考虑CEEMDAN样本熵和SVR的短期风速预测

为降低由于风速信号的非线性和非平稳性带来的风速预测难度，提高短期风速预测的准确性，提出一种考虑样本熵的组合分解模式和支持向量回归（SVR）相结合的预测模型。首先采用自适应噪声的完全集合经验模态分解（CEEMDAN）方法分解风速历史数据，并计算各模态分量的样本熵；然后采用变分模态分解（VMD）方法对样本熵最大的模态分量进行二次分解，充分削弱风速分量的非平稳性；接着对分解得到所有模态分量分别建立SVR预测模型；最后将各分量的预测值求和完成最终风速预测。实例分析表明，所提模型对比其他模型的预测误差最小，预测精度最高，可有效预测短期风速。

Short-term Wind Speed Prediction with CEEMDAN Sample Entropy and SVR

In order to reduce the difficulty of prediction caused by the non-linearity and non-stationarity of wind speed signal and improve the accuracy of short-term wind speed prediction, a prediction model is proposed by combining the combinatorial decomposition model with the sample entropy and the support vector regression. First, CEEMDAN was used to decompose the historical wind speed data and calculate the sample entropy of each modal component. Next, the maximum modal component of sample entropy was decomposed by VMD to fully weaken the non-stationarity of wind speed component. Then, the support vector regression prediction model was established for all the modal components obtained by decomposition. Finally, the predicted values of each component were summed to obtain the prediction of the final wind speed. Compared with other models, the case results show that the proposed model has the lowest prediction error and the highest prediction accuracy, and can predict the short-term wind speed effectively.