电力大数据平台建设及实时线损异常检测应用  

Construction of Power Big Data Platform and the Application of the Outlier Detection of Real Time Line Loss

作　　者：杨漾[1,2] 张诗军[1] 陈丰[1] 李远宁[1] 张世良[1] 

机构地区：[1]中国南方电网有限责任公司信息部,广州510600 [2]广东电网有限责任公司信息中心,广州510000

出　　处：《现代计算机》2016年第24期8-14,共7页Modern Computer

基　　金：广东省科技厅重大专项(No.20148010117007)

摘　　要：以某区域电网公司为例,结合电网行业的数据特征以及现有的大数据技术,完成电力大数据平台的设计及建设。同时,以电力大数据平台的流数据处理架构为基础,整合计量自动化数据、GIS数据、营配数据等,开展实时线损异常检测分析场景建设,验证平台的流数据分析能力,为后续电力行业开展其他大数据应用场景的建设奠定基础。Takes a regional power grid carp as an example, combines with the data characteristics of power grid industry and the existing big data technology, completes the design and construction of big data platform. At the same time, based on the big data platform＇ s streaming data processing architecture, it integrates measurement automation data, GIS data and business data, etc., to carry out the construction of the outlier detection and analysis of real time line loss, which proves the streaming data analytics capacity of the platform. Lays the founda- tion for the subsequent power industry to carry out the construction of other big data application scenarios. Lays the foundation to carry out the construction of other big data application in the future.

关 键 词：电力大数据平台 实时线损 异常检测 神经网络 聚类 

分 类 号：TM76[电气工程—电力系统及自动化] TP311.13[自动化与计算机技术—计算机软件与理论]