基于小波-神经网络的风电功率短期预测

根据风速、风电功率变化特点,有效地预测风电功率,可降低电网调度的难度,利用小波多分辨分析法将风速序列信号分解到不同尺度上以反映不同变化频率的风速信号,分解后的风速信号经多层前向神经网络BP（Back Propagation）预测出其对应的风电功率,通过将基于小波-神经网络模型的预测结果与基于BP神经网络模型的预测结果进行比较研究,发现基于小波-神经网络的预测精度更高,效果更好,且预测精度与预测时间长短有关。

Short-term Wind Power Prediction Based on Wavelet-Neural Network

The wind power can be effectively predicted according to the changes of wind speed and wind power,which can reduce the difficulty in grid dispatching.Wind speed sequence signals were decomposed into different scales by wavelet multi-resolution analysis method to reflect wind speed signals with different change frequency.The corresponding wind power is predicted by decomposed wind speed signals through BP Neural network.Comparing the prediction results based on wavelet-neural network model with the prediction results based on BP Neural network model,it is found that the prediction precision of the former was higher,the effect was better,and the prediction accuracy was related to the length of prediction time.