Meta Learning-Based Hybrid Ensemble Approach for Short-Term Wind Speed Forecasting

Under raising pressure of global energy and environmental issues in recent years, wind power has been considered as one of the most promising energy sources owing to with its advantages of being renewable and pollution-free. The accurate and efficient wind speed forecasting (WSF) plays a key role in the generation, distribution, and management of wind power. This study proposes a meta learning based novel hybrid ensemble approach and model for short-term WSF. The ensemble prediction model consists of meta learning part and individual predictor part. The meta learning part is based on a multi-input and multi-output back propagation (BP) neural network (NN) with multiple hidden layers, whereas the individual predictor part is composed of three pre-trained individual predictors based on BP NN, long short-term memory (LSTM) recurrent neural network (RNN), and gated recurrent units (GRU) RNN, respectively. The wind speed value to be predicted can be obtained by weighted summation of two parts of the ensemble prediction model based on historical wind speed data. The innovation in the proposed ensemble WSF model is to build a BP NN and use environmental feature data as input data to generate weight coefficients for updating the individual predictor. In order to illustrate the forecasting performance of the proposed ensemble prediction approach for short-term WSF, the prediction results of the proposed ensemble prediction model are compared with those of several single prediction models and an average coefficient hybrid prediction model under the same conditions. The results illustrate that the meta learning based ensemble prediction model proposed in this study has better forecasting performance in both of prediction accuracy, prediction stability, and data correlation than other WSF models.