基于DTW算法与稳态电流波形的非侵入式负荷辨识方法

QI Bing

您当前的位置：

首页 >

文章列表页 >

基于DTW算法与稳态电流波形的非侵入式负荷辨识方法

更新时间：2025-08-13

- 基于DTW算法与稳态电流波形的非侵入式负荷辨识方法
- Automation of Electric Power Systems Vol. 42, Issue 3, Pages: 70-76(2018)
- 作者机构：
  
  华北电力大学电气与电子工程学院,北京市,102206
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2018
- 稿件说明：
移动端阅览
QI Bing. [J]. Automation of electric power systems, 2018, 42(3): 70-76.
DOI：

QI Bing. [J]. Automation of electric power systems, 2018, 42(3): 70-76. DOI：

摘要

非侵入家用负荷识别技术可以指导家庭用户合理安排用电，提高用能效率，同时也为电力部门提供家庭用电的数据支持，有利于了解负荷用电规律及趋势，完善电力规划。由于家庭用户用电负荷的稳态特征值存在相似和无规律的问题，现有的方法多采用高级算法对所有的用电负荷组合进行训练。针对现有采用负荷稳态特征值方法进行识别所存在的不足，考虑到家用负荷稳态波形具有独特性和叠加性，提出了一种利用动态时间弯曲(DTW)算法计算与模版库波形的距离来识别家用负荷的辨识方法。首先，建立负荷稳态波形模版库；然后，在电压满足一定条件的情况下，测量家庭用户电流的稳态波形；最后，利用DTW算法计算出最小距离进行识别。

Abstract

Non-intrusive household load identification technology can guide reasonable arrangement of household users

improve energy efficiency

and provide domestic electric data support to the power sector

which is conducive to understand the load electricity law and trends for improving power planning. As steady-state characteristic values of electric load for home users are similar and irregular

most existing methods need to use advanced algorithms to train all the combinations of electrical load. Faced with the existing problems with the steady load characteristic value method and considering the unique characteristics and the superposition of steady-state waveform of domestic load

a method based on the dynamic time warping(DTW)algorithm and template library waveform is proposed to identify the household load. First of all

a template library of steady-state waveform is established. Then

under certain voltage conditions

the current steady-state waveform is measured. Finally

the DTW algorithm is used to calculate the minimum distance for identification.

关键词

Keywords

references

Views

3154

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Identification Method for Type-Ⅲ Industrial and Commercial Load Considering Identification Result Continuity

Non-intrusive Load Identification Algorithm Based on Feature Fusion and Deep Learning

Related Author

Jing DUAN

Yong LI

Zhenyu ZHANG

Weiwei LI

Lin JIANG

Lei LI

Shouxiang WANG

Luyang GUO

Related Institution

College of Electrical and Information Engineering, Hunan University

Changsha Xinao Changran Energy Development Co., Ltd.

Department of Electrical Engineering and Electronics, University of Liverpool

Changsha Xinao Xiangjiang New Energy Development Co., Ltd.

(Key Laboratory of the Ministry of Education on Smart Power Grids (Tianjin University)

⁰