Detection of Non-Technical Losses in Electrical Metering Systems in Northern Lima Using Predictive Modeling and Business Intelligence

Dayanna Perez; Miguel Flores; Pedro Castaneda; Jose Santisteban; Alejandra Onate-Andino

doi:10.48084/etasr.14923

Authors

Dayanna Perez Faculty of Information Systems Engineering, Universidad Peruana de Ciencias Aplicadas, Lima, Peru
Miguel Flores Faculty of Information Systems Engineering, Universidad Peruana de Ciencias Aplicadas, Lima, Peru
Pedro Castaneda Faculty of Systems Engineering and Electrical Mechanics, Universidad Nacional Toribio Rodriguez de Mendoza, Amazonas, Peru https://orcid.org/0000-0003-1865-1293
Jose Santisteban Information Systems Engineering, Universidad Peruana de Ciencias Aplicadas, Lima, Peru https://orcid.org/0000-0003-4526-642X
Alejandra Onate-Andino Escuela Superior Politecnica de Chimborazo, Riobamba, Ecuador

Volume: 16 | Issue: 1 | Pages: 31624-31631 | February 2026 | https://doi.org/10.48084/etasr.14923

Received: 19 September 2025 | Revised: 21 October 2025 and 30 October 2025 | Accepted: 1 November 2025 | Online: 12 December 2025

Corresponding author: Jose Santisteban

Abstract

Non-Technical Losses (NTLs) of electric energy compromise the operational efficiency and sustainability of the electrical system, particularly in the residential sector. This study addresses this problem by developing a predictive model that can estimate energy consumption and detect anomalous patterns. For this purpose, data were collected from the Plataforma Nacional de Datos Abiertos and the Osinergmin website. The study integrates two approaches: ARIMA, which is used to represent time series with well-defined seasonal patterns, and an approach based on XGBoost to represent non-linear behavior in more heterogeneous consumption intervals. The results suggest that ARIMA demonstrated optimal performance in stable cases, with errors close to zero in several cases, where the most representative systems are SR0148 with Mean Absolute Error (MAE) = 0.000124 and Root Mean Square Error (RMSE) = 0.003549, and SE1095 with MAE = 0.000287 and RMSE = 0.004481. XGBoost, on the other hand, reached its maximum performance in the interval "From 1 to 30 kWh", with MAE = 2.81, RMSE = 5.80, and a Coefficient of Determination (R²) of 0.13. This validates the effectiveness of the proposed approach based on the integration of more than one algorithm to identify electric consumption anomalies.

Keywords:

Non-Technical Losses (NTLs), business intelligence, data analysis, XGboost, regression, ARIMA, time series, energy anomalies

Downloads

Download data is not yet available.

References

S. K. Gunturi and D. Sarkar, "Ensemble Machine Learning Models for the Detection of Energy Theft," Electric Power Systems Research, vol. 192, Mar. 2021, Art. no. 106904. DOI: https://doi.org/10.1016/j.epsr.2020.106904

I. M. R. Baldawi and T. İnan, "A Novel and Effective Method Based Deep Learning Model for Detecting Non-Technical Electricity Losses," International Journal of Power Electronics and Drive Systems (IJPEDS), vol. 14, no. 4, Dec. 2023, Art. no. 2464. DOI: https://doi.org/10.11591/ijpeds.v14.i4.pp2464-2473

R. K. Ahir and B. Chakraborty, "Pattern-Based and Context-Aware Electricity Theft Detection in Smart Grid," Sustainable Energy, Grids and Networks, vol. 32, Dec. 2022, Art. no. 100833. DOI: https://doi.org/10.1016/j.segan.2022.100833

M. Toledo-Orozco, C. Arias-Marin, C. Álvarez-Bel, D. Morales-Jadan, J. Rodríguez-García, and E. Bravo-Padilla, "Innovative Methodology to Identify Errors in Electric Energy Measurement Systems in Power Utilities," Energies, vol. 14, no. 4, Feb. 2021, Art. no.958. DOI: https://doi.org/10.3390/en14040958

"Energy Theft." Pluz Energía Perú, Oct. 2024. https://www.pluz.pe/es/ayuda/hurto-de-energia.html.

A. Nawaz, T. Ali, G. Mustafa, S. U. Rehman, and M. R. Rashid, "A Novel Technique for Detecting Electricity Theft in Secure Smart Grids using CNN and XG-Boost," Intelligent Systems with Applications, vol. 17, Feb. 2023, Art. no. 200168. DOI: https://doi.org/10.1016/j.iswa.2022.200168

M. J. Abdulaal et al., "Real-Time Detection of False Readings in Smart Grid AMI Using Deep and Ensemble Learning," IEEE Access, vol. 10, pp. 47541–47556, 2022. DOI: https://doi.org/10.1109/ACCESS.2022.3171262

Osinergmin, "Electrical energy consumption report (kWh-month) (Supervisory Body for Investment in Energy and Mining)." Datosabiertos, Nov. 2024, [Online]. Available: https://www.datosabiertos.gob.pe/dataset/reporte-del-consumo-de-energ%C3%ADa-el%C3%A9ctrica-kwh-mes-organismo-supervisor-de-la-inversi%C3%B3n-en-3.

Osinergmin, "Aprobación de las Altas y Bajas 2023." Datosabiertos, 2023, [Online]. Available: https://www.osinergmin.gob.pe/seccion/institucional/regulacion-tarifaria/procesos-regulatorios/actividades-relacionadas/aprobacion-altas-bajas-2023.

Pamir, N. Javaid, M. Akbar, A. Aldegheishem, N. Alrajeh, and E. A. Mohammed, "Employing a Machine Learning Boosting Classifiers Based Stacking Ensemble Model for Detecting Non-Technical Losses in Smart Grids," IEEE Access, vol. 10, pp. 121886–121899, 2022. DOI: https://doi.org/10.1109/ACCESS.2022.3222883

Z. Liu, Y. Li, F. Shuang, Z. Huang, and R. Wang, "EMB-YOLO: Dataset, Method and Benchmark for Electric Meter Box Defect Detection," Journal of King Saud University - Computer and Information Sciences, vol. 36, no. 2, Feb. 2024, Art. no. 101936. DOI: https://doi.org/10.1016/j.jksuci.2024.101936

M. H. Zafar et al., "Step Towards Secure and Reliable Smart Grids in Industry 5.0: a Federated Learning Assisted Hybrid Deep Learning Model for Electricity Theft Detection using Smart Meters," Energy Reports, vol. 10, pp. 3001–3019, Nov. 2023. DOI: https://doi.org/10.1016/j.egyr.2023.09.100

B. Coma-Puig, A. Calvo, J. Carmona, and R. Gavaldà, "A Case Study of Improving a Non-technical Losses Detection System Through Explainability," Data Mining and Knowledge Discovery, vol. 38, no. 5, pp. 2704–2732, Sept. 2024. DOI: https://doi.org/10.1007/s10618-023-00927-7

P. K. Sebastian, K. Deepa, N. Neelima, R. Paul, and T. Özer, "A Comparative Analysis of Deep Neural Network Models in IoT‐based Smart Systems for Energy Prediction and Theft Detection," IET Renewable Power Generation, vol. 18, no. 3, pp. 398–411, Feb. 2024. DOI: https://doi.org/10.1049/rpg2.12824

E. Correia, R. Calili, J. F. Pessanha, and M. F. Almeida, "Definition of Regulatory Targets for Electricity Non-Technical Losses: Proposition of an Automatic Model-Selection Technique for Panel Data Regressions," Energies, vol. 16, no. 6, Mar. 2023, Art. no. 2519. DOI: https://doi.org/10.3390/en16062519

A. Narayanan and T. Hardy, "Synthetic Data Generation for Machine Learning Model Training for Energy Theft Scenarios using Cosimulation," IET Generation, Transmission & Distribution, vol. 17, no. 5, pp. 1035–1046, Mar. 2023. DOI: https://doi.org/10.1049/gtd2.12619

S. Lavrijssen, B. Espinosa Apráez, and T. Ten Caten, "The Legal Complexities of Processing and Protecting Personal Data in the Electricity Sector," Energies, vol. 15, no. 3, p. 1088, Feb. 2022. DOI: https://doi.org/10.3390/en15031088

F. B. Abdullah, M. Arsalan Aqeeq, R. Iqbal, M. Abdullah, and F. S. Memon, "Enhancing Electricity Distribution Efficiency in Pakistan: a framework for Progress and Action," Utilities Policy, vol. 88, June 2024, Art. no. 101746. DOI: https://doi.org/10.1016/j.jup.2024.101746

A. Khalid, G. Mustafa, M. R. R. Rana, S. M. Alshahrani, and M. Alymani, "RNN-BiLSTM-CRF based Amalgamated Deep Learning Model for Electricity Theft Detection to Secure Smart Grids," PeerJ Computer Science, vol. 10, Feb. 2024, Art. no. e1872. DOI: https://doi.org/10.7717/peerj-cs.1872

Y. Maraden et al., "Enhancing Electricity Theft Detection through K-Nearest Neighbors and Logistic Regression Algorithms with Synthetic Minority Oversampling Technique: A Case Study on State Electricity Company (PLN) Customer Data," Energies, vol. 16, no. 14, July 2023, Art. no. 5405. DOI: https://doi.org/10.3390/en16145405

M. B. Capeletti et al., "Identification of Nontechnical Losses in Distribution Systems Adding Exogenous Data and Artificial Intelligence," Energies, vol. 15, no. 23, Nov. 2022, Art. no. 8794. DOI: https://doi.org/10.3390/en15238794

A. I. Kawoosa, D. Prashar, M. Faheem, N. Jha, and A. A. Khan, "Using Machine Learning Ensemble Method for Detection of Energy Theft in Smart Meters," IET Generation, Transmission & Distribution, vol. 17, no. 21, pp. 4794–4809, Nov. 2023. DOI: https://doi.org/10.1049/gtd2.12997

O. Munoz et al., "Development of an IoT Smart Energy Meter with Power Quality Features for a Smart Grid Architecture," Sustainable Computing: Informatics and Systems, vol. 43, Sept. 2024, Art. no. 100990. DOI: https://doi.org/10.1016/j.suscom.2024.100990

S. Mitra, B. Chakraborty, and P. Mitra, "Smart Meter Data Analytics Applications for Secure, Reliable and Robust Grid System: Survey and Future Directions," Energy, vol. 289, Feb. 2024, Art. no. 129920. DOI: https://doi.org/10.1016/j.energy.2023.129920

M. A. Souza et al., "Detection of Non-Technical Losses on a Smart Distribution Grid Based on Artificial Intelligence Models," Energies, vol. 17, no. 7, Apr. 2024, Art. no. 1729. DOI: https://doi.org/10.3390/en17071729

M. Žarković and G. Dobrić, "Artificial Intelligence for Energy Theft Detection in Distribution Networks," Energies, vol. 17, no. 7, Mar. 2024, Art. no. 1580. DOI: https://doi.org/10.3390/en17071580

A. B. Pengwah, R. Razzaghi, and L. L. H. Andrew, "Model-Less Non-Technical Loss Detection using Smart Meter Data," IEEE Transactions on Power Delivery, vol. 38, no. 5, pp. 3469–3479, Oct. 2023. DOI: https://doi.org/10.1109/TPWRD.2023.3280551

M. Bartouli, A. Msolli, A. Helali, and H. Fredj, "A Real-Time Charge Predictive Model for Intelligent Networks," Engineering, Technology & Applied Science Research, vol. 14, no. 5, pp. 17091–17098, Oct. 2024. DOI: https://doi.org/10.48084/etasr.7845

Gobierno del Perú, Decreto Legislativo No. 1412 – Ley de Gobierno Digital, Lima, Perú, Sep. 2018. [Online]. Available: https://www.gob.pe/institucion/pcm/normas-legales/289706-1412.

D. Pérez, M. Flores, and P. Castañeda, "Non-Technical Loss Detection in Electric Meter Systems: A Predictive Approach with Business Intelligence in North Lima," Nanotechnology Perceptions, vol. 20, pp. 3579–3590, 2024.