半月刊

ISSN 1000-1026

CN 32-1180/TP

+高级检索 English
基于t-SNE降维和BIRCH聚类的单相用户相位及表箱辨识
作者:
作者单位:

1.浙江大学电气工程学院,浙江省杭州市 310027;2.国网浙江省电力有限公司电力科学研究院,浙江省杭州市 310014;3.国网浙江省海盐县供电有限公司,浙江省嘉兴市 314300;4.浙江华云信息科技有限公司,浙江省杭州市 310012

作者简介:

通讯作者:

基金项目:

国家重点研发计划资助项目(2016YFB0901100);国家自然科学基金资助项目(51777185);国家电网公司总部科技项目(5600-201919168A-0-0-00)。


Phase and Meter Box Identification Method for Single-phase Users Based on t-SNE Dimension Reduction and BIRCH Clustering
Author:
Affiliation:

1.College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China;2.Electric Power Research Institute of State Grid Zhejiang Electric Power Co., Ltd., Hangzhou 310014, China;3.Haiyan Electric Power Supply Company of State Grid Zhejiang Electric Power Co., Ltd., Jiaxing 314300, China;4.Zhejiang Huayun Information Technology Co., Ltd., Hangzhou 310012, China

Fund Project:

This work is supported by National Key R&D Program of China (No. 2016YFB0901100), National Natural Science Foundation of China (No. 51777185), and State Grid Corporation of China (No. 5600-201919168A-0-0-00).

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
    摘要:

    低压台区单相用户的相位及接入表箱信息的准确性对户变关系纠错和线损治理分析有重要影响。目前,拓扑档案的校验主要依靠电力员工现场排查,人力物力消耗大且排查效率低下。因此,亟需一种效率较高的低压台区拓扑档案校验方法。在此背景下,文中提出了一种基于智能电表电压数据的低压台区单相用户相位及接入表箱辨识方法,可以为低压台区的拓扑辨识及排查提供参考。首先,采用t分布的随机近邻嵌入(t-SNE)技术对原始负荷数据进行降维处理,解决台区用户原始负荷特征维度过高带来的冗余性问题;接着,应用BIRCH方法对降维后的负荷数据进行聚类,实现台区下单相用户所属相位和接入表箱的辨识。最后,以浙江省海宁市某台区为例进行验证,算例分析的结果表明所提模型具有可行性和有效性。

    Abstract:

    The accurate phase and meter box information of single-phase users in low-voltage courts have great influences on the checking of user-transformer relationships and the treatment and analysis of line losses. At present, the correction of topological documents mainly relies on the on-site checking by electrical engineers, which spends a lot of manpower and material resources and is with low efficiency. Therefore, it is necessary to study a more efficient method of checking the topological documents of the low-voltage courts. Given this background, a phase and meter box identification method based on voltage measurement data of smart meters is proposed, which is helpful for topology identification and correction of low-voltage courts. Firstly, the t-distributed stochastic neighbor embedding (t-SNE) technology is adopted to reduce the dimension of original load data, so as to solve the redundancy problems caused by excessively high dimension of original load characteristics of users. Then, the balanced iterative reducing and clustering using hierarchies (BIRCH) method is used to cluster the dimension-reduced load data, so as to identify the phase and meter box information of single-phase users. Finally, case studies for an actual low-voltage court in Haining, China, are performed to verify the correctness of the proposed method, and the results show that the proposed model is feasible and effective.

    表 4 不同降维维度下各种方法的接入表箱辨识准确率Table 4 Identification accuracy rate of meter box with different dimension by using various methods
    表 1 降维前后数据集方差与相关性的变化Table 1 Change of variance and correlation of original data and dimension-reduced data
    表 2 降维数据与原始数据接入表箱辨识准确率比较Table 2 Accuracy rate comparison of meter box identification based on original data and dimension-reduced data
    表 3 不同方法下的相位辨识准确率比较Table 3 Comparison of identification accuracy rate of phase with different methods
    图1 低压台区常规拓扑结构Fig.1 Topological structure of low-voltage courts
    图2 数据驱动的低压台区单相用户相位及接入表箱辨识流程图Fig.2 Flow chart of data-driven identification of phase and meter box of single-phase user in low-voltage courts
    图3 t-SNE降维误差收敛过程Fig.3 Convergence process of error based on t-SNE dimension reduction
    图4 低压台区单相用户相位及接入表箱辨识结果Fig.4 Identification result of phase and meter box of single-phase user in low-voltage court
    表 5 Table 5
    图 计量采集系统层次图Fig. Hierarchical diagram of measurement and acquisition system
    参考文献
    相似文献
    引证文献
引用本文

连子宽,姚力,刘晟源,等.基于t-SNE降维和BIRCH聚类的单相用户相位及表箱辨识[J/OL].电力系统自动化,http://doi.org/10.7500/AEPS20190621001.
LIAN Zikuan,YAO Li,LIU Shengyuan,et al.Phase and Meter Box Identification Method for Single-phase Users Based on t-SNE Dimension Reduction and BIRCH Clustering[J/OL].Automation of Electric Power Systems,http://doi.org/10.7500/AEPS20190621001.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2019-06-21
  • 最后修改日期:2020-02-21
  • 录用日期:2019-09-29
  • 在线发布日期:
  • 出版日期: