Quickly detecting and pinpointing failures in electrical distribution lines are important for shortening the duration of service interruption, reducing maintenance costs and increasing safety. In this work, we propose a realistic architecture for an Internet-of-Things (IoT)-enabled fault detection system designed for distribution networks. In order to continually assess electrical characteristics including voltage, current, frequency, temperature, and line status, the suggested architecture combines inexpensive, dispersed sensor nodes placed along feeders and important network points. These sensor nodes connect to edge devices via dependable wireless protocols, where they execute initial data preprocessing, filtering, and anomaly detection in order to minimize latency and bandwidth consumption. Deployed at the edge gateway or in the cloud, advanced machine learning (ML)-based analytics are utilized for fault detection, classification (e.g., line-to-ground, line- to-line, open conductor), and severity estimation. The architectural proposal fuses low-cost sensor nodes as down to the network, edge based data preprocessing and cloud or edge gateway oriented ML based analytics. We talk about the elements of the system, the data flow, fault detection and classification techniques (both rule-based and ML- based), as well as potential approaches to fault localization. Finally, we present highlevel sketch of an experimental plan and discuss the involved trade-offs. The idea is to help utilities transition from reactive maintenance to real-time monitoring and active fault management.

Keywords - IoT, distribution lines, fault detection, machine learning, smart grid edge computing.

🔒 This is a subscription article

Full text is available to subscribers and institutional members. Please choose an option below to access it.

1. Ul Mehmood M, Ulasyar A, Khattak A, Imran K, Sheh Zad H, Nisar S. Cloud based IoT solution for fault detection and localization in power distribution systems. Energies. 2020 May 26;13(11):2686.
2. Sattar MK, Waseem M, Fayyaz S, Kalsoom R, Hussain HA, Saddique MS. IoT based fault detection and protection of power transformer in the smart grid. Engineering Proceedings. 2021 Dec 22;12(1):7.
3. Goswami L, Agrawal P. Iot based diagnosing of fault detection in power line transmission through google firebase database. In2020 4th International Conference on Trends in Electronics and Informatics (ICOEI)(48184) 2020 Jun 15 (pp. 415-420). IEEE.
4. Kousar S, Zafar NA, Ali T, Alkhammash EH, Hadjouni M. Formal modeling of IoT- based distribution management system for smart grids. Sustainability. 2022 Apr 10;14(8):4499.
5. Jacob CM, George N, Lal A, George RJ, Antony M, Joseph J. An IoT based smart monitoring system for vehicles. In2020 4th international conference on trends in electronics and informatics (ICOEI)(48184) 2020 Jun 15 (pp. 396- 401). IEEE.
6. Peter G, Stonier AA, Gupta P, Gavilanes D, Vergara MM, Lung sin J. Smart fault monitoring and normalizing of a power distribution system using IoT. Energies. 2022 Nov 3;15(21):8206.
7. Yin Y, Wei L. Hyperspectral image classification using comprehensive evaluation model of extreme learning machine based on cumulative variation weights. IEEE Access. 2020 Oct 13;8:187991-8003.
8. Wani SA, Rana AS, Sohail S, Rahman O, Parveen S, Khan SA. Advances in DGA based condition monitoring of transformers: A review. Renewable and Sustainable Energy Reviews. 2021 Oct 1;149:111347.
9. Kavousi-Fard A, Nikkhah S, Pourbehzadi M, Dabbaghjamanesh M, Farughian A. IoT-based data-driven fault allocation in microgrids using advanced µPMUs. Ad Hoc Networks. 2021 Aug 1;119:102520.
10. Magesh T, Thiyagesan M, Gokul T, Samuel Franklin F, Bhavesh K. Fault detection using IoT in essential power transmission lines. In2023 Intelligent Computing and Control for Engineering and Business Systems (ICCEBS) 2023 Dec 14 (pp. 1-6). IEEE.
11. Mnyanghwalo D, Kawambwa S. Deployment of an IoT based sensor node for faults detection and classification in electrical secondary distribution networks. Cogent Engineering. 2024 Dec 31;11(1):2404679.

Quickly detecting and pinpointing failures in electrical distribution lines are important for shortening the duration of service interruption, reducing maintenance costs and increasing safety. In this work, we propose a realistic architecture for an Internet-of-Things (IoT)-enabled fault detection system designed for distribution networks. In order to continually assess electrical characteristics including voltage, current, frequency, temperature, and line status, the suggested architecture combines inexpensive, dispersed sensor nodes placed along feeders and important network points. These sensor nodes connect to edge devices via dependable wireless protocols, where they execute initial data preprocessing, filtering, and anomaly detection in order to minimize latency and bandwidth consumption. Deployed at the edge gateway or in the cloud, advanced machine learning (ML)-based analytics are utilized for fault detection, classification (e.g., line-to-ground, line- to-line, open conductor), and severity estimation. The architectural proposal fuses low-cost sensor nodes as down to the network, edge based data preprocessing and cloud or edge gateway oriented ML based analytics. We talk about the elements of the system, the data flow, fault detection and classification techniques (both rule-based and ML- based), as well as potential approaches to fault localization. Finally, we present highlevel sketch of an experimental plan and discuss the involved trade-offs. The idea is to help utilities transition from reactive maintenance to real-time monitoring and active fault management.

Keywords - IoT, distribution lines, fault detection, machine learning, smart grid edge computing.

🔒 This is a subscription article

Full text is available to subscribers and institutional members. Please choose an option below to access it.

1. Ul Mehmood M, Ulasyar A, Khattak A, Imran K, Sheh Zad H, Nisar S. Cloud based IoT solution for fault detection and localization in power distribution systems. Energies. 2020 May 26;13(11):2686.
2. Sattar MK, Waseem M, Fayyaz S, Kalsoom R, Hussain HA, Saddique MS. IoT based fault detection and protection of power transformer in the smart grid. Engineering Proceedings. 2021 Dec 22;12(1):7.
3. Goswami L, Agrawal P. Iot based diagnosing of fault detection in power line transmission through google firebase database. In2020 4th International Conference on Trends in Electronics and Informatics (ICOEI)(48184) 2020 Jun 15 (pp. 415-420). IEEE.
4. Kousar S, Zafar NA, Ali T, Alkhammash EH, Hadjouni M. Formal modeling of IoT- based distribution management system for smart grids. Sustainability. 2022 Apr 10;14(8):4499.
5. Jacob CM, George N, Lal A, George RJ, Antony M, Joseph J. An IoT based smart monitoring system for vehicles. In2020 4th international conference on trends in electronics and informatics (ICOEI)(48184) 2020 Jun 15 (pp. 396- 401). IEEE.
6. Peter G, Stonier AA, Gupta P, Gavilanes D, Vergara MM, Lung sin J. Smart fault monitoring and normalizing of a power distribution system using IoT. Energies. 2022 Nov 3;15(21):8206.
7. Yin Y, Wei L. Hyperspectral image classification using comprehensive evaluation model of extreme learning machine based on cumulative variation weights. IEEE Access. 2020 Oct 13;8:187991-8003.
8. Wani SA, Rana AS, Sohail S, Rahman O, Parveen S, Khan SA. Advances in DGA based condition monitoring of transformers: A review. Renewable and Sustainable Energy Reviews. 2021 Oct 1;149:111347.
9. Kavousi-Fard A, Nikkhah S, Pourbehzadi M, Dabbaghjamanesh M, Farughian A. IoT-based data-driven fault allocation in microgrids using advanced µPMUs. Ad Hoc Networks. 2021 Aug 1;119:102520.
10. Magesh T, Thiyagesan M, Gokul T, Samuel Franklin F, Bhavesh K. Fault detection using IoT in essential power transmission lines. In2023 Intelligent Computing and Control for Engineering and Business Systems (ICCEBS) 2023 Dec 14 (pp. 1-6). IEEE.
11. Mnyanghwalo D, Kawambwa S. Deployment of an IoT based sensor node for faults detection and classification in electrical secondary distribution networks. Cogent Engineering. 2024 Dec 31;11(1):2404679.