Non-intrusive Perception and Identification of Industrial Power Load Based on Analysis of Event on User Edge

Xin WU; Jinying YU; Lin PENG; Qinghua WANG; Yulong YAN

doi:10.7500/AEPS20200323013

您当前的位置：

首页 >

文章列表页 >

Non-intrusive Perception and Identification of Industrial Power Load Based on Analysis of Event on User Edge

Basic Research | 更新时间：2025-06-16

- Non-intrusive Perception and Identification of Industrial Power Load Based on Analysis of Event on User Edge
- Automation of Electric Power Systems Vol. 45, Issue 4, Pages: 29-37(2021)
- 作者机构：
  
  1.华北电力大学电气与电子工程学院，北京市 102206
  2.华北电力大学环境科学与工程学院，北京市 102206
  3.华北电力大学控制与计算机工程学院，北京市 102206
- 作者简介：
- 基金信息：
  
  the Fundamental Research Funds for the Central Universities
- DOI：10.7500/AEPS20200323013
  CLC：
- Received：23 March 2020，
  
  Revised：2020-09-07，
  
  Published Online：31 December 2020，
  
  Published：25 February 2021
- 稿件说明：
移动端阅览
武昕,于金莹,彭林等.基于用户边缘侧事件解析的工业电力负荷非侵入式感知辨识[J].电力系统自动化,2021,45(4):29-37.

WU Xin,YU Jinying,PENG Lin,et al.Non-intrusive Perception and Identification of Industrial Power Load Based on Analysis of Event on User Edge[J].Automation of Electric Power Systems,2021,45(4):29-37.
武昕,于金莹,彭林等.基于用户边缘侧事件解析的工业电力负荷非侵入式感知辨识[J].电力系统自动化,2021,45(4):29-37. DOI： 10.7500/AEPS20200323013.

WU Xin,YU Jinying,PENG Lin,et al.Non-intrusive Perception and Identification of Industrial Power Load Based on Analysis of Event on User Edge[J].Automation of Electric Power Systems,2021,45(4):29-37. DOI： 10.7500/AEPS20200323013.

摘要

考虑工业生产的持续、安全等因素，避免在高压生产区对负荷进行直接测量，采用非侵入式感知模式在低压总用电计量端进行监测，通过分离解析总信号获取各负荷详细的运行情况。文中研究了一种基于事件波形解析的辨识方法，为了适应不同用户生产门类及流水工艺的差异，将事件解析下沉至用户边缘。首先，利用工业负荷单体功率大的特点，结合不同投切形式分离事件波形。然后，在用户边缘形成该用户的解释空间，构建有效描述事件波形的结构化特征空间，建立映射规则实现特征空间与解释空间的对应，并通过类别判定完成事件解析与负荷辨识。最后，利用聚类对群体事件进行分类辨识以优化验证辨识结果。通过实际采集的钢铁工业用电数据验证方法的有效性，实现其用电感知与事件解析。

Abstract

Considering the sustainability and safety factors of industrial production

the direct measurement of loads in the high-voltage production area should be avoided

and the non-intrusive perception mode is adopted for monitoring at low-voltage total electricity metering terminals. The detailed operation condition of each load is obtained by decomposing and analyzing the overall signal. In this paper

an identification method based on event waveform analysis is studied. In order to adapt to the differences of production categories and pipelining processes of different users

event analysis is sunk to the edge of users. First

according to the characteristic of high power of the industrial load unit and different switching modes

the event waveform is decomposed. Then

the interpretation space of users is formed on their edge. A structured feature space which can effectively describe the event waveform is constructed. Mapping rules are established to achieve the correspondence between the feature space and the interpretation space. The event analysis and load identification are completed through category judgment. Finally

clustering is used to classify and identify group events to optimize and verify the identification results. The validity of the method is verified by the actual electricity data collected in the steel industry

and the perception and event analysis of the power consumption are realized.

关键词

Keywords

references

LIU Y H . Internet of everything for new industrial revolution ［M］. Beijing ： Tsinghua University Press ， 2016 .

马宝罗，池程，田娟，等 . 基于UICC的工业互联网标识多维数据融合研究［J］. 信息通信技术与政策， 2020 （ 8 ）： 85 - 88 .

MA Baoluo ， CHI Cheng ， TIAN Juan ， et al . Research on multidimensional data fusion of industrial internet identification based on UICC ［J］. Telecommunications Network Technology ， 2020 （ 8 ）： 85 - 88 .

MIKA B ， GOUDZ A . Blockchain-technology in the energy industry： blockchain as a driver of the energy revolution？ With focus on the situation in Germany ［J］. Energy Systems ， 2020 ： 1 - 7 .

何昉，孔德泰，闫丽蓉，等 . 新一轮能源革命条件下我国核电发展战略选择——基于SWOT-AHP框架的分析［J］. 中国能源， 2020 ， 42 （ 7 ）： 26 - 30 .

HE Fang ， KONG Detai ， YAN Lirong ， et al . China’s nuclear power development strategy choice under the new round of energy revolution—an analysis based on SWOT-AHP framework ［J］. Energy of China ， 2020 ， 42 （ 7 ）： 26 - 30 .

姚明涛，胡兆光，张宁，等 . 工业负荷提供辅助服务的多智能体响应模拟［J］. 中国电机工程学报， 2014 ， 34 （ 25 ）： 4219 - 4226 .

YAO Mingtao ， HU Zhaoguang ， ZHANG Ning ， et al . Multi-agent response simulation of industrial loads for ancillary services ［J］. Proceedings of the CSEE ， 2014 ， 34 （ 25 ）： 4219 - 4226 .

NOVOA L ， FLORES R ， BROUWER J . Optimal renewable generation and battery storage sizing and siting considering local transformer limits ［J］. Applied Energy ， 2019 ， 256 ： 113926 .

XU J ， CHEN Y F ， LIAO S Y ， et al . Demand side industrial load control for local utilization of wind power in isolated grids ［J］. Applied Energy ， 2019 ， 243 ： 47 - 56 .

HART G W . Nonintrusive appliance load monitoring ［J］. Proceedings of the IEEE ， 1992 ， 80 （ 12 ）： 1870 - 1891 .

LIU C ， AKINTAYO A ， JIANG Z H ， et al . Multivariate exploration of non-intrusive load monitoring via spatiotemporal pattern network ［J］. Applied Energy ， 2018 ， 211 ： 1106 - 1122 .

祁兵，董超，武昕，等 . 基于DTW算法与稳态电流波形的非侵入式负荷辨识方法［J］. 电力系统自动化， 2018 ， 42 （ 3 ）： 70 - 76 .

QI Bing ， DONG Chao ， WU Xin ， et al . Non-intrusive load identification method based on DTW algorithm and steady-state current waveform ［J］. Automation of Electric Power Systems ， 2018 ， 42 （ 3 ）： 70 - 76 .

WELIKALA S ， DINESH C ， EKANAYAKE M P B ， et al . Incorporating appliance usage patterns for non-intrusive load monitoring and load forecasting ［J］. IEEE Transactions on Smart Grid ， 2019 ， 10 （ 1 ）： 448 - 461 .

WELIKALA S ， THELASINGHA N ， AKRAM M ， et al . Implementation of a robust real-time non-intrusive load monitoring solution ［J］. Applied Energy ， 2019 ， 238 ： 1519 - 1529 .

HASSAN T ， JAVED F ， ARSHAD N . An empirical investigation of V - I trajectory based load signatures for non-intrusive load monitoring ［J］. IEEE Transactions on Smart Grid ， 2014 ， 5 （ 2 ）： 870 - 878 .

武昕，焦点，高宇辰 . 基于非侵入式用电数据分解的自适应特征库构建与负荷辨识［J］. 电力系统自动化， 2020 ， 44 （ 4 ）： 101 - 109 .

WU Xin ， JIAO Dian ， GAO Yuchen . Construction of adaptive feature library and load identification based on decomposition of non-intrusive power consumption data ［J］. Automation of Electric Power Systems ， 2020 ， 44 （ 4 ）： 101 - 109 .

王守相，郭陆阳，陈海文，等 . 基于特征融合与深度学习的非侵入式负荷辨识算法［J/OL］. 电力系统自动化［ 2020-03-13 ］. https：//kns-cnki-net.webvpn.ncepu.edu.cn/kcms/detail/32.1180.TP.20191022.1625.016.html https://kns-cnki-net.webvpn.ncepu.edu.cn/kcms/detail/32.1180.TP.20191022.1625.016.html .

WANG Shouxiang ， GUO Luyang ， CHEN Haiwen ， et al . Non-invasive load identification algorithm based on feature fusion and deep learning ［J/OL］. Automation of Electric Power Systems ［ 2020-03-13 ］. https：//kns-cnki-net.webvpn.ncepu.edu.cn/kcms/detail/32.1180.TP.20191022.1625.016.html https://kns-cnki-net.webvpn.ncepu.edu.cn/kcms/detail/32.1180.TP.20191022.1625.016.html .

HE K H ， STANKOVIC L ， LIAO J ， et al . Non-intrusive load disaggregation using graph signal processing ［J］. IEEE Transactions on Smart Grid ， 2018 ， 9 （ 3 ）： 1739 - 1747 .

CHANG H ， CHEN K ， TSAI Y ， et al . A new measurement method for power signatures of nonintrusive demand monitoring and load identification ［J］. IEEE Transactions on Industry Applications ， 2012 ， 48 （ 2 ）： 764 - 771 .

陈小闽 . 非侵入式负荷分解技术及应用研究［D］. 广州：华南理工大学， 2018 .

CHEN Xiaomin . Research on non-invasive load decomposition technology and application ［D］. Guangzhou ： South China University of Technology ， 2018 .

HOLMEGAARD E ， BAUN KJAERGAARD M . NILM in an industrial setting： a load characterization and algorithm evaluation ［C］// 2016 IEEE International Conference on Smart Computing （SMARTCOMP）， May 18 - 20 ， 2016 ， St . Louis， USA.

YI S H ， YIN X D ， DIAO Y L ， et al . A new event-detection method based on composite windows in NILM for industrial settings ［C］// 2019 IEEE Sustainable Power and Energy Conference （ISPEC）， November 21 - 23 ， 2019 ， Beijing， China.

张小龙 . 大数据环境下用户用电行为分析的研究［D］. 北京：华北电力大学， 2017 .

ZHANG Xiaolong . Research on power user behavior analysis in big data ［D］. Beijing ： North China Electric Power University ， 2017 .

郭涛，马林东，葛智平，等 . 关于高耗能大工业用户提高大规模风电消纳能力的研究［J］. 工业仪表与自动化装置， 2013 （ 5 ）： 17 - 19 .

GUO Tao ， MA Lindong ， GE Zhiping ， et al . Research on high-energy consuming large industry consumers for large-scale wind power integration improvement ［J］. Industrial Instrumentation & Automation ， 2013 （ 5 ）： 17 - 19 .

涂夏哲，徐箭，廖思阳，等 . 考虑过程控制的钢铁工业负荷用能行为分析与功率特性建模［J］. 电力系统自动化， 2018 ， 42 （ 2 ）： 114 - 120 .

TU Xiazhe ， XU Jian ， LIAO Siyang ， et al . Process controlling based energy consumption behavior analysis and power characteristic modeling for iron and steel industry ［J］. Automation of Electric Power Systems ， 2018 ， 42 （ 2 ）： 114 - 120 .

赵加佩 . 铁矿石烧结过程的数值模拟与试验验证［D］. 杭州：浙江大学， 2012 .

ZHAO Jiapei . Numerical simulation and experimental verification of iron ore sintering process ［D］. Hangzhou ： Zhejiang University ， 2012 .

武昕，韩璐，韩笑，等 . 欠定分离机制下基于特征滤波的居民负荷非侵入辨识算法［J］. 电力系统自动化， 2017 ， 41 （ 20 ）： 118 - 125 .

WU Xin ， HAN Lu ， HAN Xiao ， et al . Feature filtering based non-intrusive identification algorithm for residential load in underdetermined separation mechanism ［J］. Automation of Electric Power Systems ， 2017 ， 41 （ 20 ）： 118 - 125

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Non-intrusive Load Identification by Combined Support Vector Machine Based on Structured Characteristic Spectrum

一种适用于非侵入式负荷监测的暂态事件检测算法

Precise Peak-shaving Strategy at Demand Side Considering Response Reliability and Economy

Economic Dispatch Model Considering Production Process of Energy-Intensive Industrial Load Under Demand Response

Non-cooperative Game Based Strategy for Energy-Intensive Industrial Load Participating in Peak-regulation Demand

Related Author

Meng YAN

Yifan GUO

Kaiyan HUANG

Dian JIAO

NIU Lulu

JIA Hongjie

MA Peng

QI Jun

Related Institution

Beijing Electric Power Economic Research Institute Co., Ltd.

Tianjin University

Hebi Colledge of Vocation and Technology

School of Electrical and Electronic Engineering, Huazhong University of Science and Technology

Alxa Power Supply Company of Inner Mongolia Electric Power (Group) Co., Ltd.

⁰