Desenvolvimento de um modelo de clusterização de usinas eólicas para atendimento dos modelos de previsão do ONS
Keywords: Wind power, clustering, electrical systems planning
AbstractThe present work proposes to obtain a clustering of wind farms using the Gaussian Mixture Models (GMM) method, based on the wind profile and geographic location of wind farms operating in the South and Northeast regions from Brazil. The purpose of the generated grouping is to provide inputs for the wind generation forecasting models, helping the daily schedule of the operation of the National Electric System Operator (ONS). The success of this application allows the creation of generation and wind series more assertively within each cluster, thus increasing the reliability of the system operation. Thus, the main contribution of this work is to propose an alternative form of clustering, in relation to what is currently used by the ONS.