基于相似数据的支持向量机短期风速预测仿真研究

风电场功率预报是减小大规模风电并网对电网造成不良影响的有效手段,提高短期风速预测的精度是保障风电场功率预报的重要基础。提出了基于相似数据并结合小波分析的支持向量机短期风速预测方法。该方法从大量的数据样本中提取相似数据创建训练样本,采用小波分解技术将风速信号分解成低频趋势信号和高频随机信号,分别采用支持向量机理论建模,合成得到风速预测数据。仿真结果表明,相似数据有效地提高了数据的相关度,小波分解使支持向量机模型更好地拟合风速信号的低频和高频特性,提高了预测精度。通过与某风电场的实际风速数据验证,表明模型具有较强的泛化能力,程序运行时间可满足工程需要。

Short-term Wind Speed Forecasting Based on Support Vector Machine With Similar Data

Wind power prediction is an effective way to decrease the effects for the large-scale wind power connecting to grid.Improving accuracy of short-term wind prediction is key of wind power prediction.In this paper,a support vector machine(SVM) method was proposed based on wavelet analysis and similar data.Similar data were extracted from large amounts of data to create the training samples.The original wind speed data was decomposed into trend signal of low frequency band and random signal of high frequency band by wavelet decomposition.Different SVM speed forecasting models were trained respectively and combined to obtain forecasting results.The simulation experiments show that similar data effectively improve the relevance of data.SVM models better approximate the wind speed characteristics of low and high frequency band by wavelet decomposition and prediction accuracy is improved.By validation with the measured wind speed data of a wind farm,the model has generalization capability and good run time for meeting requirement of engineering application.