As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
As an important renewable energy, wind power is paid great attention by all countries. It is of great significance to predict wind speed accurately for the power system which includes large amounts of wind power. The wind speed time series appears typical non-stationary, as a result, the outcome obtained from applying single prediction method directly will be unsatisfied. In order to improve the accuracy of wind speed prediction, a model based on empirical mode decomposition (EMD) and support vector machines (SVM) is proposed in the paper. The wind speed time series is made by EMD at first, then appropriate support vector machine model is established with different frequency bands, finally the output value of each model is summed equal right to get the final prediction result. The radial kernel is selected by the SVM, the parameters that necessary are obtained through cross-validation. The actual cases are employed to demonstrate the validity of the proposed approach. The results are compared with those obtained by the single SVM model, which shows that the given model can effectively improve the accuracy of wind speed forecasting.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.