摘要
为提高电力用户类型分类精度及电力业务人员工作效率,提出基于多源数据融合的电力用户画像构建方法。收集电力客户缴费数据,采用灰色关联分析法,获取欠费数据与价格指数的关联度,利用电力网络多源数据集合与概率密度函数,提取用户欠费数据多源信息特征,构建电力用户多源数据融合体系,采用改进K均值聚类算法,获得电力用户总体调控簇别,评估用户信息全貌。实验结果表明,所提方法的敏感度用户类型分类精度较高,电力用户画像构建耗时较短,能够有效提高电力业务人员工作效率。
In order to improve the classification accuracy of power user types and the efficiency of power business personnel,a method for building power user portraits based on multi-source data fusion is proposed.It collects electricity customer payment data,uses grey correlation analysis to obtain the correlation between arrears data and price index,uses the power network multi-source data collection and probability density function to extract the multi-source information characteristics of user arrears data,and builds a multi-source power user the data fusion system uses an improved K-means clustering algorithm to obtain the overall control clusters of power users and evaluate the overall picture of user information.The experimental results show that the proposed method has higher classification accuracy of sensitive user types,and the construction of power user profile takes less time,which can effectively improve the work efficiency of power business personnel.
作者
苗光尧
安静
黄小花
李叶飞
王国彬
MIAO Guang-yao;AN Jing;HUANG Xiao-hua;LI Ye-fei;WANG Guo-bin(Marketing Service Center of State Grid Ningxia Power Co.,Ltd.,(Measurement Center of State Grid Ningxia Power Co.,Ltd.),Yinchuan 750001 China)
出处
《自动化技术与应用》
2022年第8期93-96,125,共5页
Techniques of Automation and Applications
关键词
多源数据融合
用户画像
敏感型
用电特征
消费习惯
multi source data fusion
user portrait
sensitive
electricity consumption characteristics
consumption habits
作者简介
苗光尧(1973-),男,高级工程师,研究方向:电力营销技术、用电能效与综合能源等。
