首页 | 本学科首页   官方微博 | 高级检索  
     

基于先验知识与DBM采样的类不平衡用电数据分类方法
引用本文:王凯亮,陆俊,徐志强,齐增清,龚钢军,王赟.基于先验知识与DBM采样的类不平衡用电数据分类方法[J].电力系统自动化,2019,43(20):57-64.
作者姓名:王凯亮  陆俊  徐志强  齐增清  龚钢军  王赟
作者单位:华北电力大学电气与电子工程学院,北京市,102206;湖南经研电力设计有限公司,湖南省长沙市,410004
基金项目:国网湖南省电力有限公司科技项目(SGHNJY00JHQT190128)
摘    要:智能电网建设过程中现有客户标签体系不够完善,针对海量用户用电数据的分类管理中带有标签的样本数据量小以及类不平衡分布的问题,提出了一种基于先验知识与深度玻尔兹曼机(DBM)采样的不平衡用电数据分类方法。首先,提取负荷曲线的特征,建立采样原则,利用先验知识和DBM对负荷曲线进行采样。然后,将采样数据通过极限学习机(ELM)网络进行训练。最后以爱尔兰用户用电数据为数据源,通过与原始非采样、随机过采样、合成少数类过采样技术(SMOTE)的对比性实验分析结果表明,所提出的基于先验知识与DBM采样的不平衡用电数据分类方法能够更好地对类不平衡用电数据集进行分类,实现用户用电行为的分析,有效支撑用户侧错峰避峰工作。

关 键 词:类不平衡数据  用户行为分析  深度学习  先验知识  深度玻尔兹曼机
收稿时间:2018/11/28 0:00:00
修稿时间:2019/7/1 0:00:00

Classification Method of Unbalanced Power Consumption Data Based on Prior Knowledge and Deep Boltzmann Machine Sampling
WANG Kailiang,LU Jun,XU Zhiqiang,QI Zengqing,GONG Gangjun and WANG Yun.Classification Method of Unbalanced Power Consumption Data Based on Prior Knowledge and Deep Boltzmann Machine Sampling[J].Automation of Electric Power Systems,2019,43(20):57-64.
Authors:WANG Kailiang  LU Jun  XU Zhiqiang  QI Zengqing  GONG Gangjun and WANG Yun
Affiliation:School of Electrical and Electronic Engineering, North China Electric Power University, Beijing 102206, China,School of Electrical and Electronic Engineering, North China Electric Power University, Beijing 102206, China,Hunan Power Economic Research Design Co., Ltd., Changsha 410004, China,Hunan Power Economic Research Design Co., Ltd., Changsha 410004, China,School of Electrical and Electronic Engineering, North China Electric Power University, Beijing 102206, China and School of Electrical and Electronic Engineering, North China Electric Power University, Beijing 102206, China
Abstract:The existing customer labeling system in the smart grid construction process is not perfect. In the classification management of electricity data for massive users, there is a problem of small sample data and unbalanced distribution of labels. This paper proposes a classification method of unbalanced electricity data based on prior knowledge and deep Boltzmann machine(DBM)sampling. Firstly, the characteristics of load curve are extracted, the sampling principle is established, and the prior knowledge and DBM are used to sample the load curve. Then, the sample data are trained through the extreme learning machine(ELM)network. Finally, the Irish users'' electricity data are used as the data source. Contrastive experimental analysis results of original non-sampling, random oversampling and synthetic minority oversampling technique(SMOTE)show that the proposed method can better classify the unbalanced electricity data sets, realize the analysis of the user''s electricity usage behavior, and effectively support the peak shifting and peak avoidance at user side.
Keywords:unbalanced data  analysis of users'' behaviors  deep learning  prior knowledge  deep Boltzmann machine
本文献已被 万方数据 等数据库收录!
点击此处可从《电力系统自动化》浏览原始摘要信息
点击此处可从《电力系统自动化》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号