基于偏序约简的智能电网大数据预处理方法  

A Partial Order Reduction Based Method for Big Data Preprocessing in Smart Grid Environment

作　　者：李刚[1,2] 焦谱 文福拴[2,3] 宋雨[1] 尚金成[4] 何洋[4] 

机构地区：[1]华北电力大学控制与计算机工程学院,河北省保定市071003 [2]浙江大学电气工程学院,浙江省杭州市310027 [3]文莱科技大学电机与电子工程系 [4]国网河南省电力公司,河南省郑州市450052

出　　处：《电力系统自动化》2016年第7期98-106,共9页Automation of Electric Power Systems

基　　金：国家自然科学基金资助项目(51477151;51407076);河北省自然科学基金资助项目(F2014502050);河北省高等学校科学研究项目(Z2013007);中央高校基本科研业务费专项资金资助项目(2015ZD28)~~

摘　　要：针对电力一次系统和电力信息系统的数据所具有的多维度、时空混杂等特征,建立了一种基于偏序约简的大数据属性约简预处理方法。该方法综合利用了MapReduce的可并行化优点,着眼于并发事件间的独立性,可以满足电力大数据属性维度与约简方面的覆盖要求。最后,分别以某光伏发电系统监测数据、变压器故障诊断数据和智能变电站通信系统实时性与可靠性预测数据为例,对属性约简进行模拟计算,并通过Hadoop平台进行测试,表明所提出的电力大数据属性约简方法性能优良。By taking into account the multi-dimensional,hybrid spatial and temporal characteristics of data from a power system and/or a power information system,a big data attribute reduction preprocessing method based on partial order reduction is presented.In the proposed method,the parallel advantage of MapReduce is employed and the independence of concurrent events is focused on,making it possible to meet the coverage requirements of big data attribute dimension and reduction in a power system.Finally,the proposed attribute reducing method is simulated by some examples including the monitoring data of aphotovoltaic（PV）power generation system,the fault diagnosis data of a transformer,and real-time and reliability data of the communication system of an intelligent substation,with good performance observed through a Hadoop platform.

关 键 词：智能电网 大数据 偏序约简 数据预处理 MAPREDUCE HADOOP 

分 类 号：TM76[电气工程—电力系统及自动化]