Using Hybrid Convolutional Neural Network and Random Forest (CNN-RF) Algorithms to Address Non-Technical Losses in Power Distribution Systems

Babawale Bunmi Folajinmi¹ , Emmanuel Majiyebo Eronu² , Seyi Josiah Fanifosi³

Section:Research Paper, Product Type: Journal-Paper
Vol.12 , Issue.1 , pp.1-8, Mar-2025

Online published on Mar 31, 2025

Copyright © Babawale Bunmi Folajinmi, Emmanuel Majiyebo Eronu, Seyi Josiah Fanifosi . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
 

View this paper at   Google Scholar | DPI Digital Library

XML View     PDF Download

How to Cite this Paper

Abstract :
The electricity distribution sector experiences substantial financial losses due to non-technical losses (NTLs) including electricity theft, faulty meters, and commercial losses. This research introduces a combined Convolutional Neural Network and Random Forest (CNN-RF) approach to detect NTLs using metered customer electricity consumption data from the Abuja Electricity Distribution Company. The dataset, covering February 1, 2021, to January 31, 2022, was cleaned, preprocessed, and used to train the model. The CNN part uses a multi-layer design with convolutional layers for automatic feature extraction, followed by dropout layers to mitigate overfitting. Early stopping mechanisms were introduced to optimize training efficiency and prevent model degradation. The RF component was trained on the automatically extracted features by the CNN component and classifies consumers into "energy loss" and "no energy loss" categories. The GridSearchCV algorithm facilitated the RF’s hyperparameters fine-tuning to achieve optimal configurations. The proposed model demonstrated a classification accuracy of 97% with a low false positive rate, thereby surpassing the effectiveness of manual inspections in detecting NTLs. This model can enhance the inspection hit rate and serve as an effective tool for detecting NTL activities in the electricity distribution sector.

Key-Words / Index Term :
Non-Technical Loss Detection, Random Forest, Machine Learning, Deep Learning, Energy Consumption, Convolution Neural Network

References :
[1] U. Soni and U. Kumari, “Prevention of Power Theft Using Concept of Multifunction Meter and PLC,” International Journal of Computer Sciences and Engineering” Open Access Survey Paper, Vol.6, Issue.12, pp.443-447, 2018.
[2] Z. A. Khan, M. Adil, N. Javaid, M. N. Saqib, M. Shafiq, and J. G. Choi, “Electricity theft detection using supervised learning techniques on smart meter data,” Sustain., Vol.12, No.19, pp.1–25, 2020.
[3] O. Olaoluwa, “Electricity theft and power quality in Nigeria,” Int. J. Eng. Res., Vol.6, No.6, pp.1180–1184, 2017.
[4] E. U. Haq, C. Pei, R. Zhang, H. Jianjun, and F. Ahmad, “Electricity-theft detection for smart grid security using smart meter data: A deep-CNN based approach,” Energy Reports, Vol.9, pp.634–643, 2023.
[5] S. Fanifosi, S. Ike, E. Buraimoh, and I. E. Davidson, “33kV Distribution Feeder Line Sag and Swell Mitigation using Customized DVR,” in Proceedings of the 5th International Conference on Information Technology for Education and Development: Changing the Narratives Through Building a Secure Society with Disruptive Technologies, ITED 2022, Institute of Electrical and Electronics Engineers Inc., 2022.
[6] R. Din and P. B. Prabadevi, "Data Analyzing using Big Data (Hadoop) in Billing System," International Journal of Computer Sciences and Engineering, Vol.5, No.5, pp.84-88, 2017.
[7] S. Abbas et al., “Improving Smart Grids Security: An Active Learning Approach for Smart Grid-Based Energy Theft Detection,” IEEE Access, Vol.12, pp.1706–1717, 2024.
[8] R. Yadav and Y. Kumar, “Detection of non-technical losses in electric distribution network by applying machine learning and feature engineering,” J. Eur. des Syst. Autom., Vol.54, No.3, pp.487–493, 2021.
[9] L. D. Soares, A. de S. Queiroz, G. P. López, E. M. Carreño-Franco, J. M. López-Lezama, and N. Muñoz-Galeano, “BiGRU-CNN Neural Network Applied to Electric Energy Theft Detection,” Electron. 2022, Vol.11, pp.693, 2022.
[10] M. Adil, N. Javaid, U. Qasim, I. Ullah, M. Shafiq, and J. G. Choi, “LSTM and bat-based rusboost approach for electricity theft detection,” Appl. Sci., Vol.10, No.12, 2020.
[11] H. Gul, N. Javaid, I. Ullah, A. M. Qamar, M. K. Afzal, and G. P. Joshi, “Detection of non-technical losses using SOSTLink and Bidirectional Gated Recurrent Unit to Secure Smart Meters,” Appl. Sci., Vol.10, No.9, 2020.
[12] Z. Zheng, Y. Yang, X. Niu, H. N. Dai, and Y. Zhou, “Wide and Deep Convolutional Neural Networks for Electricity-Theft Detection to Secure Smart Grids,” IEEE Trans. Ind. Informatics, Vol.14, No.4, pp.1606–1615, 2018.
[13] G. Lin et al., “Electricity Theft Detection in Power Consumption Data Based on Adaptive Tuning Recurrent Neural Network,” Front. Energy Res., Vol.9, pp.673, 2021.
[14] Petrlik, P. Lezama, C. Rodriguez, R. Inquilla, J. E. Reyna-González, and R. Esparza, “Electricity Theft Detection using Machine Learning,” Int. J. Adv. Comput. Sci. Appl., Vol.13, No.12, pp.420–425, 2022.
[15] Z. A. Khan, M. Adil, N. Javaid, M. N. Saqib, M. Shafiq, and J. G. Choi, “Electricity theft detection using supervised learning techniques on smart meter data,” Sustain., Vol.12, No.19, pp.1–25, 2020.
[16] X. Lu, Y. Zhou, Z. Wang, Y. Yi, L. Feng, and F. Wang, “Knowledge embedded semi-supervised deep learning for detecting non-technical losses in the smart grid,” Energies (Basel), Vol.12, No.18, 2019.
[17] R. Akram et al., “Towards big data electricity theft detection based on improved rusboost classifiers in smart grid,” Energies (Basel), Vol.14, No.23, 2021.
[18] A. Ullah, N. Javaid, A. S. Yahaya, T. Sultana, F. A. Al-Zahrani, and F. Zaman, “A Hybrid Deep Neural Network for Electricity Theft Detection Using Intelligent Antenna-Based Smart Meters,” Wirel Commun Mob Comput, Vol.2021, 2021.
[19] 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 and Distribution, 2023.
[20] S. Li, Y. Han, X. Yao, S. Yingchen, J. Wang, and Q. Zhao, “Electricity Theft Detection in Power Grids with Deep Learning and Random Forests,” J. Electr. Comput. Eng., Vol.2019, 2019.