A hybrid wind power prediction method

As a type of clean and renewable energy source, wind power is being widely used all around the world. However, owing to the uncertainty and instability of the wind power, it is important to build an accurate prediction model for wind power for the grid-connected security operation. The performance of hybrid method is always better than that of single ones in the wind power prediction. Actual wind power can be decomposed into hourly level and turbulence level. Key factors in the wind power hourly level data can be found by Gray Correlation Analysis. The hidden rules of wind power turbulence level is extracted by historical data from wind farm based on deep belief network (DBN). Several experiments are conducted to compare different solutions. The experimental results show that prediction errors are significantly reduced using the proposed technique.

[1]  Wei-Chiang Hong,et al.  Chaotic particle swarm optimization algorithm in a support vector regression electric load forecasting model , 2009 .

[2]  Tijmen Tieleman,et al.  Training restricted Boltzmann machines using approximations to the likelihood gradient , 2008, ICML '08.

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

[4]  Hui Liu,et al.  Comparison of two new ARIMA-ANN and ARIMA-Kalman hybrid methods for wind speed prediction , 2012 .

[5]  Ergin Erdem,et al.  ARMA based approaches for forecasting the tuple of wind speed and direction , 2011 .

[6]  Haiyan Lu,et al.  Multi-step forecasting for wind speed using a modified EMD-based artificial neural network model , 2012 .

[7]  S. Shankar Sastry,et al.  Generalized principal component analysis (GPCA) , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Chao Chen,et al.  A hybrid model for wind speed prediction using empirical mode decomposition and artificial neural networks , 2012 .

[9]  A. Gastli,et al.  Review of the use of Numerical Weather Prediction (NWP) Models for wind energy assessment , 2010 .

[10]  Henrik Madsen,et al.  A review on the young history of the wind power short-term prediction , 2008 .

[11]  I. V. D. Hoven.  POWER SPECTRUM OF HORIZONTAL WIND SPEED IN THE FREQUENCY RANGE FROM 0.0007 TO 900 CYCLES PER HOUR , 1957 .

[12]  Geoffrey E. Hinton,et al.  Deep Boltzmann Machines , 2009, AISTATS.

[13]  Joao P. S. Catalao,et al.  A hybrid PSO–ANFIS approach for short-term wind power prediction in Portugal , 2011 .

[14]  Jing Shi,et al.  Bayesian adaptive combination of short-term wind speed forecasts from neural network models , 2011 .

[15]  Bart Thomee,et al.  New trends and ideas in visual concept detection: the MIR flickr retrieval evaluation initiative , 2010, MIR '10.

[16]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[17]  J.B. Theocharis,et al.  A fuzzy model for wind speed prediction and power generation in wind parks using spatial correlation , 2004, IEEE Transactions on Energy Conversion.