摘要
用户的用电情况会影响台区电压偏离正常值,影响配电系统供电可靠性。为了实现供电系统的优化管理,提出一种基于模糊C-均值聚类的台区电压与用户关系辨识方法。首先,对来自智能电表的不良数据进行处理和修补;然后,采用PCA(主成分分析)法对其数据进行特征提取,并模拟不同对象进行模糊C-均值分类。根据多种数据特征,把用户归为大、中、小3个等级类型。采用皮尔逊相关系数,阐明各个等级类型用户的用电行为对台区的电压影响,构建明确的台区电压与用户之间的关系。以广州某小区为实例,通过历史数据进行了多场景仿真对比,验证了该辨识方法的有效性和适用性。结果表明,该辨识方法能够快速识别某些特殊用户的用电行为及其对台区电压产生的异常影响。
The users′electricity consumption will affect the voltage deviation from the normal value and affect the reliability of power supply of distribution system.In order to realize the optimal management of power supply,an identification method for relationship between transformer and users based on fuzzy C-means clustering is proposed.Firstly,the bad data from smart meter is identified and repaired,and then the principal component analysis(PCA)method is used to extract the features of the data,and the different objects are simulated for fuzzy C-means classification.According to a variety of data characteristics,users are classified into three levels:large,medium and small.The Pearson correlation coefficient is used to clarify the influence of electricity consumption behavior of different types of users on the voltage in the substation area,and to build a clear relationship between transformer and users.Taking a residential area in Guangzhou for example,the effectiveness and applicability of the proposed identification method are verified by comparing the historical data with multi-scene simulation.The results show that the proposed identification method can quickly identify the electricity consumption behavior of some special users and the abnormal impact on the voltage of the substation area.
作者
曾顺奇
吴杰康
李欣
蔡志宏
Zeng Shunqi;Wu Jiekang;Li Xing;Cai Zhihong(Guangzhou Power Supply Bureau of Guangdong Power Grid Co.,Ltd.,Guangzhou 510000,Guangdong,China;School of Automation,Guangdong University of Technology,Guangzhou 510006,Guangdong,China)
出处
《四川电力技术》
2021年第3期69-75,87,共8页
Sichuan Electric Power Technology
基金
广东电网有限责任公司广州供电局科技项目(GZHKJXM20190062)。
关键词
台区电压与用户关系
不良数据修补
用户用电行为
模糊C-均值聚类分析
主成分分析
relationship between transformer and users
repair of bad data
users′electricity consumption behavior
fuzzy C-means clustering analysis
principal component analysis
