[1]蒋菱[],王旭东[],于建成[],等. 基于分布式计算的海量用电数据分析技术研究[J].计算机技术与发展,2016,26(12):176-181.
　JIANG Ling[],WANG Xu-dong[],YU Jian-cheng[],et al. Research on Power Usage Behavior Analysis Based on Distributed Computing[J].,2016,26(12):176-181.
点击复制

 基于分布式计算的海量用电数据分析技术研究()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
26
期数:
2016年12期
页码:
176-181
栏目:
应用开发研究
出版日期:
2016-12-10

文章信息/Info

Title:
 Research on Power Usage Behavior Analysis Based on Distributed Computing
文章编号:
1673-629X（2016)12-0176-06
作者:
 蒋菱[1]; 王旭东[1]; 于建成[1]; 袁晓冬[2]
1. 国网天津市电力公司；2.江苏省电力科学研究院
Author(s):
 JIANG Ling[1]; WANG Xu-dong[1]; YU Jian-cheng[1]; YUAN Xiao-dong[2]
关键词:
 ; MapReduce; 模糊C均值聚类; 用电行为分析; 大数据
Keywords:
 ; MapReduce; FCM; analysis of electric behavior; big data
分类号:
TP39
文献标志码:
A
摘要:
 用电行为分析技术对供电企业掌握用户用能方式、调整生产计划以及进行电网规划有着较大的现实意义。传统用电行为分析多利用少量样本数据，由于数据源覆盖面的问题往往容易造成结果偏差。借助大数据技术，可以利用海量用电数据提高用电行为分析的准确性。针对用电行为分析在处理海量数据时效率低下的问题，提出了基于MapReduce技术的模糊 C 均值聚类( FCM)并行算法，通过将FCM算法的迭代过程分解到Map和Reduce两个步骤中，可以有效地提高聚类过程中数据对象和聚类中心的相似度计算效率。在此基础上，利用所提出的FCM并行算法对居民用电数据的四个特征进行聚类分析。实验结果表明，所提算法可以提高海量用电数据聚类分析的效率，证明了计算模型的可行性。
Abstract:
 The power usage behavior analysis technology can be used to acquire costumer power usage pattern,adjust power generation schedule and plan gird development. Thus,it is meaningful to power grid company. Traditional power usage behavior analysis only uses small volume of data. The limited data will draw to inaccurate result. This problem can be solved by using large scale of data. In allusion to the problem about electricity behavior analysis in the low efficiency of dealing with huge amounts of data,the Fuzzy C-Means cluste-ring ( FCM) parallel algorithm based on MapReduce is put forward. By decomposing the iterative process of FCM algorithm into two steps of Map and Reduce,it can effectively improve the efficiency of similarity computing between the data objects and the clustering cen-ters. On this basis,the four characteristics of resident electrical data are clustering analyzed by using the proposed FCM parallel algorithm. The experimental results show that the proposed algorithm can improve the efficiency of mass data clustering analysis and also proves the feasibility of the model.

相似文献/References:

[1]李玲娟 张敏.云计算环境下关联规则挖掘算法的研究[J].计算机技术与发展,2011,(02):43.
　LI Ling-juan,ZHANG Min.Research on Algorithms of Mining Association Rule under Cloud Computing Environment[J].,2011,(12):43.
[2]李远方 邓世昆 闻玉彪 韩月阳.Hadoop-MapReduce下的PageRank矩阵分块算法[J].计算机技术与发展,2011,(08):6.
　LI Yuan-fang,DENG Shi-kun,WEN Yu-biao,et al.PageRank Matrix Partitioned Algorithm Using Hadoop-MapReduce[J].,2011,(12):6.
[3]李远方 贾时银 邓世昆 韩月阳.基于树结构的MapReduce模型[J].计算机技术与发展,2011,(08):149.
　LI Yuan-fang,JIA Shi-yin,DENG Shi-kun,et al.MapReduce Model Based on Tree Structure[J].,2011,(12):149.
[4]王梅,朱信忠,赵建民,等.基于 Hadoop 的海量图像检索系统[J].计算机技术与发展,2013,(01):204.
　WANG Mei,ZHU Xin-zhong,ZHAO Jian-min,et al.Massive Images Retrieval System Based on Hadoop[J].,2013,(12):204.
[5]贺瑶,王文庆,薛飞.基于云计算的海量数据挖掘研究[J].计算机技术与发展,2013,(02):69.
[6]舒琰,向阳,张骐,等.基于PageRank的微博排名MapReduce算法研究[J].计算机技术与发展,2013,(02):73.
　SHU Yan,XIANG Yang,ZHANG Qi,et al.Research on MapReduce Algorithm of Micro Blog Ranking Based on PageRank[J].,2013,(12):73.
[7]朱贤军,李敬兆.无加密模式下对云数据的隐私保密[J].计算机技术与发展,2013,(06):216.
　ZHU Xian-jun,LI Jing-zhao.Cloud Data Privacy under None Encryption[J].,2013,(12):216.
[8]周婷,张君瑛,罗成.基于Hadoop的K-means聚类算法的实现[J].计算机技术与发展,2013,(07):18.
　ZHOU Ting[],ZHANG Jun-ying[],LUO Cheng[].Realization of K-means Clustering Algorithm Based on Hadoop[J].,2013,(12):18.
[9]张志宏,吴庆波,邵立松,等.基于飞腾平台TOE协议栈的设计与实现[J].计算机技术与发展,2014,24(07):1.
　ZHANG Zhi-hong,WU Qing-bo,SHAO Li-song,et al. Design and Implementation of TCP/IP Offload Engine Protocol Stack Based on FT Platform[J].,2014,24(12):1.
[10]梁文快,李毅. 改进的基因表达算法对航班优化排序问题研究[J].计算机技术与发展,2014,24(07):5.
　LIANG Wen-kuai,LI Yi. Research on Optimization of Flight Scheduling Problem Based on Improved Gene Expression Algorithm[J].,2014,24(12):5.
[11]孙媛,黄刚. 基于Hadoop平台的C4.5算法的分析与研究[J].计算机技术与发展,2014,24(11):83.
　SUN Yuan,HUANG Gang. Analysis and Study of C4 . 5 Algorithm Based on Hadoop Platform[J].,2014,24(12):83.
[12]王添,姜麟,米允龙. 海量数据下不完备信息系统的知识约简算法[J].计算机技术与发展,2015,25(01):137.
　WANG Tian,JIANG Lin,MI Yun-long. Knowledge Reduction Algorithms of Incomplete Information System in Massive Datasets[J].,2015,25(12):137.
[13]秦军[],童毅[],戴新华[],等. 基于MapReduce数据密集型负载调度策略研究[J].计算机技术与发展,2015,25(04):48.
　QIN Jun[],TONG Yi[],DAI Xin-hua[],et al. Research on Scheduling Strategy of Data Intensive Workloads Based on MapReduce[J].,2015,25(12):48.
[14]陈静,郑彦. 基于二叉树的并行频繁项集挖掘算法[J].计算机技术与发展,2015,25(10):80.
　CHEN Jing,ZHENG Yan. Parallel Algorithm of Frequent Itemset Mining Based on Binary-tree[J].,2015,25(12):80.
[15]李振举,李学军,刘涛,等. MapReduce 性能预测模型构建[J].计算机技术与发展,2016,26(01):70.
　LI Zhen-ju,LI Xue-jun,LIU Tao,et al. Performance Prediction Model Construction of MapReduce[J].,2016,26(12):70.
[16]李程,曹菡,师军. 基于MapReduce的混合推荐算法及应用[J].计算机技术与发展,2016,26(04):74.
　LI Cheng,CAO Han,SHI Jun. Hybrid Recommendation Algorithm Based on MapReduce and Its Application[J].,2016,26(12):74.
[17]郭先超,林宗缪,姚文勇. 互联网+质量检测平台设计[J].计算机技术与发展,2016,26(05):120.
　GUO Xian-chao,LIN Zong-miao,YAO Wen-yong. Design of Platform for Internet+ Quality Inspection[J].,2016,26(12):120.
[18]范素娟[],田军锋[]. 基于Hadoop的云计算平台研究与实现[J].计算机技术与发展,2016,26(07):127.
　FAN Su-juan[],TIAN Jun-feng[]. Research and Implementation of Cloud Computing Platform Based on Hadoop[J].,2016,26(12):127.
[19]王伟,杨庚,张成果. CryptDB密文数据库系统并行方案研究[J].计算机技术与发展,2017,27(02):90.
　WANG Wei,YANG Geng,ZHANG Cheng-guo. Investigation on Parallel Scheme of CryptDB Encrypted Database System[J].,2017,27(12):90.
[20]杨洁,黄刚. 基于云计算的SPRINT算法研究[J].计算机技术与发展,2017,27(03):108.
　YANG Jie,HUANG Gang. Research on SPRINT Algorithm Based on Cloud Computing[J].,2017,27(12):108.

更新日期/Last Update: 2017-02-04