半月刊

ISSN 1000-1026

CN 32-1180/TP

+高级检索 English
基于DDTW距离与DBSCAN算法的户变关系识别方法
作者:
作者单位:

1.湖南大学电气与信息工程学院,湖南省长沙市 410082;2.常德国力变压器有限公司,湖南省常德市 415000;3.湖南文理学院计算机与电气工程学院,湖南省常德市 415006

摘要:

针对低压配电台区拓扑结构中户变关系缺失或异常的问题,提出了一种基于导数动态时间弯曲(DDTW)算法与基于密度的有噪空间聚类应用(DBSCAN)算法的户变关系识别方法。首先,采用DDTW算法对台区配电变压器(以下简称台变)低压侧电压和用户电压的时间序列进行相似性分析。然后,根据DDTW距离对台变和用户进行聚类得到户变关系的概率性结果,减小聚类算法参数对聚类结果的影响。该方法能够对时间间隔不同、不等长的电压时间序列进行分析,对电压数据缺失或异常不敏感,且不需要人为设定阈值,户变关系识别准确性高。最后,通过实例分析验证了所提方法的有效性。

关键词:

基金项目:

湖南省自然科学基金资助项目(2019JJ60012);湖南省战略性新兴产业科技攻关与重大科技成果转化项目(2018GK4025)。

通信作者:

作者简介:

刘苏(1995—),男,硕士研究生,主要研究方向:配电网自动化、电力系统故障诊断。E-mail:1316003502@qq.com
黄纯(1966—),男,通信作者,博士,教授,博士生导师,主要研究方向:电力系统继电保护及自动控制技术。E-mail:yellowpure@hotmail.com
侯帅帅(1993—),男,硕士研究生,主要研究方向:配电网自动化。E-mail:1179541091@qq.com


Identification Method for Household-Transformer Relationship Based on Derivative Dynamic Time Warping Distance and Density-based Spatial Clustering of Application with Noise Algorithm
Author:
Affiliation:

1.College of Electrical and Information Engineering, Hunan University, Changsha 410082, China;2.Changde GuoLi Transformer Co., Ltd., Changde 415000, China;3.Department of Computer and Electrical Engineering, Hunan University of Arts and Science, Changde 415006, China

Abstract:

Aiming at the problem of the missing or abnormal household-transformer relationship in the topology of low-voltage distribution stations, this paper proposes an identification method of household-transformer relationship based on the derivative dynamic time warping (DDTW) algorithm and the density-based spatial clustering of application with noise (DBSCAN) algorithm. Firstly, the DDTW algorithm is used to analyze the similarity of the time series of the voltages between the low-voltage side of the substation transformers and the users. Secondly, the probabilistic results of the household-transformer relationship are obtained by clustering the substation transformers and the users according to the DDTW distance. The influence of the parameters of the clustering algorithm on the clustering results is reduced. The method is able to analyze voltage time series with different time intervals and unequal lengths. It is insensitive to missing or abnormal voltage data and does not require artificially threshold setting, and has high accuracy in identifying household-transformer relationships. Finally, the effectiveness of the proposed method is verified through case analysis.

Keywords:

Foundation:
This work is supported by Hunan Provincial Natural Science Foundation of China (No. 2019JJ60012) and Hunan Province Strategic Emerging Industry Science and Technology Research and Major Science and Technology Achievement Transformation Project (No. 2018GK4025).
引用本文
[1]刘苏,黄纯,侯帅帅,等.基于DDTW距离与DBSCAN算法的户变关系识别方法[J].电力系统自动化,2021,45(18):71-77. DOI:10.7500/AEPS20201123001.
LIU Su, HUANG Chun, HOU Shuaishuai, et al. Identification Method for Household-Transformer Relationship Based on Derivative Dynamic Time Warping Distance and Density-based Spatial Clustering of Application with Noise Algorithm[J]. Automation of Electric Power Systems, 2021, 45(18):71-77. DOI:10.7500/AEPS20201123001.
复制
分享
历史
  • 收稿日期:2020-11-23
  • 最后修改日期:2021-04-02
  • 录用日期:
  • 在线发布日期: 2021-09-16
  • 出版日期:
相关附件