Robust Energy Theft Detection in Smart Distribution Method Using a Data-driven Method

Olushola Akintola; Babatunde Adetokun; Oghenewvogaga Oghorada

doi:doi:10.11648/j.jeee.20261401.15

Research Article |

| Peer-Reviewed

Robust Energy Theft Detection in Smart Distribution Method Using a Data-driven Method

Olushola Akintola^*

, Babatunde Adetokun

, Oghenewvogaga Oghorada

Published in Journal of Electrical and Electronic Engineering (Volume 14, Issue 1)

Received: 21 January 2026 Accepted: 31 January 2026 Published: 11 February 2026

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

Energy theft poses a significant challenge to modern power systems, leading to economic losses, reduced efficiency, and compromised reliability in smart grids. Detecting such anomalies requires robust, scalable analytical frameworks that can accurately distinguish normal consumption, marginally increased usage, and patterns indicative of electricity theft across diverse operating conditions. This study investigates the application of machine learning techniques for energy theft detection using a dataset of recorded consumption values. Two numerical features, energy used by theft in per unit and normal energy, were employed as predictors. At the same time, the target variable comprises three categorical conditions: Theft detected, Normal, and Energy slightly higher. Four classifiers were implemented and compared: Decision Tree, Support Vector Machine (SVM) with Error-Correcting Output Codes (ECOC), Random Forest, and k-Nearest Neighbors (kNN). The models were trained and evaluated using MATLAB with an 80/20 hold-out validation approach. Performance was assessed using accuracy metrics and confusion matrices. Results demonstrated that SVM achieved the highest accuracy (86.67%), followed closely by Random Forest (83.33%) and kNN (82.33%), while Decision Tree yielded the lowest accuracy (73.33%). Confusion matrix analysis showed that all classifiers detected theft-based cases with high accuracy, whereas most classification errors arose from overlap and ambiguity between normal consumption and elevated energy usage conditions. The study adds to the expanding literature on data-driven energy management by providing practical evidence of how machine-learning techniques can strengthen grid security, minimize financial losses, and enhance overall operational efficiency.

Published in	Journal of Electrical and Electronic Engineering (Volume 14, Issue 1)
DOI	10.11648/j.jeee.20261401.15
Page(s)	46-53
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2026. Published by Science Publishing Group

Keywords

Distribution Network, Energy Theft, Energy Theft Detection, Machine Learning

References

[1]	F. Dewangan, A. Y. Abdelaziz, and M. Biswal, “Load Forecasting Models in Smart Grid Using Smart Meter Information: A Review,” Energies. 2023, vol. 16, pp. 1–55. https://doi.org/10.3390/en16031404
[2]	J. Chen, Y. A. Nanehkaran, W. Chen, Y. Liu, and D. Zhang, “Data-driven intelligent method for detection of electricity theft,” International Journal of Electrical Power & Energy Systems. 2023, vol. 148, p. 108948. https://doi.org/10.1016/j.ijepes.2023.108948
[3]	R. Razavi and M. Fleury, “Socio-economic predictors of electricity theft in developing countries: An Indian case study,” Energy for Sustainable Development. 2019, vol. 49, pp. 1–10. https://doi.org/10.1016/j.esd.2018.12.006
[4]	C. L. Athanasiadis, T. A. Papadopoulos, G. C. Kryonidis, and D. I. Doukas, “A review of distribution network applications based on smart meter data analytics,” Renewable and Sustainable Energy Reviews. 2024, vol. 191, p. 114151. https://doi.org/10.1016/j.rser.2023.114151
[5]	O. Yakubu, N. Babu C., and O. Adjei, “Electricity theft: Analysis of the underlying contributory factors in Ghana,” Energy Policy. 2018, vol. 123, pp. 611–618. https://doi.org/10.1016/j.enpol.2018.09.019
[6]	S. Kim et al., “Data-Driven Approaches for Energy Theft Detection: A Comprehensive Review,” Energies. 2024, 17(12). https://doi.org/10.3390/en17123057
[7]	M. Z. Gunduz and R. Das, “Smart Grid Security: An Effective Hybrid CNN-Based Approach for Detecting Energy Theft Using Consumption Patterns,” Sensors. 2024, 24, 1148. https://doi.org/10.3390/s24041148
[8]	W. Chen, K. Yang, Z. Yu, Y. Shi, and C. L. P. Chen, “A survey on imbalanced learning: latest research, applications and future directions,” Artif. Intell. Rev. 2024, 57(6), pp. 1-51. https://doi.org/10.1007/s10462-024-10759-6
[9]	X. Gong, B. Tang, R. Zhu, W. Liao, and L. Song, “Data Augmentation for Electricity Theft Detection Using Conditional Variational Auto-Encoder,” Energies. 2020, 13(17), pp. 1-14. https://doi.org/10.3390/en13174291
[10]	S. Chandrasekaran, “Multiobjective optimal power flow using interior search algorithm: A case study on a real-time electrical network,” Comput. Intell. 2020, 36(3), pp. 1078–1096. https://doi.org/10.1111/coin.12312
[11]	H. Shahinzadeh, A. Mahmoudi, J. Moradi, H. Nafisi, E. Kabalci, and M. Benbouzid, “Anomaly Detection and Resilience-Oriented Countermeasures against Cyberattacks in Smart Grids,” Proceedings - 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS), Tehran, Iran, 2021, pp. 1-7. https://doi.org/10.1109/ICSPIS54653.2021.9729386
[12]	S. K. Gunturi and D. Sarkar, “Ensemble machine learning models for the detection of energy theft,” Electric Power Systems Research. 2021, vol. 192, p. 106904. https://doi.org/10.1016/j.epsr.2020.106904
[13]	A. Hirsi et al., “HSF: A Hybrid SVM-RF Machine Learning Framework for Dual-Plane DDoS Detection and Mitigation in Software-Defined Networks,” IEEE Access. 2025, vol. 13, pp. 112303–112323. https://doi.org/10.1109/ACCESS.2025.3583712
[14]	A. P. Taruna, G. Arisona, D. Irwanto, A. B. Bestari, and W. Juniawan, “Electricity Theft Detection Using Machine Learning in Traditional Meter Postpaid Residential Customers: A Case Study on State Electricity Company (PLN) Indonesia,” IEEE Access. 2025, vol. 13, pp. 7167–7191. https://doi.org/10.1109/ACCESS.2025.3526764
[15]	N. M. Elshennawy, D. M. Ibrahim, and A. M. Gab Allah, “An efficient electricity theft detection based on deep learning,” Scientific Reports. 2025 15(1), pp. 1-15, https://doi.org/10.1038/s41598-025-93140-z
[16]	Z. Jiang, X. Liu, and L. Zhang, “Wide and Deep Learning-Aided Nonlinear Equalizer for Coherent Optical Communication Systems,” Photonics. 2024, 11(2), p. 141. https://doi.org/10.3390/photonics11020141
[17]	V. K. Jaiswal, H. K. Singh, and K. Singh, “Arduino GSM-based Power Theft Detection and Energy Metering System,” 5th International Conference on Communication and Electronics Systems (ICCES), Coimbatore, India, 2020, pp. 448–452. https://doi.org/10.1109/ICCES48766.2020.9138085
[18]	E. Stracqualursi, A. Rosato, G. Di Lorenzo, M. Panella, and R. Araneo, “Systematic review of energy theft practices and autonomous detection through artificial intelligence methods,” Renewable and Sustainable Energy Reviews. 2023, vol. 184, p. 113544. https://doi.org/10.1016/j.rser.2023.113544
[19]	S. Zidi, A. Mihoub, S. Mian Qaisar, M. Krichen, and Q. Abu Al-Haija, “Theft detection dataset for benchmarking and machine learning based classification in a smart grid environment,” Journal of King Saud University - Computer and Information Sciences. 2023, 35(1), pp. 13–25. https://doi.org/10.1016/j.jksuci.2022.05.007
[20]	K. Fei, Q. Li, and C. Zhu, “Non-technical losses detection using missing values’ pattern and neural architecture search,” International Journal of Electrical Power & Energy Systems. 2022, vol. 134, p. 107410. https://doi.org/10.1016/j.ijepes.2021.107410
[21]	Y.-C. Tsao, D. Rahmalia, and J.-C. Lu, “Machine-learning techniques for enhancing electricity theft detection considering transformer reliability and supply interruptions,” Energy Reports, vol. 12, pp. 3048–3064, 2024. https://doi.org/10.1016/j.egyr.2024.08.068
[22]	I. Petrlik, P. Lezama, C. Rodriguez, R. Inquilla, J. Elizabeth Reyna-González, and R. Esparza, “Electricity Theft Detection using Machine Learning,” International Journal of Advanced Computer Science and Applications. 2022, 13(12), pp. 420–425, 2022. https://doi.org/10.14569/IJACSA.2022.0131251
[23]	N. G. Ezeji, K. I. Chibueze, and N. H. Nwobodo-Nzeribe, “Developing and Implementing an Artificial Intelligence (AI)-Driven System for Electricity Theft Detection,” ABUAD Journal of Engineering Research and Development (AJERD). 2024, 7(2), pp. 317–328. https://doi.org/10.53982/AJERD.2024.0702.31-J
[24]	S. A. Abro, G. L. Hua, J. A. Laghari, M. A. Bhayo, and A. A. Memon, “Machine learning-based electricity theft detection using support vector machines,” International Journal of Electrical and Computer Engineering (IJECE). 2024, 14(2), pp. 1240–1250. http://arxiv.org/abs/1809.03006

Cite This Article

Plain Text BibTeX RIS

APA Style

Akintola, O., Adetokun, B., Oghorada, O. (2026). Robust Energy Theft Detection in Smart Distribution Method Using a Data-driven Method. Journal of Electrical and Electronic Engineering, 14(1), 46-53. https://doi.org/10.11648/j.jeee.20261401.15

Copy | Download

ACS Style

Akintola, O.; Adetokun, B.; Oghorada, O. Robust Energy Theft Detection in Smart Distribution Method Using a Data-driven Method. J. Electr. Electron. Eng. 2026, 14(1), 46-53. doi: 10.11648/j.jeee.20261401.15

Copy | Download

AMA Style

Akintola O, Adetokun B, Oghorada O. Robust Energy Theft Detection in Smart Distribution Method Using a Data-driven Method. J Electr Electron Eng. 2026;14(1):46-53. doi: 10.11648/j.jeee.20261401.15

Copy | Download

@article{10.11648/j.jeee.20261401.15,
  author = {Olushola Akintola and Babatunde Adetokun and Oghenewvogaga Oghorada},
  title = {Robust Energy Theft Detection in Smart Distribution Method Using a Data-driven Method},
  journal = {Journal of Electrical and Electronic Engineering},
  volume = {14},
  number = {1},
  pages = {46-53},
  doi = {10.11648/j.jeee.20261401.15},
  url = {https://doi.org/10.11648/j.jeee.20261401.15},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.jeee.20261401.15},
  abstract = {Energy theft poses a significant challenge to modern power systems, leading to economic losses, reduced efficiency, and compromised reliability in smart grids. Detecting such anomalies requires robust, scalable analytical frameworks that can accurately distinguish normal consumption, marginally increased usage, and patterns indicative of electricity theft across diverse operating conditions. This study investigates the application of machine learning techniques for energy theft detection using a dataset of recorded consumption values. Two numerical features, energy used by theft in per unit and normal energy, were employed as predictors. At the same time, the target variable comprises three categorical conditions: Theft detected, Normal, and Energy slightly higher. Four classifiers were implemented and compared: Decision Tree, Support Vector Machine (SVM) with Error-Correcting Output Codes (ECOC), Random Forest, and k-Nearest Neighbors (kNN). The models were trained and evaluated using MATLAB with an 80/20 hold-out validation approach. Performance was assessed using accuracy metrics and confusion matrices. Results demonstrated that SVM achieved the highest accuracy (86.67%), followed closely by Random Forest (83.33%) and kNN (82.33%), while Decision Tree yielded the lowest accuracy (73.33%). Confusion matrix analysis showed that all classifiers detected theft-based cases with high accuracy, whereas most classification errors arose from overlap and ambiguity between normal consumption and elevated energy usage conditions. The study adds to the expanding literature on data-driven energy management by providing practical evidence of how machine-learning techniques can strengthen grid security, minimize financial losses, and enhance overall operational efficiency.},
 year = {2026}
}

Copy | Download

TY  - JOUR
T1  - Robust Energy Theft Detection in Smart Distribution Method Using a Data-driven Method
AU  - Olushola Akintola
AU  - Babatunde Adetokun
AU  - Oghenewvogaga Oghorada
Y1  - 2026/02/11
PY  - 2026
N1  - https://doi.org/10.11648/j.jeee.20261401.15
DO  - 10.11648/j.jeee.20261401.15
T2  - Journal of Electrical and Electronic Engineering
JF  - Journal of Electrical and Electronic Engineering
JO  - Journal of Electrical and Electronic Engineering
SP  - 46
EP  - 53
PB  - Science Publishing Group
SN  - 2329-1605
UR  - https://doi.org/10.11648/j.jeee.20261401.15
AB  - Energy theft poses a significant challenge to modern power systems, leading to economic losses, reduced efficiency, and compromised reliability in smart grids. Detecting such anomalies requires robust, scalable analytical frameworks that can accurately distinguish normal consumption, marginally increased usage, and patterns indicative of electricity theft across diverse operating conditions. This study investigates the application of machine learning techniques for energy theft detection using a dataset of recorded consumption values. Two numerical features, energy used by theft in per unit and normal energy, were employed as predictors. At the same time, the target variable comprises three categorical conditions: Theft detected, Normal, and Energy slightly higher. Four classifiers were implemented and compared: Decision Tree, Support Vector Machine (SVM) with Error-Correcting Output Codes (ECOC), Random Forest, and k-Nearest Neighbors (kNN). The models were trained and evaluated using MATLAB with an 80/20 hold-out validation approach. Performance was assessed using accuracy metrics and confusion matrices. Results demonstrated that SVM achieved the highest accuracy (86.67%), followed closely by Random Forest (83.33%) and kNN (82.33%), while Decision Tree yielded the lowest accuracy (73.33%). Confusion matrix analysis showed that all classifiers detected theft-based cases with high accuracy, whereas most classification errors arose from overlap and ambiguity between normal consumption and elevated energy usage conditions. The study adds to the expanding literature on data-driven energy management by providing practical evidence of how machine-learning techniques can strengthen grid security, minimize financial losses, and enhance overall operational efficiency.
VL  - 14
IS  - 1
ER  -

Copy | Download

Author Information

Olushola Akintola

Electrical and Electronics Engineering Department, Nile University of Nigeria, Abuja, Nigeria

Contact Email

http://orcid.org/0009-0009-3873-6316
Babatunde Adetokun

Electrical and Electronics Engineering Department, Nile University of Nigeria, Abuja, Nigeria

http://orcid.org/0000-0002-7175-7452
Oghenewvogaga Oghorada

Electrical and Electronics Engineering Department, Nile University of Nigeria, Abuja, Nigeria

http://orcid.org/0000-0001-7891-0256

Download PDF

Submit an Article

Sections

Plain Text BibTeX RIS

APA Style

Akintola, O., Adetokun, B., Oghorada, O. (2026). Robust Energy Theft Detection in Smart Distribution Method Using a Data-driven Method. Journal of Electrical and Electronic Engineering, 14(1), 46-53. https://doi.org/10.11648/j.jeee.20261401.15

Copy | Download

ACS Style

Akintola, O.; Adetokun, B.; Oghorada, O. Robust Energy Theft Detection in Smart Distribution Method Using a Data-driven Method. J. Electr. Electron. Eng. 2026, 14(1), 46-53. doi: 10.11648/j.jeee.20261401.15

Copy | Download

AMA Style

Akintola O, Adetokun B, Oghorada O. Robust Energy Theft Detection in Smart Distribution Method Using a Data-driven Method. J Electr Electron Eng. 2026;14(1):46-53. doi: 10.11648/j.jeee.20261401.15

Copy | Download

@article{10.11648/j.jeee.20261401.15,
  author = {Olushola Akintola and Babatunde Adetokun and Oghenewvogaga Oghorada},
  title = {Robust Energy Theft Detection in Smart Distribution Method Using a Data-driven Method},
  journal = {Journal of Electrical and Electronic Engineering},
  volume = {14},
  number = {1},
  pages = {46-53},
  doi = {10.11648/j.jeee.20261401.15},
  url = {https://doi.org/10.11648/j.jeee.20261401.15},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.jeee.20261401.15},
  abstract = {Energy theft poses a significant challenge to modern power systems, leading to economic losses, reduced efficiency, and compromised reliability in smart grids. Detecting such anomalies requires robust, scalable analytical frameworks that can accurately distinguish normal consumption, marginally increased usage, and patterns indicative of electricity theft across diverse operating conditions. This study investigates the application of machine learning techniques for energy theft detection using a dataset of recorded consumption values. Two numerical features, energy used by theft in per unit and normal energy, were employed as predictors. At the same time, the target variable comprises three categorical conditions: Theft detected, Normal, and Energy slightly higher. Four classifiers were implemented and compared: Decision Tree, Support Vector Machine (SVM) with Error-Correcting Output Codes (ECOC), Random Forest, and k-Nearest Neighbors (kNN). The models were trained and evaluated using MATLAB with an 80/20 hold-out validation approach. Performance was assessed using accuracy metrics and confusion matrices. Results demonstrated that SVM achieved the highest accuracy (86.67%), followed closely by Random Forest (83.33%) and kNN (82.33%), while Decision Tree yielded the lowest accuracy (73.33%). Confusion matrix analysis showed that all classifiers detected theft-based cases with high accuracy, whereas most classification errors arose from overlap and ambiguity between normal consumption and elevated energy usage conditions. The study adds to the expanding literature on data-driven energy management by providing practical evidence of how machine-learning techniques can strengthen grid security, minimize financial losses, and enhance overall operational efficiency.},
 year = {2026}
}

Copy | Download

TY  - JOUR
T1  - Robust Energy Theft Detection in Smart Distribution Method Using a Data-driven Method
AU  - Olushola Akintola
AU  - Babatunde Adetokun
AU  - Oghenewvogaga Oghorada
Y1  - 2026/02/11
PY  - 2026
N1  - https://doi.org/10.11648/j.jeee.20261401.15
DO  - 10.11648/j.jeee.20261401.15
T2  - Journal of Electrical and Electronic Engineering
JF  - Journal of Electrical and Electronic Engineering
JO  - Journal of Electrical and Electronic Engineering
SP  - 46
EP  - 53
PB  - Science Publishing Group
SN  - 2329-1605
UR  - https://doi.org/10.11648/j.jeee.20261401.15
AB  - Energy theft poses a significant challenge to modern power systems, leading to economic losses, reduced efficiency, and compromised reliability in smart grids. Detecting such anomalies requires robust, scalable analytical frameworks that can accurately distinguish normal consumption, marginally increased usage, and patterns indicative of electricity theft across diverse operating conditions. This study investigates the application of machine learning techniques for energy theft detection using a dataset of recorded consumption values. Two numerical features, energy used by theft in per unit and normal energy, were employed as predictors. At the same time, the target variable comprises three categorical conditions: Theft detected, Normal, and Energy slightly higher. Four classifiers were implemented and compared: Decision Tree, Support Vector Machine (SVM) with Error-Correcting Output Codes (ECOC), Random Forest, and k-Nearest Neighbors (kNN). The models were trained and evaluated using MATLAB with an 80/20 hold-out validation approach. Performance was assessed using accuracy metrics and confusion matrices. Results demonstrated that SVM achieved the highest accuracy (86.67%), followed closely by Random Forest (83.33%) and kNN (82.33%), while Decision Tree yielded the lowest accuracy (73.33%). Confusion matrix analysis showed that all classifiers detected theft-based cases with high accuracy, whereas most classification errors arose from overlap and ambiguity between normal consumption and elevated energy usage conditions. The study adds to the expanding literature on data-driven energy management by providing practical evidence of how machine-learning techniques can strengthen grid security, minimize financial losses, and enhance overall operational efficiency.
VL  - 14
IS  - 1
ER  -

Copy | Download