基于最小二乘支持向量机的风速预测模型

风速具有较大的随机性,预测的准确度不高。针对这种现象,基于最小二乘支持向量机(least squares support vector machine,LS-SVM)理论,结合某风电场实测风速数据,建立了最小二乘支持向量机风速预测模型。对该风电场的风速进行了提前1h的预测,其预测的平均绝对百分比误差仅为8.55%,预测效果比较理想。同时将文中的风速预测模型与神经网络理论、支持向量机(support vector machine,SVM)理论建立的风速预测模型进行了比较。仿真结果表明,文中所提模型在预测精度和运算速度上皆优于其他模型。

A Wind Speed Forecasting Model Based on Least Squares Support Vector Machine

Due to its strong randomness,it is very difficult to predict wind speed accurately. To solve this problem,using least squares support vector machine (LS-SVM) and based on actual wind speed data measured in a certain wind farm,a wind speed predicting model based on LS-SVM is built; the one hour-ahead wind speed of this wind farm is predicted by the proposed model,and a satisfied prediction result that the mean average percentage error of the predicted wind speed is only 8.55% is obtained. The proposed wind s...