基于组合预测方法的风电场短期风速预测  

SHORT TERM WIND SPEED FORECAST BASED ON COMBINED PREDICTION

作　　者：彭怀午[1] 刘方锐[2] 杨晓峰[1] 

机构地区：[1]内蒙古电力勘测设计院,呼和浩特010020 [2]华中科技大学电气与电子工程学院,武汉430074

出　　处：《太阳能学报》2011年第4期543-547,共5页Acta Energiae Solaris Sinica

基　　金：国家自然科学基金重点项目(50837003);国家重点基础研究发展计划(2009CB219701)

摘　　要：基于持续法、人工神经网络法(ANN)和支持向量机(SVM)3种不同预测模型对内蒙古某风电场短期风速进行了预测研究,比较了不同单一预测模型的预测精度,并进行了4种不同预测模型的组合预测。计算结果表明,单一预测模型中支持向量机方法精度最高,而组合预测中3种方法组合的预测精度最高,并且组合预测精度均高于单一预测方法的精度。同时发现,当单一模型预测误差之间存在较强的负相关关系时,组合预测精度提高明显;而当单一模型预测误差之间存在较强的正相关关系时,则组合预测精度改进有限。Three different prediction models were investigated for short term wind speed prediction of a wind farm in this paper. The adopted prediction models are persistence method, artificial neural network （ANN） and support vector machine（SVM）, respectively. The performance of three prediction models were compared. Four kinds of combined predictions of three model were evaluated as well. The calculated results show that the SVM method performs best among the individual prediction model and the combination of three forecasting methods exhibit the highest precision among the combined prediction strategies. Moreover, the forecasting accuracy of combined model is better than that of any individual prediction method. Meanwhile, it is found that the accuracy of combined prediction is improved apparently if the prediction errors between single methods have strong negative correlations; while the accuracy of combined prediction is improved limitedly if the prediction errors between single methods have strong positive correlations.

关 键 词：短期风速预测 持续法 人工神经网络 支持向量机 组合预测 

分 类 号：TK81[动力工程及工程热物理—流体机械及工程]