A Short-term Wind Power Prediction Framework based on Two-layer Decomposition and the Combination of Ensemble Model and Deep Network

The time series of wind power is influenced by many external factors, showing strong volatility and randomness. Aiming at the problem low prediction accuracy series, this paper proposes a short-term framework based on two-layer decomposition combination ensemble model deep network, which composed complete empirical mode (CEEMD), sample entropy (SE), stacking ensemble, linear regression (LR), variational (VMD), long short term memory (LSTM) multi-layer perceptron (MLP). Firstly, CEEMD used to decompose into different modes then SE for reconstruction. Secondly, models are applied predict reconstruction components select optimal model. Subsequently, VMD partially decomposed combined LSTM established. Finally, in order further improve accuracy, MLP correct error corrected superimposed with results other obtain final predicted value. simulation show that effectiveness superior traditional improved effectively.