摘要
为了提高短期风电功率的精准预测,文章提出了一种基于VMD-ISMA-SVM组合模型的短期风电功率预测方法。首先采用变分模态分解(variational modal decomposition,VMD)对风电功率时间序列数据进行分解,获得了8个不同频率的风电功率模态分量;其次利用黏菌优化算法(improved slime mould algorithm,ISMA)对支持向量机(support vector machine,SVM)进行参数最优值搜索,构建ISMA-SVM模型;然后利用ISMA-SVM模型对各风电功率模态分量进行预测,得到各风电功率分量预测值;最后累加各分量预测值获得风电功率的预测值。文章为了验证该组合模型在风电功率预测方面的有效性和优越性,选取4种组合模式与之进行对比,算例结果表明,VMD-ISMA-SVM组合模型能显著地提升风电功率预测的精度和抑制数据的波动性。
In order to achieve accurate prediction of short-term wind power,this paper proposes a short-term wind power prediction method based on the combined model of VMD-ISMA-SVM.Firstly,variational modal decomposition(VMD)is used to decompose the wind power time series data,and eight wind power modal components with different frequencies are obtained.Secondly,the improved slime mould algorithm(ISMA)is used to search for the optimal parameters of support vector machine(SVM),and an ISMA-SVM model is constructed.Then,the ISMA-SVM model is used to predict each wind power modal component,and the predicted values of each wind power component are obtained.Finally,the predicted values of each component are added up to get the predicted value of wind power.In order to verify the effectiveness and superiority of the combined model in wind power prediction,the paper selects four combination modes for comparison.The results show that the VMD-ISMA-SVM combined model can significantly improve the accuracy of wind power prediction and suppress the volatility of the data.
作者
万亮
胡俊
李小龙
张喻
刘炬
WAN Liang;HU Jun;LI Xiaolong;ZHANG Yu;LIU Ju(State Grid Hubei Electric Power Co.,Ltd.Zhongxiang Power Supply Company,Jingmen 431900,China;State Grid Hubei Electric Power Co.,Ltd.Jingmen Power Supply Company,Jingmen 448000,China)
出处
《安徽电气工程职业技术学院学报》
2025年第1期69-77,共9页
Journal of Anhui Electrical Engineering Professional Technique College
关键词
风电功率预测
组合模型
支持向量机
改进黏菌算法
变分模态分解
wind power prediction
combined model
support vector machine
improved slime mould algorithm
variational modal decomposition
