Abstract

Dynamic characterization of energy availability profiles is paramount for an adequate incorporation of Non-Conventional Renewable Energies. This fact is particularly significant for sizing and design of eolic energy parks. The integration of eolic parks with interconnected systems requires accurate and precise knowledge on maximum and minimum power availability, as well as the moments in which you should expect the aforementioned conditions. Prognosis tools can help to determine the wind speed with a certain degree of reliability, in order to forecast energy availability. In this regard, this article presents the design and implementation of a wind speed vector-autoregressive-based prognosis method which includes data clustering, time series statistical analysis and its characterization through time-variant parametric models, for a medium term horizon. The proposed method is able to perform the prognosis for a complete day in just one step, instead of classic approaches that repeat several one-step ahead transitions to obtain similar results. The employed methodology facilitates the identification of periodical components of the wind, including daily and seasonal, facilitating the differentiation of data clusters with similar behaviors or tendencies. In order to perform the clustering, seasonal patterns are distinguishable through the use of similar probability distributions. Kullback-Leibler divergence is used as a measure of the difference between the probability distributions, while the K-means algorithm is used for clustering. Finally, for the validation of the design two common methods are implemented: Nielsen Reference Model and an ARMA-GARCH model. Our comparative analysis shows that the proposed method greatly improves the precision and accuracy of the resulting wind forecasting.