A novel hybrid methodology for short-term wind power forecasting based on adaptive neuro-fuzzy inference system

With the increased penetration of wind power into the electric grid of China, many challenges emerge due to its fluctuation and intermittence. In this context, it is crucial to achieve higher accuracy of the short-term wind power forecasting for safe and economical operation of the power system. Hence, this paper proposes a novel hybrid methodology for short-term wind power forecasting, successfully combining three individual forecasting models using the adaptive neuro-fuzzy inference system (ANFIS). The backpropagation neural network (BPNN), radial basis function neural network (RBFNN), and least squares support vector machine (LSSVM) are selected as the individual forecasting models. A new data preprocessing method based on Pearson correlation coefficient (PCC) is also applied for selecting proper inputs for three individual models. Results obtained show the advancement of the PCC based data preprocessing method. Also, the comparison studies demonstrate that the proposed hybrid methodology presents a significant improvement in accuracy with respect to three individual models.