Machine Learning-Based Detection of Non-Technical Losses in Power Distribution Networks

This study focuses on the serious sustainability and reliability problem caused by non-technical losses (NTL) due to energy theft in electrical grid systems. In order to reduce these losses, we propose an artificial intelligence-based approach that utilizes deep learning architectures in the detecti...

Full description

Saved in:
Bibliographic Details
Main Authors: Mahmut Türk, Heybet Kılıç, Cem Haydaroglu
Format: Article
Language:English
Published: Firat University 2025-02-01
Series:Firat University Journal of Experimental and Computational Engineering
Subjects:
Online Access:https://dergipark.org.tr/tr/download/article-file/4220967
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850077022335795200
author Mahmut Türk
Heybet Kılıç
Cem Haydaroglu
author_facet Mahmut Türk
Heybet Kılıç
Cem Haydaroglu
author_sort Mahmut Türk
collection DOAJ
description This study focuses on the serious sustainability and reliability problem caused by non-technical losses (NTL) due to energy theft in electrical grid systems. In order to reduce these losses, we propose an artificial intelligence-based approach that utilizes deep learning architectures in the detection of different types of leakage (voltage leakage, current leakage and voltage-current leakage). Unlike the studies in the literature, the data set is converted into two-dimensional matrices and analyzed with today's popular approaches, Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) models; CNN surpassed LSTM's 64.17% accuracy rate with 97.50% accuracy rate. In addition, from the classical methods, 67.5 accuracy rate was obtained with the k-Nearest Neighbor (k-NN) method and 62.25 accuracy rate was obtained with the Support Vector Machines (SVM) method. Comparisons with such traditional methods have revealed the superiority of CNN in determining complex leakage patterns. The findings highlight the potential of CNN to be used as a reliable tool for real-time theft detection by integrating it into smart grid systems. Future research will aim to further increase the scalability and effectiveness of this solution by examining the integration of real-time data and hybrid model approaches.
format Article
id doaj-art-9fefc2de907240a2ac5cee7029076ab0
institution DOAJ
issn 2822-2881
language English
publishDate 2025-02-01
publisher Firat University
record_format Article
series Firat University Journal of Experimental and Computational Engineering
spelling doaj-art-9fefc2de907240a2ac5cee7029076ab02025-08-20T02:45:53ZengFirat UniversityFirat University Journal of Experimental and Computational Engineering2822-28812025-02-014119220510.62520/fujece.15516011769Machine Learning-Based Detection of Non-Technical Losses in Power Distribution NetworksMahmut Türk0https://orcid.org/0000-0002-5733-6854Heybet Kılıç1https://orcid.org/0000-0002-6119-0886Cem Haydaroglu2https://orcid.org/0000-0003-0830-5530DICLE UNIVERSITYDICLE UNIVERSITYDİCLE ÜNİVERSİTESİThis study focuses on the serious sustainability and reliability problem caused by non-technical losses (NTL) due to energy theft in electrical grid systems. In order to reduce these losses, we propose an artificial intelligence-based approach that utilizes deep learning architectures in the detection of different types of leakage (voltage leakage, current leakage and voltage-current leakage). Unlike the studies in the literature, the data set is converted into two-dimensional matrices and analyzed with today's popular approaches, Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) models; CNN surpassed LSTM's 64.17% accuracy rate with 97.50% accuracy rate. In addition, from the classical methods, 67.5 accuracy rate was obtained with the k-Nearest Neighbor (k-NN) method and 62.25 accuracy rate was obtained with the Support Vector Machines (SVM) method. Comparisons with such traditional methods have revealed the superiority of CNN in determining complex leakage patterns. The findings highlight the potential of CNN to be used as a reliable tool for real-time theft detection by integrating it into smart grid systems. Future research will aim to further increase the scalability and effectiveness of this solution by examining the integration of real-time data and hybrid model approaches.https://dergipark.org.tr/tr/download/article-file/4220967teknik olmayan kayıplar (tok)kaçak elektrik tespitiderin öğrenmekonvolüsyonel sinir ağı (cnn)akıllı şebekenon-technical losses (ntl)electricity theft detectiondeep learningconvolutional neural network(cnn)smartgrid
spellingShingle Mahmut Türk
Heybet Kılıç
Cem Haydaroglu
Machine Learning-Based Detection of Non-Technical Losses in Power Distribution Networks
Firat University Journal of Experimental and Computational Engineering
teknik olmayan kayıplar (tok)
kaçak elektrik tespiti
derin öğrenme
konvolüsyonel sinir ağı (cnn)
akıllı şebeke
non-technical losses (ntl)
electricity theft detection
deep learning
convolutional neural network(cnn)
smartgrid
title Machine Learning-Based Detection of Non-Technical Losses in Power Distribution Networks
title_full Machine Learning-Based Detection of Non-Technical Losses in Power Distribution Networks
title_fullStr Machine Learning-Based Detection of Non-Technical Losses in Power Distribution Networks
title_full_unstemmed Machine Learning-Based Detection of Non-Technical Losses in Power Distribution Networks
title_short Machine Learning-Based Detection of Non-Technical Losses in Power Distribution Networks
title_sort machine learning based detection of non technical losses in power distribution networks
topic teknik olmayan kayıplar (tok)
kaçak elektrik tespiti
derin öğrenme
konvolüsyonel sinir ağı (cnn)
akıllı şebeke
non-technical losses (ntl)
electricity theft detection
deep learning
convolutional neural network(cnn)
smartgrid
url https://dergipark.org.tr/tr/download/article-file/4220967
work_keys_str_mv AT mahmutturk machinelearningbaseddetectionofnontechnicallossesinpowerdistributionnetworks
AT heybetkılıc machinelearningbaseddetectionofnontechnicallossesinpowerdistributionnetworks
AT cemhaydaroglu machinelearningbaseddetectionofnontechnicallossesinpowerdistributionnetworks