基于云计算的电力运行大数据异常值快速检测算法  

Fast detection algorithm of big data outliers in power operation based on cloud computing

作　　者：石莹 罗峥[1] 胡佳[1] 魏添 SHI Ying;LUO Zheng;HU Jia;WEI Tian(State Grid Wuhan Power Supply Company,Wuhan 430077,China;State Grid Wuhan Caidian District Power Supply Company,Wuhan 430000,China)

机构地区：[1]国网武汉供电公司,湖北武汉430077 [2]国网武汉市蔡甸区供电公司,湖北武汉430000

出　　处：《电子设计工程》2020年第18期43-46,51,共5页Electronic Design Engineering

基　　金：国家自然科学基金项目(51402096)。

摘　　要：针对传统电力大数据异常值检测算法存在的检测精度低、检测效率差的问题,提出一种新的基于云计算的电力运行大数据异常值快速检测算法。该算法首先构建云计算基本架构,利用数据仓库获取电力运行大数据。对获得的电力运行大数据进行降维、清洗、标准化处理。利用模糊c-均值聚类算法分类识别处理后的电力运行大数据,快速检测其中的异常值。最后为验证检测算法有效性,进行仿真对比实验。实验结果表明:与传统电力运行大数据异常值检测算法相比,利用所提算法进行电力运行大数据异常值检测,在保证检测准确性的同时,也提高了检测效率,达到了本次研究的预期目标。Aiming at the problems of low detection accuracy and low detection efficiency existing in the traditional big data outliers detection algorithm,a new fast detection algorithm of big data outliers in power operation based on cloud computing is proposed.The algorithm first constructs the basic architecture of cloud computing,and uses data warehouse to obtain big data of power operation.To reduce the dimension,clean and standardize the power operation big data.The fuzzy c-means clustering algorithm is used to classify and identify the processed power operation big data,and detect the abnormal value quickly.Finally,in order to verify the effectiveness of the detection algorithm,simulation experiments are carried out.The experimental results show that compared with the traditional detection algorithm of big data outliers in power operation,the proposed algorithm can not only ensure the detection accuracy,but also improve the detection efficiency and achieve the expected goal of this study.

关 键 词：云计算 电力运行大数据 异常值 检测算法 

分 类 号：TN245.55[电子电信—物理电子学]