摘要
深度挖掘与分析电力计量大数据,提取有价值的信息,对于电网正常运行具有重要意义。而当前方法在数据挖掘过程中容易受到噪音影响,导致挖掘准确率较低,因此提出了基于特征标签的电力计量大数据深度挖掘方法。利用模糊C-均值聚类算法生成特征标签,通过特征标签对电力计量大数据进行改善,结合云计算平台搭建基于特征标签的电力计量大数据挖掘架构,通过编辑预处理后的数据与建模完成对于电力计量大数据的深度挖掘。实验结果表明,基于特征标签的电力计量大数据深度挖掘方法在挖掘过程中的稳定性极好,挖掘准确率能够达到99%,实际应用效果好。
It is of great significance for the normal operation of power grid to deeply mine and analyze the big data of power metering and extract valuable information.However,the current methods are easily affected by noise in the process of data mining,resulting in low mining accuracy.Therefore,a deep mining method of power metering big data based on feature tag is proposed.The fuzzy C⁃means clustering alg⁃orithm is used to generate feature labels.The power metering big data is improved through the feature tag.Combined with the cloud computing platform,the power metering big data mining architecture based on the feature tag is built.The deep mining of power metering big data is completed by editing the preprocessed data and modeling.The experimental results show that the power metering big data deep mining method based on feature tag has excellent stability in the mining process,the mining accuracy can reach 99%,and the practical application effect is good.
作者
王奕萱
李翼铭
徐二强
李会君
李明亮
WANG Yixuan;LI Yiming;XU Erqiang;LI Huijun;LI Mingliang(State Grid Henan Marketing Service Center(Metrology Center),Zhengzhou 450052,China;State Grid Henan Electric Power Company,Zhengzhou 450052,China;Henan Jiuyu Tenglong Information Engineering Co.,Ltd.,Zhengzhou 450052,China)
出处
《电子设计工程》
2023年第24期186-189,195,共5页
Electronic Design Engineering
