Authors : Gowthami J; Dr. Sathish Paranthaman

Volume/Issue : Volume 10 - 2025, Issue 4 - April

Google Scholar : https://tinyurl.com/4tr3u4t

Scribd : https://tinyurl.com/y7wuf57h

DOI : https://doi.org/10.38124/ijisrt/25apr019

Google Scholar

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 15 to 20 days to display the article.

Abstract : Power utilities around the world face a serious problem with electricity theft, which leads to large financial losses and inefficient operations. The design and development of an Internet of Things (IoT)-based prototype for real-time electricity theft detection and distribution optimization through sophisticated machine-learning techniques is presented in this work. The system provides precise, real-time statistics by continually monitoring electricity consumption through the integration of smart meters and Internet of Things sensors. The proposed solution shows significant potential for improving the operational effectiveness of power utilities, providing a scalable, reliable, and effective framework for modern energy management. The prototype uses Deep Neural Networks (DNNs) to identify anomalous usage patterns indicative of theft, ensuring quick and accurate detection. Additionally, the structure influences machine-learning procedures to optimize electricity distribution, increasing overall efficiency and reducing waste. This comprehensive method not only reduces the risk of theft but also improves the dependability and sustainability of electricity supply.

Keywords : Power utilities around the world face a serious problem with electricity theft, which leads to large financial losses and inefficient operations. The design and development of an Internet of Things (IoT)-based prototype for real-time electricity theft detection and distribution optimization through sophisticated machine-learning techniques is presented in this work. The system provides precise, real-time statistics by continually monitoring electricity consumption through the integration of smart meters and Internet of Things sensors. The proposed solution shows significant potential for improving the operational effectiveness of power utilities, providing a scalable, reliable, and effective framework for modern energy management. The prototype uses Deep Neural Networks (DNNs) to identify anomalous usage patterns indicative of theft, ensuring quick and accurate detection. Additionally, the structure influences machine-learning procedures to optimize electricity distribution, increasing overall efficiency and reducing waste. This comprehensive method not only reduces the risk of theft but also improves the dependability and sustainability of electricity supply.

References :

1. Mohammad Tabrez Quasim1, Khair ul Nisa1, Mohammad Zunnun Khan1, Mohammad Shahid Husain2, Shadab Alam3, Mohammed Shuaib3, Mohammad Meraj4 and Monir Abdullah5. (2023) .An internet of things enabled machine learning model for Energy Theft Prevention System (ETPS) in Smart Cities. https://doi.org/10.1186/s13677-023-00525-4. Quasim et al. Journal of Cloud Computing
2. Adil, M., Javaid, N., Qasim, U., Ullah, I., Shafiq, M., and Choi, J. G. (2020). LSTM and bat-based RUSBoost approach for electricity theft detection. Appl. Sci. 10 (12), 4378. doi:10.3390/app10124378
3. Arif, A., Alghamdi, T. A., Khan, Z. A., and Javaid, N. (2022). Towards efficient energy utilization using big data analytics in smart cities for electricity theft detection. Big Data Res. 27, 100285. doi:10.1016/j.bdr.2021.100285
4. Banga, A., Ahuja, R., and Sharma, S. (2022). Accurate detection of electricity theft using classification algorithms and Internet of Things in smart grid. Arabian J. Sci. Eng. 47 (8), 9583–9599. doi:10.1007/s13369-021-06313-z
5. Bohani, F. A., Suliman, A., Saripuddin, M., Sameon, S. S., Md Salleh, N. S., and Nazeri, S. (2021). A comprehensive analysis of supervised learning techniques for electricity theft detection. J. Electr. Comput. Eng. 2021, 1–10. doi:10.1155/2021/ 9136206
6. Stracqualursi, E., Rosato, A., Di Lorenzo, G., Panella, M., and Araneo, R. (2023). Systematic review of energy theft practices and autonomous detection through artificial intelligence methods. Renew. Sustain. Energy Rev. 184, 113544. doi:10.1016/j.rser.2023. 113544
7. Xie, R. (2023).An energy theft detection framework with privacy protection for smart grid. 2023 International Joint Conference on Neural Networks (IJCNN), Gold Coast, Australia, IEEE.
8. Kocaman, B., and Tümen, V. (2020). Detection of electricity theft using data processing and LSTM method in distribution systems. Sādhanā 45 (1), 286. doi:10. 1007/s12046-020-01512-0
9. Khan, N., (2024). A novel deep learning technique to detect electricity theft in smart grids using AlexNet. IET Renewable Power Generation. 17, 12846, doi:10.1049/rpg2. 12846
10. Razavi, R., Gharipour, A., Fleury, M., and Akpan, I. J. (2019). A practical feature engineering framework for electricity theft detection in smart grids. Appl. energy 238, 481–494. doi:10.1016/j.apenergy.2019.01.076