Neuro-Fuzzy Versus Traditional Models for Forecasting Wind Energy Production

It is a well-known fact that the process of forecasting wind energy production is very popular with many researchers who are involved with RES (renewable energy sources). This chapter presents a wind energy production forecasting method, which was carried out with the use of an adaptive neural network with a fuzzy inference system (ANFIS). The model is tested with two different inputs: lagged values of the average speed of wind and the maximum speed of wind. The value of one-step-ahead energy production represents the output of the model. ANFIS uses a combination of the least-squares method and the backpropagation gradient descent method to estimate the optimal parameters of the model. The model is applied to a plant on the island of Evia, Greece. The results are compared with those of the autoregressive (AR) model and those of the autoregressive moving average (ARMA) model. The superiority of ANFIS is revealed.

[1]  K.-D. Mönnich.  Vorhersage der Leistungsabgabe netzeinspeisender Windkraftanlagen zur Unterstützung der Kraftwerkseinsatzplanung , 2001 .

[2]  Mehrdad Abedi,et al.  Short term wind speed forecasting for wind turbine applications using linear prediction method , 2008 .

[3]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[4]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[5]  D. K. Ranaweera,et al.  Application of radial basis function neural network model for short-term load forecasting , 1995 .

[6]  S. Watson,et al.  Short-term prediction of local wind conditions , 1994 .

[7]  Lars Landberg,et al.  Short-term prediction of local wind conditions , 1994 .

[8]  Soteris A. Kalogirou,et al.  Applications of artificial neural-networks for energy systems , 2000 .

[9]  W. Rivera,et al.  Short term wind speed forecasting in La Venta, Oaxaca, México, using artificial neural networks , 2009 .

[10]  Ahmet Duran Şahin,et al.  Progress and recent trends in wind energy , 2004 .

[11]  Les E. Atlas,et al.  Recurrent neural networks and robust time series prediction , 1994, IEEE Trans. Neural Networks.

[12]  Kazuyuki Aihara,et al.  Complex-valued forecasting of wind profile , 2006 .

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

[14]  Georges Kariniotakis,et al.  Improvements in wind speed forecasts for wind power prediction purposes using Kalman filtering. , 2005 .

[15]  J.-S.R. Jang,et al.  Predicting chaotic time series with fuzzy if-then rules , 1993, [Proceedings 1993] Second IEEE International Conference on Fuzzy Systems.

[16]  D.R. Hush,et al.  Progress in supervised neural networks , 1993, IEEE Signal Processing Magazine.