With the integration of wind energy into electricity grids, it is becoming increasingly important to obtain accurate wind speed forecasts, and accurate wind speed forecasts are necessary to schedule power system. In this study, an artificial neural networks (NNs) model with a variational mode decomposition (VMD) for a short-term wind speed forecasting was presented. To reduce the non-stationary of wind speed time series, the historical wind speed was decomposed into different intrinsic mode functions (IMFs) by a VMD. The back-propagation NN with Levenberg-Marquardt was adopted to build sub-models according to the different characteristic of each IMF. The sub-models corresponding to different IMFs were superposed to obtain wind speedforecasting models. In the experiment, the proposed forecasting model was compared with an NN with wavelet decomposition and empirical mode decomposition. The performance was evaluated based on three metrics, namely maximum absolute error, root mean square error and the correlation coefficient. The comparison results indicate that significant improvements in forecasting accuracy were obtained with the proposed forecasting models compared with other forecasting methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.