Ensemble Empirical Mode Decomposition Based Deep Learning Model for Short-Term Wind Power Forecasting

Abstract. In the last few years, wind power forecasting has established itself as an essential tool in energy industry due to increase of penetration electric grid. This paper presents a method based on ensemble empirical mode decomposition (EEMD) and deep learning. EEMD is employed decompose time series data into several intrinsic functions residual component. Afterwards, every function trained by means CNN-LSTM architecture. Finally, forecast obtained adding prediction Compared benchmark model, proposed approach provides more accurate predictions for horizons. Furthermore, intervals are modelled using quantile regression.