The Study of Wind Power Predict Model Based on Wavelet Transform and Elman Neural Network

In order to reduce adverse effects of wind power, this thesis studies the wind prediction model, which is the basis for predicting the end of load model. We use the wavelet transform analysis method to decompose the data into five layers, reduce the input, determine the principal components of the wind power process and simplify the structure of Elman neural network for the wind farm which is not stability and has the characteristics of many uncertain factors. According to a wind farm factory which provide 720 groups of sampling data, this paper establish the wind power model. The sampling interval is one hour and we sample a total of one month. Firstly, we use the DB8 wavelet transform to decompose the sampled data and then use the Elman neural network to predict the power of the wind farm. Finally, it is effectively to verify the method after using MATLAB simulation and also the method can significantly improve the prediction accuracy and help to improve the utilization rate of wind power through the comparison.