Short term wind power forecasting using hybrid variational mode decomposition and multi-kernel regularized pseudo inverse neural network

In this paper a new hybrid method combining variational mode decomposition (VMD) and single or Multi-kernel regularized pseudo inverse neural network (MKRPINN) is presented for effective and efficient wind power forecasting. The original non-linear and non-stationary time series data is decomposed using VMD approach to prevent the mutual effects among the different modes. The proposed VMD-KRPINN (VMD based kernel regularized pseudo inverse neural network) and VMD-MKRPINN methods are then used to predict wind power generation of a wind farm in the state of Wyoming, USA for different time intervals of 10 min, 30 min, 1 h and 3 h ahead. Comparison with empirical mode decomposition (EMD) based kernel regularized pseudo inverse neural networks is also presented in the paper to validate the superiority of the VMD based wind power prediction models. Also to improve the performance of the proposed EMD-MKPRINN and VMD-MKRPINN models, their parameters are optimized using vaporization and precipitation based water cycle algorithm (VAPWCA). Further a fast reduced version of the VMD-KRPINN is presented in the paper to reduce the execution time substantially using randomly selected support vectors from the data set while resulting in a reasonably accurate forecast. (C) 2017 Elsevier Ltd. All rights reserved.