Detection and identification of non-technical loss based on electricity consumption curve and deep learning

Non-technical loss in power grid not only has a significant impact on the economic benefits of the power company, but also poses a serious threat to power quality and operational safety of the power system. In addition, measures taken by malicious users to seek profits grow in complexity, resulting...

Full description

Saved in:
Bibliographic Details
Main Authors: WANG Yunjing, XIAO Keyu, QU Zhengwei, HAN Xiaoming, DONG Haiyan, Popov Maxim Georgievitch
Format: Article
Language:zho
Published: Harbin Jinhe Electrical Measurement & Instrumentation Magazine Publishing Co., Ltd. 2025-06-01
Series:Diance yu yibiao
Subjects:
Online Access:http://www.emijournal.net/dcyyb/ch/reader/create_pdf.aspx?file_no=20220902008&flag=1&journal_id=dcyyb&year_id=2025
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849472988117729280
author WANG Yunjing
XIAO Keyu
QU Zhengwei
HAN Xiaoming
DONG Haiyan
Popov Maxim Georgievitch
author_facet WANG Yunjing
XIAO Keyu
QU Zhengwei
HAN Xiaoming
DONG Haiyan
Popov Maxim Georgievitch
author_sort WANG Yunjing
collection DOAJ
description Non-technical loss in power grid not only has a significant impact on the economic benefits of the power company, but also poses a serious threat to power quality and operational safety of the power system. In addition, measures taken by malicious users to seek profits grow in complexity, resulting in traditional detection methods gradually falling to limitation. Implementation means for non-technical loss based on electricity consumption curve are studied and tampering strategies used to generate false data are summarized. Behavior features of power users are extracted from the electricity consumption curve and associated with the results of electrical tampering implementation by bidirectional long short-term memory network. Finally, a multi-level neural network architecture is designed and deep learning is utilized to solve the multiclass classification problem of the feature sequences. Simulation based on actual power consumption dataset of a certain area shows that the research content can realize an effective detection of non-technical loss as well as identification of specific tampering strategies.
format Article
id doaj-art-c9836eb8a65945cc9bb9bf016863e22e
institution Kabale University
issn 1001-1390
language zho
publishDate 2025-06-01
publisher Harbin Jinhe Electrical Measurement & Instrumentation Magazine Publishing Co., Ltd.
record_format Article
series Diance yu yibiao
spelling doaj-art-c9836eb8a65945cc9bb9bf016863e22e2025-08-20T03:24:21ZzhoHarbin Jinhe Electrical Measurement & Instrumentation Magazine Publishing Co., Ltd.Diance yu yibiao1001-13902025-06-0162620221110.19753/j.issn1001-1390.2025.06.0221001-1390(2025)06-0202-10Detection and identification of non-technical loss based on electricity consumption curve and deep learningWANG Yunjing0XIAO Keyu1QU Zhengwei2HAN Xiaoming3DONG Haiyan4Popov Maxim Georgievitch5Institute of Electrical Engineering, Yanshan University, Qinhuangdao 066004, Hebei, ChinaInstitute of Electrical Engineering, Yanshan University, Qinhuangdao 066004, Hebei, ChinaInstitute of Electrical Engineering, Yanshan University, Qinhuangdao 066004, Hebei, ChinaInstitute of Electrical Engineering, Yanshan University, Qinhuangdao 066004, Hebei, ChinaInstitute of Electrical Engineering, Yanshan University, Qinhuangdao 066004, Hebei, ChinaInstitute of Energy, Peter the Great St. Petersburg Polytechnic University, St. Petersburg 195251, RussiaNon-technical loss in power grid not only has a significant impact on the economic benefits of the power company, but also poses a serious threat to power quality and operational safety of the power system. In addition, measures taken by malicious users to seek profits grow in complexity, resulting in traditional detection methods gradually falling to limitation. Implementation means for non-technical loss based on electricity consumption curve are studied and tampering strategies used to generate false data are summarized. Behavior features of power users are extracted from the electricity consumption curve and associated with the results of electrical tampering implementation by bidirectional long short-term memory network. Finally, a multi-level neural network architecture is designed and deep learning is utilized to solve the multiclass classification problem of the feature sequences. Simulation based on actual power consumption dataset of a certain area shows that the research content can realize an effective detection of non-technical loss as well as identification of specific tampering strategies.http://www.emijournal.net/dcyyb/ch/reader/create_pdf.aspx?file_no=20220902008&flag=1&journal_id=dcyyb&year_id=2025non-technical lossdeep learningelectricity consumption curvebidirectional long short-term memorymulticlass classification problem
spellingShingle WANG Yunjing
XIAO Keyu
QU Zhengwei
HAN Xiaoming
DONG Haiyan
Popov Maxim Georgievitch
Detection and identification of non-technical loss based on electricity consumption curve and deep learning
Diance yu yibiao
non-technical loss
deep learning
electricity consumption curve
bidirectional long short-term memory
multiclass classification problem
title Detection and identification of non-technical loss based on electricity consumption curve and deep learning
title_full Detection and identification of non-technical loss based on electricity consumption curve and deep learning
title_fullStr Detection and identification of non-technical loss based on electricity consumption curve and deep learning
title_full_unstemmed Detection and identification of non-technical loss based on electricity consumption curve and deep learning
title_short Detection and identification of non-technical loss based on electricity consumption curve and deep learning
title_sort detection and identification of non technical loss based on electricity consumption curve and deep learning
topic non-technical loss
deep learning
electricity consumption curve
bidirectional long short-term memory
multiclass classification problem
url http://www.emijournal.net/dcyyb/ch/reader/create_pdf.aspx?file_no=20220902008&flag=1&journal_id=dcyyb&year_id=2025
work_keys_str_mv AT wangyunjing detectionandidentificationofnontechnicallossbasedonelectricityconsumptioncurveanddeeplearning
AT xiaokeyu detectionandidentificationofnontechnicallossbasedonelectricityconsumptioncurveanddeeplearning
AT quzhengwei detectionandidentificationofnontechnicallossbasedonelectricityconsumptioncurveanddeeplearning
AT hanxiaoming detectionandidentificationofnontechnicallossbasedonelectricityconsumptioncurveanddeeplearning
AT donghaiyan detectionandidentificationofnontechnicallossbasedonelectricityconsumptioncurveanddeeplearning
AT popovmaximgeorgievitch detectionandidentificationofnontechnicallossbasedonelectricityconsumptioncurveanddeeplearning