Enhancing Smart Grid Resilience Through AI-Based Fault Classification

Year : 2026 | Volume : 04 | Issue : 01 | Page : 10 15
    By

    Alok Prasad,

  • Alok Kumar,

  1. Student, Department Electrical Engineering, Bansal Institute of Engineering and Technology, Lucknow, Uttar Pradesh, India
  2. Assistant Professor, Department Electrical Engineering, Bansal Institute of Engineering and Technology, Lucknow, Uttar Pradesh, India

Abstract

Traditional power grids can be developed into smart grids, and they are comprised of the latest information and communication technologies (ICTs), which are based on establishing the relationship between the conventional electricity systems along with the usage of smart meters and distributed generation. This dynamic improves energy efficiency and the integration of renewables. Well, the dynamic and reversible power injection from Distributed Energy Resources (DERs) creates substantial operational problems. These features include very variable fault currents, more complex patterns of power flow, and high levels of harmonic distortion. This volatility makes traditional, static-level relay technology increasingly ineffective because it is not fast or flexible enough to accurately pick up faults in today’s environment. This paper provides a rapid and flexible fault detection and classification solution for Software-Defined Networks (SDNs) in response to this demand. We present a novel model-based artificial intelligence (AI)-enabled data-driven technique for accurate classification of different fault types. The approach includes safe voltage and current high-fidelity data acquisition on the fly with advanced signal processing to extract discriminatory features, characterizing individual fault signals. Then, the features of interest are used to train a strong Random Forest (RF) classifier. The proposed AI model shows excellent performance with an exceptional accuracy of 98.04% in categorizing the fault conditions. Importantly, it can decide in less than 10 milliseconds. The speed and accuracy of this process confirm that AI is a key enabler to provide significant improvements in the reliability and operational responsiveness of smart grids during transient fault conditions.

Keywords: Artificial intelligence, distribution network, fault classification, random forest, smart grid

[This article belongs to International Journal of Algorithms Design and Analysis Review ]

How to cite this article:
Alok Prasad, Alok Kumar. Enhancing Smart Grid Resilience Through AI-Based Fault Classification. International Journal of Algorithms Design and Analysis Review. 2026; 04(01):10-15.
How to cite this URL:
Alok Prasad, Alok Kumar. Enhancing Smart Grid Resilience Through AI-Based Fault Classification. International Journal of Algorithms Design and Analysis Review. 2026; 04(01):10-15. Available from: https://journals.stmjournals.com/ijadar/article=2026/view=248553


References

  1. Chuan OW, Ab Aziz NF, Yasin ZM, Salim NA, Wahab NA. Fault classification in smart distribution network using support vector machine. Indones J Electr Eng Comput Sci. 2020;18(3):1148–1155. doi:10.11591/ijeecs.v18.i3.pp1148-1155.
  2. Padovani Neto FC, Lessa Assis TM, Ferreira VH. Artificial neural network-based protection scheme of active distribution systems. 2019 IEEE PES Innovative Smart Grid Technologies Conference – Latin America (ISGT Latin America), Gramado, Brazil, 2019. p. 1–6. doi:10.1109/ISGT-LA.2019.8895396.
  3. Cano A, Arévalo P, Benavides D, Jurado F. Integrating discrete wavelet transform with neural networks and machine learning for fault detection in microgrids. Int J Electr Power Energy Syst. 2024;155:109616. doi:10.1016/j.ijepes.2023.109616.
  4. Etukuri S, Siva M, Varma BRK. Intelligent protection of renewable-rich three-terminal transmission systems using GRU deep learning models. Eng Res Express. 2025;7(4):045379. doi:10.1088/2631-8695/ae2195.
  5. Singh M. Protection coordination in distribution systems with and without distributed energy resources: A review. Prot Control Mod Power Syst. 2017;2(3):1–7. doi:10.1186/s41601-017-0061-1.
  6. Moreno Escobar JJ, Morales Matamoros O, Tejeida Padilla R, Lina Reyes I, Quintana Espinosa H. A comprehensive review on smart grids: Challenges and opportunities. Sensors (Basel). 2021;21(21):6978. doi:10.3390/s21216978. PubMed: 34770285.
  7. Al-Bhadely F, İnan A. An innovative approach for enhancing relay coordination in distribution systems through online adaptive strategies utilizing DNN machine learning and a hybrid GA–SQP framework. Arab J Sci Eng. 2024;49(12):16865–16887. doi:10.1007/s13369-024-09291-0.
  8. Chakraborty D, Sur U, Banerjee PK. Random forest based fault classification technique for active power system networks. In: 2019 IEEE International WIE Conference on Electrical and Computer Engineering (WIECON-ECE); 2019. p. 1–4. doi:10.1109/WIECON-ECE48653.2019.9019922.
  9. Lucas F, Costa P, Batalha R, Leite D, Škrjanc I. Fault detection in smart grids with time-varying distributed generation using wavelet energy and evolving neural networks. Evol Syst. 2020;11(2):165–180. doi:10.1007/s12530-020-09328-3.
  10. Elbouchikhi E, Zia MF, Benbouzid M, El Hani S. Overview of signal processing and machine learning for smart grid condition monitoring. Electronics. 2021;10(21):2725. doi:10.3390/electronics10212725.
  11. Haddadi A, Farantatos E, Kocar I, Karaagac U. Impact of inverter based resources on system protection. Energies. 2021;14(4):1050. doi:10.3390/en14041050.
  12. Khare G, Mohapatra A, Singh SN. A real-time approach for detection and correction of false data in PMU measurements. Electr Power Syst Res. 2021;191:106866. doi:10.1016/j.epsr.2020.106866.
  13. Ibrahim AHM, Sadanandan SK, Ghaoud T, Rajkumar VS, Sharma M. Incipient fault detection in power distribution networks: Review, analysis, challenges, and future directions. IEEE Access. 2024;12:112822–112838. doi:10.1109/ACCESS.2024.3443252.
  14. Sekhar P, Mohanty S. Classification and assessment of power system static security using decision tree and random forest classifiers. Int J Numer Model Electron Netw Devices Fields. 2016;29(3):465–474. doi:10.1002/jnm.2096.
  15. Xiao W, Ren X. Artificial intelligence algorithms enhancing relay protection and operational efficiency in high and low voltage distribution networks. Intell Decis Technol. 2025;19(5):3072–3087. doi:10.1177/18724981251355872.
  16. Li Q, Deng Y, Liu X, Sun W, Li W, Li J, et al. Autonomous smart grid fault detection. IEEE Commun Stand Mag. 2023;7(2):40–47. doi:10.1109/MCOMSTD.0001.2200019.
  17. Esakimuthu Pandarakone S, Mizuno Y, Nakamura H. A comparative study between machine learning algorithm and artificial intelligence neural network in detecting minor bearing fault of induction motors. Energies. 2019;12(11):2105. doi:10.3390/en12112105.
  18. El-Hawary ME. The smart grid—state-of-the-art and future trends. Electr Power Compon Syst. 2014;42(3–4):239–250. doi:10.1080/15325008.2013.868558.
  19. Mazhar T, Irfan HM, Haq I, Ullah I, Ashraf M, Shloul TA, et al. Analysis of challenges and solutions of IoT in smart grids using AI and machine learning techniques: A review. Electronics. 2023;12(1):242. doi:10.3390/electronics12010242.
  20. Aleem SA, Hussain SMS, Ustun TS. A review of strategies to increase PV penetration level in smart grids. Energies. 2020;13(3):636. doi:10.3390/en13030636.
Regular Issue Subscription Review Article
Volume 04
Issue 01
Received 09/12/2025
Accepted 20/12/2025
Published 20/02/2026
Publication Time 73 Days
44

Login


My IP

PlumX Metrics