电子测量与仪器学报

王永超,唐求,马俊,邱伟,杨莹莹.基于复合核 SVM 的智能电表基本误差预测方法[J].电子测量与仪器学报,2021,35(10):209-216

基于复合核 SVM 的智能电表基本误差预测方法

Prediction method of basic error of smart meter based on composite core SVM

DOI：

英文关键词:smart meter composite core support vector machine fuzzy C-means clustering basic error prediction

基金项目:国家电网公司总部科技项目(5230HQ19000F)、湖南省研究生科研创新项目（CX20200426）资助

作者	单位
王永超	1. 国网新疆电力有限公司营销服务中心
唐求	2. 湖南大学电气与信息工程学院
马俊	2. 湖南大学电气与信息工程学院
邱伟	2. 湖南大学电气与信息工程学院
杨莹莹	2. 湖南大学电气与信息工程学院

Author	Institution
Wang Yongchao	1. State Grid Xinjiang Electric Power Co. , Ltd. Marketing Service Center
Tang Qiu	2. College of Electrical and Information Engineering, Hunan University
Ma Jun	2. College of Electrical and Information Engineering, Hunan University
Qiu Wei	2. College of Electrical and Information Engineering, Hunan University
Yang Yingying	2. College of Electrical and Information Engineering, Hunan University

摘要点击次数: 804

全文下载次数: 1030

中文摘要:

智能电表作为电网的终端设备,其退化情况与工作环境、运行时间等因素密切相关。针对复杂变量条件下智能电表退化情况难以预测的问题,提出一种基于复合核支持向量机(support vector machine, SVM)的智能电表基本误差预测方法。首先对智能电表退化数据进行分析,采用皮尔逊相关性分析找出与智能电表基本误差相关性极强的环境变量。然后,为进一步提取数据退化特征,采用模糊 C 均值聚类算法对智能电表退化数据进行聚类,确定退化特征向量。最后,基于高斯径向基核函数与多项式核函数构造一种新的复合核 SVM 模型用以预测智能电表基本误差。结合新疆地区智能电表退化数据对复合核 SVM 模型性能进行验证,实验结果表明,复合核 SVM 模型可以准确预测复杂环境下智能电表的基本误差,其预测准确率高于贝叶斯方法、神经网络方法以及经典 SVM 方法。

英文摘要:

As the terminal equipment of the power grid, the degradation of smart meters is closely related to factors such as working environment and running time. Aiming at the problem that the degradation of smart meters under complex variable conditions is difficult to predict, a smart meter basic error prediction method based on the composite core support vector machine (SVM) is proposed. First, analyze the degradation data of smart meters, and use Pearson correlation analysis to find environmental variables that are highly correlated with the basic errors of smart meters. Then, in order to further extract the data degradation features, the fuzzy C-means clustering algorithm is used to cluster the smart meter degradation data and determine the degradation feature vector. Finally, based on the Gaussian radial basis kernel function and polynomial kernel function, a new composite kernel SVM model is constructed to predict the basic error of smart meters. The performance of the composite core SVM model is verified by combining the degradation data of smart meters in Xinjiang. The experimental results show that the composite core SVM model proposed in this paper can accurately predict the basic errors of smart meters in complex environments, and its prediction accuracy is higher than that of Bayesian methods. Neural network method and classic SVM method.

查看全文查看/发表评论下载PDF阅读器