Ensemble Empirical Mode Decomposition and GA-BP Neural Network

Abstract-Wind energy is one of the most important renewable energy resources. Wind speed forecasting is a critical tool for wind energy conversion system implementation. However, the uncertainty and intermittency of wind speed always affect the prediction accuracy. This paper proposes a novel wind speed forecasting method based on ensemble empirical mode decomposition (EEMD) and GA-BP neural network. The wind speed data are decomposed into certain signals with different frequencies by EEMD. Each signal is taken as input data to establish GA-BP neural network forecasting model. Final forecasted wind speed data are then obtained by adding up the predicted data of each signal. A case study of a wind farm in Inner Mongolia, China shows that this method is more accurate than traditional GA-BP forecasting approach. The study also shows that method with EEMD is more accurate than that with empirical mode decomposition (EMD). Index Terms- EMD, EEMD, Genetic Algorithm, GA-BP Neural Network, Wind Speed Forecasting

[1]  N. Huang,et al.  A study of the characteristics of white noise using the empirical mode decomposition method , 2004, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[2]  Jing Shi,et al.  On comparing three artificial neural networks for wind speed forecasting , 2010 .

[3]  George Stavrakakis,et al.  Wind power forecasting using advanced neural networks models , 1996 .

[4]  Lawrence Davis,et al.  Training Feedforward Neural Networks Using Genetic Algorithms , 1989, IJCAI.

[5]  Jing-Shan Hong,et al.  Evaluation of the High-Resolution Model Forecasts over the Taiwan Area during GIMEX , 2003 .

[6]  Norden E. Huang,et al.  Ensemble Empirical Mode Decomposition: a Noise-Assisted Data Analysis Method , 2009, Adv. Data Sci. Adapt. Anal..

[7]  Mohammad Monfared,et al.  A new strategy for wind speed forecasting using artificial intelligent methods , 2009 .

[8]  T. Wang,et al.  Comparing the applications of EMD and EEMD on time-frequency analysis of seismic signal , 2012 .

[9]  Lars Landberg,et al.  A mathematical look at a physical power prediction model , 1998 .

[10]  Gedong Jiang,et al.  Feed-axis gearbox condition monitoring using built-in position sensors and EEMD method , 2011 .

[11]  Yaguo Lei,et al.  Application of the EEMD method to rotor fault diagnosis of rotating machinery , 2009 .

[12]  E. El-Saadany,et al.  Grey predictor for wind energy conversion systems output power prediction , 2006, IEEE Transactions on Power Systems.

[13]  M. J. Lin,et al.  Application of the VLF-EM method with EEMD to the study of a mud volcano in southern Taiwan , 2010 .

[14]  Gabriel Rilling,et al.  Empirical mode decomposition as a filter bank , 2004, IEEE Signal Processing Letters.

[15]  M. C. Deo,et al.  Forecasting wind with neural networks , 2003 .

[16]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.