基于异常点检测和改进K-means算法的台区用户相别辨识方法  被引量:26

Phase Identification Method for Distribution Area Users Based on Outlier Detection and Improved K-means Algorithm

在线阅读下载全文

作  者:张然 孙晓璐[1] 何仲潇 薛莉思 陈维民[1] 徐严军 连利波 ZHANG Ran;SUN Xiaolu;HE Zhongxiao;XUE Lisi;CHEN Weimin;XU Yanjun;LIAN Libo(State Grid Sichuan Electric Power Corporation Metering Center,Chengdu 610000,China;Tsinghua Sichuan Energy Internet Research Institute,Chengdu 610000,China)

机构地区:[1]国网四川省电力公司计量中心,四川成都610000 [2]清华四川能源互联网研究院,四川成都610000

出  处:《智慧电力》2020年第1期91-96,共6页Smart Power

基  金:国家重点研发计划资助(2018YFB0905200);国家电网公司科技项目资助(521997170025)~~

摘  要:解决配电台区用户线变不匹配问题是推进配电网智能化管理的关键一步。大数据技术的快速普及为实现低成本、高效率的台区用户相别辨识提供了可能。提出了基于异常点检测和改进K-means算法的台区用户相别辨识方法。首先通过局部因子算法对聚类分析数据进行预处理,剔除不属于待分析台区的用户数据。然后,根据实际应用场景特点对K-means算法进行改进,包括确定聚类个数、初始质心,并选用相关系数作为评估样本相似度的指标。最后利用改进的K-means算法对预处理后的数据进行聚类分析,实现低压台区用户相别的精准辨识。算例分析表明,所提方法能够有效提升用户辨识准确率,且在不同的数据环境中可保持较高的稳定性。Solving the problem of the mismatch of subscriber line in distribution area is a key step to promote the intelligent management of distribution network.The rapid popularization of big data technology makes it possible to realize distribution area user identification with low-cost and high-efficiency.The paper proposes a phase identification method for the users based on outlier detection and improved K-means algorithm.Firstly,the data of clustering analysis is preprocessed by local factor algorithm,and the user data that aren't part of the area data to be analyzed is deleted.Then,K-means algorithm is improved according to the characteristics of practical application scenarios,determining the number of clustering,initial centroid and selecting correlation coefficient as the index of evaluating sample similarity.Finally,the improved K-means algorithm is used to cluster the pre-processed data to realize the accurate identification of the users in low voltage station area.Examples show that the proposed method can ef-fectively improve the accuracy of the user identification and maintain high stability in different data environments.

关 键 词:配电网 台区 相别辨识 局部异常因子算法 改进K-MEANS 

分 类 号:TM721[电气工程—电力系统及自动化]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象