Support vector machines in the wind energy framework: a new model for wind energy forecasting

In this work we expose a new model for wind energy forecasting based in Support Vector Machines. Support vector machines (SVMs) are a group of supervised learning methods that can be applied to classification or regression. They represent an extension to nonlinear models of the generalized portrait algorithm developed by Vladimir Vapnik. Support vector machines (SVMs) appeared in the early nineties as optimal margin classifiers in the context of Vapnik's statistical learning theory. Since then SVMs have been successfully applied to real-world data analysis problems, often providing improved results compared with other techniques. The SVMs operate within the framework of regularization theory by minimizing an empirical risk in a well-posed and consistent way. A clear advantage of the support vector approach is that sparse solutions to classification and regression problems are usually obtained: only a few samples are involved in the determination of the classification or regression functions. This fact facilitates the application of SVMs to problems that involve a large amount of data. Joint to that, the use of kernel functions into their algorithms allows the adaptability to nonlinear problems of SVMs. There are many "traditional" problems in the wind power forecasting systems that affect the accuracy and robustness of the forecasts, as availability of real power measures, the existence of wrong data and the nonlinearity of the relationship between meteorological variables and power. So, these robustness and adaptability of SVMs suggest that these types of learning machines could be a good set of tools to solve many problems in the wind energy context.