RESEARCH PAPER
Reliability-Oriented Diagnosis of Non-Technical Losses in Electricity Distribution Networks Using Real AMR Data
1
Department of Electrical and Electronics Engineering, Dicle University, Turkey
2
AMR Systems Engineer, DICLE ELECTRIC DISTRIBUTION INC., Turkmenistan
These authors had equal contribution to this work
A – Conceptualization; B – Methodology; C – Software; D – Validation; E – Formal analysis; F – Investigation; G – Resources; H – Data curation; I – Writing – original draft; J – Writing – review & editing; K – Visualization; L – Supervision; M – Project administration; N – Funding acquisition
Submission date: 2026-04-27
Final revision date: 2026-06-17
Acceptance date: 2026-07-28
Online publication date: 2026-08-13
Corresponding author
Hüseyin Acar
Department of Electrical and Electronics Engineering, Dicle University, 21100, Diyarbakır, Turkey
Department of Electrical and Electronics Engineering, Dicle University, 21100, Diyarbakır, Turkey
KEYWORDS
TOPICS
ABSTRACT
Non-technical losses in electricity distribution networks constitute a critical operational risk that affects utility revenue, system reliability, monitoring accuracy, and field inspection efficiency. This study presents an expert-assisted hybrid diagnostic framework using real AMR data from 951 subscribers in the Dicle distribution region. The data were standardized to hourly resolution, and six expert rules were used to generate reference risk labels under limited field-verified annotations. After undersampling, a balanced dataset consisting of 304 risky and 304 clean subscribers was constructed, and Random Forest, LSTM, and CNN models were comparatively evaluated. The Random Forest model achieved 96.27% accuracy, 0.9952 AUC, 96.97% precision, 95.52% recall, and a 96.24% F1-score, outperforming LSTM (91.52% accuracy) and CNN (88.00% accuracy). These findings show that the proposed framework provides an effective reliability-oriented decision-support tool for diagnostics and risk-based field inspection planning in smart distribution networks.
REFERENCES (40)
1.
Adil M, Javaid N, Qasim U, Ullah I, Shafiq M, Choi JG. LSTM and bat-based RUSBoost approach for electricity theft detection. Applied Sciences 2020; 10(12): 4378. https://doi.org/10.3390/app101....
2.
Chandel P, Thakur T, Sawle BA, Sharma R. Power theft: Major cause of non technical losses in Indian distribution sector. 2016 IEEE 7th Power India International Conference (PIICON), p. 1-6. https://doi.org/10.1109/POWERI....
3.
Yang Z, Wei J, Wei X, Pan J, Jiang W, Wei H. A review of cybersecurity and non-technical loss model in the smart grid. 2025 CAA Symposium on Fault Detection, Supervision, and Safety for Technical Processes (SAFEPROCESS), p. 1-6. https://doi.org/10.1109/SAFEPR....
4.
Lepolesa LJ, Achari S, Cheng L. Electricity theft detection in smart grids based on deep neural network. IEEE Access 2022; 10: 39638-39655. https://doi.org/10.1109/ACCESS....
5.
Depuru SSSR, Wang L, Devabhaktuni V. Electricity theft: Overview, issues, prevention and a smart meter based approach to control theft. Energy policy 2011; 39(2): 1007-1015. https://doi.org/10.1016/j.enpo....
6.
Xia X, Xiao Y, Liang W, Cui J. Detection methods in smart meters for electricity thefts: A survey. Proceedings of the IEEE 2022; 110(2): 273-319. https://doi.org/10.1109/JPROC.....
7.
Anas M, Javaid N, Mahmood A, Raza SM, Qasim U, Khan ZA. Minimizing electricity theft using smart meters in AMI. 2012 Seventh International conference on P2P, parallel, grid, cloud and internet computing, p. 176-182. IEEE. https://doi.org/10.1109/3PGCIC....
8.
Chuwa MG, Wang F. A review of non-technical loss attack models and detection methods in the smart grid. Electric Power Systems Research 2021; 199: 107415. https://doi.org/10.1016/j.epsr....
9.
Buzau MM, Tejedor-Aguilera J, Cruz-Romero P, Gómez-Expósito A. Detection of non-technical losses using smart meter data and supervised learning. IEEE Transactions on Smart Grid 2018; 10(3): 2661-2670. https://doi.org/10.1109/TSG.20....
10.
Sahoo S, Nikovski D, Muso T, Tsuru K. Electricity theft detection using smart meter data. 2015 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), p. 1-5, IEEE. https://doi.org/10.1109/ISGT.2....
11.
Khan ZA, Adil M, Javaid N, Saqib MN, Shafiq M, Choi JG. Electricity theft detection using supervised learning techniques on smart meter data. Sustainability 2020; 12(19): 8023. https://doi.org/10.3390/su1219....
12.
Ahmad T. Non-technical loss analysis and prevention using smart meters. Renewable and Sustainable Energy Reviews 2017; 72: 573-589. https://doi.org/10.1016/j.rser....
13.
Han W, Xiao Y. A novel detector to detect colluded non-technical loss frauds in smart grid. Computer Networks 2017; 117: 19-31. https://doi.org/10.1016/j.comn....
14.
Haq EU, Pei C, Zhang R, Jianjun H, Ahmad F. Electricity-theft detection for smart grid security using smart meter data: A deep-CNN based approach. Energy Reports 2023; 9: 634-643. https://doi.org/10.1016/j.egyr....
15.
Pengwah AB, Razzaghi R, Andrew LL. Model-less non-technical loss detection using smart meter data. IEEE Transactions on Power Delivery 2023; 38(5): 3469-3479. https://doi.org/10.1109/TPWRD.....
16.
Han W, Xiao Y. NFD: A practical scheme to detect non-technical loss fraud in smart grid. 2014 IEEE International Conference on Communications (ICC), p. 605-609. IEEE. https://doi.org/10.1109/ICC.20....
17.
Faqishafyee NJ, Sadiq EH, Taha HM. Mitigating non-technical losses and electricity theft through smart meters: A case study of the Akre district power distribution network. Journal of Intelligent Systems and Control 2024; 3(3): 135-151. https://doi.org/10.56578/jisc0....
18.
Seepromting K, Rajitroj N, Michel J, Surawanitkun C. Strategic Smart Meter Deployment in Power Distribution: Leveraging Machine Learning and Economic Evaluation for Non-Technical Loss Reduction. 2025 60th International Universities Power Engineering Conference (UPEC), p. 1-7, IEEE. https://doi.org/10.1109/UPEC65....
19.
Viegas JL, Esteves PR, Melicio R, Mendes VMF, Vieira SM. Solutions for detection of non-technical losses in the electricity grid: A review. Renewable and Sustainable Energy Reviews 2017; 80: 1256-1268. https://doi.org/10.1016/j.rser....
20.
Shah AL, Mesbah W, Al-Awami AT. An algorithm for accurate detection and correction of technical and nontechnical losses using smart metering. IEEE Transactions on Instrumentation and Measurement 2020; 69(11): 8809-8820. https://doi.org/10.1109/TIM.20....
21.
Kim JY, Hwang YM, Sun YG, Sim I, Kim DI, Wang X. Detection for non-technical loss by smart energy theft with intermediate monitor meter in smart grid. IEEE Access 2019; 7: 129043-129053. https://doi.org/10.1109/ACCESS....
22.
Raggi LM, Trindade FC, Cunha VC, Freitas W. Non-technical loss identification by using data analytics and customer smart meters. IEEE Transactions on Power Delivery 2020; 35(6): 2700-2710. https://doi.org/10.1109/TPWRD.....
23.
Gao Y, Foggo B, Yu N. A physically inspired data-driven model for electricity theft detection with smart meter data. IEEE Transactions on Industrial Informatics 2019; 15(9): 5076-5088. https://doi.org/10.1109/TII.20....
24.
Otchere-Appiah G, Takahashi S, Yeboah MS, Yoshida Y. The impact of smart prepaid metering on non-technical losses in Ghana. Energies 2021; 14(7): 1852. https://doi.org/10.3390/en1407....
25.
Kara Y, Aksu A. Tüketicilerde Kaçak Elektrik Kullanımının Akıllı Sayaç Verisi Üzerinden Gradyan Artırmalı Karar Ağacı Tabanlı Makine Öğrenmesi Yöntemleriyle Tespiti. Journal of Investigations on Engineering and Technology 2023; 6(1): 1-12. https://dergipark.org.tr/en/pu....
26.
Türk M, Haydaroglu C, Kılıç H. Machine learning-based detection of non-technical losses in power distribution networks. Firat University Journal of Experimental and Computational Engineering 2025; 4(1): 192-205. https://doi.org/10.62520/fujec....
27.
Kocaman B. Teknik olmayan enerji kayıplarının azaltılmasında PLC sayaçlarının önemi. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi 2018; 7(2): 220-230. https://doi.org/10.17798/bitli....
28.
Çelikpençe, M. Elektrik Dağıtım Şebekelerinde Teknik Olmayan Kayıp Kaçakların Makina Öğrenmesi İle Tespiti, PhD Thesis, İstanbul Sabahattin Zaim Üniversitesi 2023.
29.
Depuru SSSR, Wang L, Devabhaktuni V. Support vector machine based data classification for detection of electricity theft. 2011 IEEE/PES Power Systems Conference and Exposition, p. 1-8. IEEE. https://doi.org/10.1109/PSCE.2....
30.
Villar-Rodriguez E, Del Ser J, Oregi I, Bilbao MN, Gil-Lopez S. Detection of non-technical losses in smart meter data based on load curve profiling and time series analysis. Energy 2017; 137: 118-128. https://doi.org/10.1016/j.ener....
31.
Glauner P, Meira, JA, Valtchev, P, State R, Bettinger F. The challenge of non-technical loss detection using artificial intelligence: A survey. International journal of computational intelligence systems 2017; 10(1): 760-775. https://doi.org/10.2991/ijcis.....
32.
Emmanuel T, Maupong T, Mpoeleng D, Semong T, Mphago B, Tabona O. A survey on missing data in machine learning. Journal of Big data 2021; 8(1): 140. https://doi.org/10.1186/s40537....
33.
Hou Z, Liu J. Enhancing smart grid sustainability: using advanced hybrid machine learning techniques while considering multiple influencing factors for imputing missing electric load data. Sustainability 2024; 16(18): 8092. https://doi.org/10.3390/su1618....
34.
Jung S, Moon J, Park S, Rho S, Baik SW, Hwang E. Bagging ensemble of multilayer perceptrons for missing electricity consumption data imputation. Sensors 2020; 20(6): 1772. https://doi.org/10.3390/s20061....
35.
Gardian H, Beck JP, Koch M, Kunze R, Muschner C, Hülk L, Bucksteeg M. Data harmonisation for energy system analysis–Example of multi-model experiments. Renewable and Sustainable Energy Reviews 2022; 162: 112472. https://doi.org/10.1016/j.rser....
36.
Nagi J, Yap KS, Tiong SK, Ahmed SK, Mohamad M. Nontechnical loss detection for metered customers in power utility using support vector machines. IEEE transactions on Power Delivery 2009; 25(2): 1162-1171. https://doi.org/10.1109/TPWRD.....
37.
Aydın EY, Önal K, Haydaroğlu C, Kılıç H, Yıldırım Ö, Katar O, Erdoğan H. A Novel Scenario-Based Comparative Framework for Short-and Medium-Term Solar PV Power Forecasting Using Deep Learning Models. Applied Sciences 2025; 15(24): 12965. https://doi.org/10.3390/app152....
38.
Abro, SA, Laghari, JA, Memon, SA, Khan TA, Memon I, Nasir H, Fatima, K. Non-technical loss detection in power distribution networks using machine learning. Scientific Reports 2025; 15(1): 36189. https://doi.org/10.1038/s41598....
39.
Saeed MS, Mustafa MW, Sheikh UU, Jumani TA, Mirjat NH. Ensemble bagged tree based classification for reducing non-technical losses in multan electric power company of Pakistan. Electronics 2019; 8(8): 860. https://doi.org/10.3390/electr....
40.
Ghori KM, Imran M, Nawaz A, Abbasi RA, Ullah A, Szathmary, L. Performance analysis of machine learning classifiers for non-technical loss detection. Journal of Ambient Intelligence and Humanized Computing 2023; 14(11): 15327-15342 https://doi.org/10.1007/s12652....
| eISSN: | 2956-3860 |
| ISSN: | 1507-2711 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
