中文说明：
针对风电场短期风速的预测提出一种基于小波变换的组合预测方法。首先利用Mallat 算法对短期风速时间序列进行db3 小波三层分解与重构，得到短期风速时间序列的近似分量和细节分量。针对近似分量和细节分量的不同特性，对近似分量利用粒子群算法优化的最小二乘支持向量机进行预测，对细节分量利用自回归求和滑动平均模型进行预测。最后各预测模型预测值组合叠加得到最终的短期风速预测值。仿真结果表明该方法具有较高的预测准确度。
English Description：
Aiming at the short-term wind speed prediction of wind farm, a combined forecasting method based on wavelet transform is proposed. Firstly, Mallat algorithm is used to decompose and reconstruct the short-term wind speed time series with db3 wavelet, and the approximate and detailed components of the short-term wind speed time series are obtained. According to the different characteristics of the approximate component and the detail component, the approximate component is predicted by the least squares support vector machine optimized by particle swarm optimization, and the detail component is predicted by the autoregressive summation moving average model. Finally, the final short-term wind speed prediction value is obtained by combining the predicted values of each prediction model. Simulation results show that the method has high prediction accuracy