Document Type : Original Research Article
Received: 08 January 2026
|
Revised: 27 January 2026
|
Accepted: 09 February 2026
|
Published: 12 June 2026
Authors
Naveen Sankaran
1,*
1
Engineering and Solutions, DACK Consulting Solutions, Inc., White Plains, New York, USA
*
Author to whom correspondence should be addressed.
Abstract
The increased sophistication of smart grids and integration of renewable energy has only increased the complexity of monitoring electrical faults and making accurate and real-time fault diagnosis essential for network stability. The current prevailing methods are generally typified by low degrees of robustness, high degrees of false alarms, learning of redundant features and low fault impact predictability under operating conditions which are dynamic in nature. To address these issues, this research proposed an Adaptive Hierarchical Attention Fault Classifier Network (AHA-FCNet) and a Hierarchical Fault Impact Prediction Network (HFIP-Net). The first step is to improve the quality of the signal by normalizing and smoothing the signal and the hybrid feature selection is used to remove the irrelevant features in the voltage, current, and power signal. Two-stage classification of fault/non-fault state and a classification of line-to-ground (LG), line-to-line (LL), double line-to-ground (LLG) or three-phase faults (LLL) faults based on attention-guided deep learning are carried out by AHA-FCNet. HFIP-Net also envisions a voltage drop, current variation and power loss through hierarchical regression learning. The experimental results showed that the highest performance was achieved with the highest classification accuracy of 98.30%. For prediction, HFIP-Net achieved MAE of 0.85, RMSE of 1.39, and R² of 99.45. The proposed architecture is a smart and intelligent plan of real-time smart grid fault detection and stability improvement.
Keywords:
Attention Mechanism
,
Deep Learning
,
Electrical Fault Detection
,
Feature Selection
,
Smart Grid
,
Voltage Stability
References
[1]
Lahon, P., Kandali, A.B., Barman, U., Konwar, R.J., Saha, D., & Saikia, M.J. (2024). Deep Neural Network-Based Smart Grid Stability Analysis: Enhancing Grid Resilience and Performance. Energies, 17(11), 2642.
https://doi.org/10.3390/en17112642
[2]
Xie, Z., Zhang, D., Hu, W., & Han, X. (2024). Power System Transient Stability Preventive Control via Aptenodytes Forsteri Optimization with an Improved Transient Stability Assessment Model. Energies, 17(8), 1942.
https://doi.org/10.3390/en17081942
[3]
Vijay, A.S. (2025). Stability Analysis of DC Microgrids with Constant Power Loads Using Droop Control and Virtual Resistance Shaping. Energy Conversion and Economics.
https://doi.org/10.1049/enc2.70013
[4]
Peng, B., & Wang, Y. (2024). Coordinated Active-Reactive Power Optimization Considering Photovoltaic Abandon Based on Second Order Cone Programming in Active Distribution Networks. PLOS ONE.
https://doi.org/10.1371/journal.pone.0308450
[5]
Candra, O., Alghamdi, M. I., Hammid, A. T., et al. (2024). Optimal distribution grid allocation of reactive power with a focus on the particle swarm optimization technique and voltage stability. Scientific Reports, 14, 10889.
https://doi.org/10.1038/s41598-024-61412-9
[6]
He, P., Huang, X., He, R., & Yuan, L. (2025). Load Frequency Control in Isolated Island City Microgrids Using Deep Graph Reinforcement Learning Considering Extensive Scenarios. AIP Advances, 15(1), 015316.
https://doi.org/doi.org/10.1063/5.0247965
[7]
Guo W, Du H, Han T, Li S, Lu C and Huang X (2024) Learning-driven load frequency control for islanded microgrid using graph networks-based deep reinforcement learning. Front. Energy Res. 12:1517861.
https://doi.org/10.3389/fenrg.2024.1517861
[8]
Danaei, N.M., & Naghdi, V. (2025). Adaptive Distributed Stochastic Deep Reinforcement Learning Control for Voltage and Frequency Restoration in Islanded AC Microgrids with Communication Noise and Delay. Scientific Reports.
https://doi.org/10.1038/s41598-025-13010-6
[9]
Ahmadimonfared, Z., & Eichner, S. (2025). Stability Assessment of Fully Inverter-Based Power Systems Using Grid-Forming Controls. Electronics, 14(21), 4202.
https://doi.org/10.3390/electronics14214202
[10]
Khandelwal, D., Anand, P., Ray, M., & Sangeetha, R. G. (2025). Fault detection in electrical power systems using attention-GRU-based fault classifier (AGFC-Net). Scientific Reports, 15, Article 24133.
https://doi.org/10.1038/s41598-025-06493-w
[11]
Nayak, P., Das, S. R., Mallick, R. K., Mishra, S., & Althobaiti, A. (2024). 2D-convolutional neural network based fault detection and classification of transmission lines using scalogram images. E-Prime – Advances in Electrical Engineering, Electronics and Energy, 10, e38947.
https://doi.org/10.1016/j.heliyon.2024.e38947
[12]
Raza, M. A., et al. (2024). A hybrid LSTM random forest model with grey wolf optimization for enhanced detection of multiple bearing faults. Scientific Reports, 14, Article 26147.
https://doi.org/10.1038/s41598-024-75174-x
[13]
Lee, B., Kim, Y., Lee, H., & Kang, C. (2025). Bidirectional gated recurrent unit neural network for fault diagnosis and rapid maintenance in medium-voltage direct current systems. Sensors, 25(3), 693.
https://doi.org/10.3390/s25030693
[14]
Faza, A. (2024). Optimal PMU placement for fault classification and localization using enhanced feature selection in machine learning algorithms. International Journal of Energy Research, 2024, 5543160.
https://doi.org/10.1155/2024/5543160
[15]
Anwar, T., Mu, C., Yousaf, M. Z., & Khan, W. (2025). Robust fault detection and classification in power transmission lines via ensemble machine learning models. Scientific Reports, 15, 2549.
https://doi.org/10.1038/s41598-025-86554-2
[16]
Perçuku, A., Minkovska, D., & Hinov, N. (2025). Enhancing electricity load forecasting with machine learning and deep learning. Technologies, 13(2), 59.
https://doi.org/10.3390/technologies13020059
[17]
Alsalem, K. (2025). A hybrid time series forecasting approach integrating fuzzy clustering and machine learning for enhanced power consumption prediction. Scientific Reports, 15, 6447.
https://doi.org/10.1038/s41598-025-91123-8
[18]
Zhao, L., et al. (2025). Decision tree-based fault diagnosis system for distribution network fault indicators. Journal of Engineering and Applied Science, 72, 1–15.
https://doi.org/10.1186/s44147-025-00767-w
[19]
Özdemir, Ö., Köker, R., & Pamuk, N. (2025). Fault classification and precise fault location detection in 400 kV high-voltage power transmission lines using machine learning algorithms. Processes, 13(2), 527.
https://doi.org/10.3390/pr13020527
[20]
Yousaf, M. Z., Singh, A. R., & Khalid, S. (2024). Enhancing HVDC transmission line fault detection using disjoint bagging and Bayesian optimization with artificial neural networks and scientometric insights. Scientific Reports, 14, 23610.
https://doi.org/10.1038/s41598-024-74300-z
[21]
Shakouri, M., et al. (2025). Advanced AI-driven techniques for fault and transient analysis in high-voltage power systems. Scientific Reports, 15, Article 6041.
https://doi.org/10.1038/s41598-025-90055-7
[22]
Toprak, M., et al. (2025). Machine learning-based fault detection in transmission lines: A comparative study with random search optimization. Bulletin of the Polish Academy of Sciences: Technical Sciences, 73(2), e153229.
https://doi.org/10.24425/bpasts.2025.153229
[23]
Teshome, A., & Worku, G. (2025). Machine learning algorithms for voltage stability assessment in electrical distribution systems. Scientific Reports, 15, Article 28791.
https://doi.org/10.1038/s41598-025-15791-2
[24]
Yang, Y., Long, J., Yang, L., Mo, S., & Wu, X. (2024). Online prediction and correction of static voltage stability index based on extreme gradient boosting algorithm. Energies, 17(22), 5710.
https://doi.org/10.3390/en17225710
[25]
Senyuk, M., et al. (2025). Bulk low-inertia power systems adaptive fault type classification method based on machine learning and phasor measurement units data. Mathematics, 13(2), 316.
https://doi.org/10.3390/math13020316
