论文部分内容阅读
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。
The wind speed has a large randomness and the prediction accuracy is not high. In view of this phenomenon, based on least squares support vector machine (LS-SVM) theory, combined with the measured wind speed data of a wind farm, the least squares support vector machine wind speed prediction model is established. The wind speed of the wind farm was predicted 1h ahead of schedule. The average absolute percentage error of prediction was only 8.55%. The forecasting result was satisfactory. At the same time, the wind speed prediction model in this paper is compared with the neural network theory and the wind speed prediction model established by the support vector machine (SVM) theory. Simulation results show that the proposed model is superior to other models in prediction accuracy and speed.