基于小波实时分解模式的风功率协同预测研究

COOPERATIVE PREDICTION BASED ON WAVELET REAL-TIME DECOMPOSITION FOR WIND POWER

利用小波理论建立风电功率多步预测模型,针对预测模型中预测值随预测步数恶化的问题,引入小波实时分解模式,对不同频段分量的特性采用不同方法分别预测,最终将结果叠加得到多步预测值,结合国家能源局对于风电场风电功率实时预测的指标,通过吉林省某风电场的实测风电功率数据验证该方法的有效性。

Using wavelet theory to establish model for wind power multi-step prediction, aimed at the predictive value deteriorate with the increasing of prediction steps in the model, the real-time wavelet decomposition theory to predict different frequency component using different predictive methods was introduced, then the superimposed multi-step predictive value was got. According to the index of wind power real-time prediction of wind farm published by the National Energy Administration, the wind power data measured from wind farm of Jilin province were used to verify the validity of the method.