A Fuzzy Group Forecasting Model Based on BPNN for Wind Power Output

Many forecasting models have been developed for forecasting wind farm electricity output. In most situations, performance of models is problem-dependent. Thus, it is difficult for forecasters to choose the right technique for each unique situation. In order to overcome this problem, this paper integrates multiple models into an aggregated model to obtain further performance improvement. Firstly, three groups of BPNN forecasting models are designed, i.e. univariate BPNN models, the hybrid model of ARIMA and BPNN and the multivariate model. Each group of the models can be regarded as an expert in forecasting, and then the fuzzy theory is used to combine all these forecasting results into the final answer. Results show that this group forecasting model performs well in terms of accuracy and consistency.

[1]  Desheng Dash Wu,et al.  Power load forecasting using support vector machine and ant colony optimization , 2010, Expert Syst. Appl..

[2]  Aoife Foley,et al.  Current methods and advances in forecasting of wind power generation , 2012 .

[3]  C. P. Unsworth,et al.  Excessive Noise Injection Training of Neural Networks for Markerless Tracking in Obscured and Segmented Environments , 2006, Neural Computation.

[4]  Lambros Ekonomou,et al.  Electricity demand load forecasting of the Hellenic power system using an ARMA model , 2010 .

[5]  Merrill Jones Barradale.  Impact of public policy uncertainty on renewable energy investment: Wind power and the production tax credit , 2010 .

[6]  Jack Brouwer,et al.  Spatial and temporal analysis of electric wind generation intermittency and dynamics , 2011 .

[7]  Carlos de Castro,et al.  Global wind power potential: Physical and technological limits , 2011 .

[8]  Ehab F. El-Saadany,et al.  Improved Grey predictor rolling models for wind power prediction , 2007 .

[9]  Kin Keung Lai,et al.  A Novel Support Vector Machine Metamodel for Business Risk Identification , 2006, PRICAI.

[10]  G. Bortolan,et al.  A review of some methods for ranking fuzzy subsets , 1985 .

[11]  Sheng-wei Fei,et al.  Fault diagnosis of power transformer based on support vector machine with genetic algorithm , 2009, Expert Syst. Appl..

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

[13]  E.F. El-Saadany,et al.  Annual Wind Speed Estimation Utilizing Constrained Grey Predictor , 2009, IEEE Transactions on Energy Conversion.

[14]  Dissertação De Mestrado Apresentada,et al.  WIND POWER FORECASTING UNCERTAINTY AND UNIT COMMITMENT , 2014 .

[15]  S. Mandal.  Comments on ‘Temporal significant wave height estimation from wind speed by perceptron Kalman filtering’ by A. Altunkaynak and M. Ozger, Ocean Engineering, Vol. 31(10); 2004,1245-1255 , 2007 .

[16]  R. Kavasseri,et al.  Day-ahead wind speed forecasting using f-ARIMA models , 2009 .

[17]  Eugene Fernandez,et al.  Analysis of wind power generation and prediction using ANN: A case study , 2008 .

[18]  Ping-Feng Pai,et al.  A hybrid ARIMA and support vector machines model in stock price forecasting , 2005 .

[19]  Leighton Cochran,et al.  A physical modeler's view of Computational Wind Engineering , 2011 .