal is to improve the data quality for the time series modeling.
Palavras-chave: Wind power; wind speed; data cleaning; smothing; cluster analysis
Páginas: 6
Código DOI: 10.21528/CBIC2011-18.5
Artigo em pdf: st_18.5.pdf
Arquivo BibTex: st_18.5.bib