Short-term wind power prediction based on combined grey-Markov model

The rapid growth of wind generation is introducing additional variability and uncertainty into power system operations and planning. Wind power forecasting will improve the wind power integration in both economic and technical aspects. In the paper, a combined approach based on grey model and Markov model was proposed to predict wind power in a short term. Firstly a Grey model was created to forecast the wind speed. Secondly the residual error which was obtained by subtracting the predicted values from actual values of wind speeds can be divided into several different states by using Markov model. The residual values were further forecasted through calculating the probability distribution of each state. The residual errors can be used to correct the predicted values to improve the accuracy of wind speeds. Finally short term wind power forecasting was made based on wind speed data through a fitted wind power curve. Case study was carried out to investigate the validity of the combined grey-Markov model. Results showed that the proposed combined model can improve the short term forecasting accuracy of wind power effectively.

[1]  Ming Meng,et al.  Forecasting electricity demand using Grey-Markov model , 2008, 2008 International Conference on Machine Learning and Cybernetics.

[2]  V. Miranda,et al.  Entropy and Correntropy Against Minimum Square Error in Offline and Online Three-Day Ahead Wind Power Forecasting , 2009, IEEE Transactions on Power Systems.

[3]  H. M. I. Pousinho,et al.  An Artificial Neural Network Approach for Short-Term Wind Power Forecasting in Portugal , 2009, 2009 15th International Conference on Intelligent System Applications to Power Systems.

[4]  Cuifeng Li,et al.  Study on Theory of the Grey Markov Chain Method and Its Application , 2006, The Proceedings of the Multiconference on "Computational Engineering in Systems Applications".

[5]  Deng Julong,et al.  Application of grey system theory in China , 1990, [1990] Proceedings. First International Symposium on Uncertainty Modeling and Analysis.

[6]  Sifeng Liu.  Proceedings of 2007 IEEE International Conference on Grey Systems and Intelligent Services , 2007 .

[7]  Georges Kariniotakis,et al.  Wind power forecasting using fuzzy neural networks enhanced with on-line prediction risk assessment , 2003, 2003 IEEE Bologna Power Tech Conference Proceedings,.

[8]  Jean-François Muzy,et al.  Short‐term forecasting of surface layer wind speed using a continuous random cascade model , 2011 .

[9]  Deng Ju-Long,et al.  Control problems of grey systems , 1982 .

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

[11]  Hanif Livani,et al.  Hour-ahead wind power prediction for power systems using Hidden Markov Models and Viterbi Algorithm , 2010, IEEE PES General Meeting.

[12]  P. S. Dokopoulos,et al.  Wind speed and power forecasting based on spatial correlation models , 1999 .

[13]  Ruiqing Wang,et al.  A hybrid forecasting method for day-ahead electricity price based on GM(1,1) and ARMA , 2009, 2009 IEEE International Conference on Grey Systems and Intelligent Services (GSIS 2009).

[14]  Henrik Madsen,et al.  The Zephyr project - The next generation prediction system (poster) , 2001 .

[15]  Wei-Jen Lee,et al.  Forecasting the Wind Generation Using a Two-Stage Network Based on Meteorological Information , 2009, IEEE Transactions on Energy Conversion.

[16]  N.D. Hatziargyriou,et al.  An Advanced Statistical Method for Wind Power Forecasting , 2007, IEEE Transactions on Power Systems.

[17]  J.B. Theocharis,et al.  Long-term wind speed and power forecasting using local recurrent neural network models , 2006, IEEE Transactions on Energy Conversion.

[18]  Gregor Giebel,et al.  The State-Of-The-Art in Short-Term Prediction of Wind Power. A Literature Overview , 2003 .

[19]  J. Usaola,et al.  Next generation forecasting tools for the optimal management of wind generation , 2006, 2006 International Conference on Probabilistic Methods Applied to Power Systems.

[20]  G.N. Kariniotakis,et al.  Probabilistic Short-term Wind Power Forecasting for the Optimal Management of Wind Generation , 2007, 2007 IEEE Lausanne Power Tech.

[21]  Pravin B. Dangar,et al.  Offshore wind speed forecasting by SVM and power integration through HVDC light , 2010, 2010 Conference Proceedings IPEC.