Explainable Artificial Intelligence for Real-Time Stability Assessment in Smart Power Systems
DOI:
https://doi.org/10.4108/ew.13678Keywords:
Smart Grid Stability, Graph Transformer, Temporal Fusion Transformer, Explainable AI, SHapley Additive exPLanations, Real-Time PredictionAbstract
INTRODUCTION: Smart grid stability analysis is necessary for reliable power system operations in the presence of increased renewable energy penetration and distributed energy resources.
OBJECTIVES: This study proposes a novel Graph Transformer–Temporal Fusion Transformer (GT-TFT) with an Explainable Artificial Intelligence (XAI) framework for real-time smart grid stability prediction.
METHODS: A feature-correlation graph is constructed and processed using a Graph Transformer (GT) to capture spatial dependencies, while a Temporal Fusion Transformer (TFT) learns temporal dynamics from smart grid measurements. The extracted features are fused through a feature fusion layer and classified using a neural network classifier. SHapley Additive exPlanations (SHAP) is employed to improve model interpretability.
RESULTS: Experimental evaluation on the Smart Grid Stability dataset demonstrates superior performance, achieving an accuracy of 0.9879, precision of 0.9886, recall of 0.9926, F1-score of 0.9905, and AUC of 0.9999. Comparative analysis confirms that the proposed framework outperforms existing baseline models.
CONCLUSION: The suggested GT-TF-XAI framework offers a solution to real-time smart grid stability assessment that is accurate, reliable, and explainable to enable effective decision-making in current smart power systems.
Downloads
References
[1] Strielkowski W, Firsova I, Lukashenko I, Raudeliūnienė J, Tvaronavičienė M. Effective management of energy consumption during the COVID-19 pandemic: The role of ICT solutions. Energies. 2021, 14(4), 893.
[2] Ahmad A, Khan Z, Saad Alam M, Khateeb S, et al. An optimized home energy management system with integrated renewable energy and storage resources. Energies. 2017, 10(4), 549.
[3] Vlasa I, Gligor A, Dumitru CD, Iantovics LB. Smart Vlasa I, Gligor A, Dumitru CD, Iantovics LB. Smart metering systems optimization for non-technical losses reduction and consumption recording operation improvement in electricity sector. Sensors. 2020, 20(10), 2947.
[4] Sousa EL, Oliveira AM, Silva JG, et al. Development a low-cost wireless smart meter with power quality measurement for smart grid applications. Sensors. 2023, 23(16), 7210.
[5] Barwińska-Małajowicz A, Pyrek R, Szczotka K, Szymiczek J, Piecuch T. Improving the energy efficiency of public utility buildings in Poland through thermomodernization and renewable energy sources—A case study. Energies. 2023, 16(10), 4021.
[6] Ramesh J, Shahriar S, Al-Ali AR, Osman A, Shaaban MF. Machine learning approach for smart distribution transformers load monitoring and management system. Energies. 2022, 15(21), 7981.
[7] Stošović MA, Radivojević N, Ivanova M. Electricity consumption prediction in an electronic system using artificial neural networks. Electronics. 2022, 11(21), 3506.
[8] Toledo-Orozco M, Arias-Marin C, Álvarez-Bel B, Morales-Jadan D, Rodríguez-García J, Bravo-Padilla E. Innovative methodology to identify errors in electric energy measurement systems in power utilities. Energies. 2021, 14(4), 958.
[9] Chen Y, Li C, Zhao X. TSGformer: A unified temporal–spatial graph transformer with adaptive cross-scale modeling for multivariate time series. Systems. 2025, 13(8), 688.
[10] Petrosian O, Zhang Y. Solar power generation forecasting in smart cities and explanation based on explainable AI. Smart Cities. 2024, 7(6), 3388–3411.
[11] Al-Zubaydi NA. Smart Technology Based Empirical Mode Decomposition (EMD) Approach for Autonomous Transmission Line Fault Detection Protection. EAI Endorsed Transactions on Energy Web. 2022, 9(38), e7.
[12] Naderi E. Quantum-accelerated digital twins for cyber-resilient smart power systems against false data injection cyberattacks using bitcoin-mining-based virtual energy storage framework for voltage restoration. Electronics. 2026, 15(9), 1894.
[13] Sarajcev P, Kunac A, Petrovic G, Despalatovic M. Power system transient stability assessment using stacked autoencoder and voting ensemble. Energies. 2021, 14(11), 3148.
[14] Zhao J, Han X, Wang C, Yang J, Zhang G. Contrastive-active transfer learning-based real-time adaptive assessment method for power system transient stability. Sensors. 2024, 24(15), 5052.
[15] Gautam S, Sharma A, et al. Digital real-time simulation and power quality analysis of a hydrogen-generating nuclear-renewable integrated energy system. Energies. 2025, 18(4), 937.
[16] Ucar F. A comprehensive analysis of smart grid stability prediction along with explainable artificial intelligence. Symmetry. 2023, 15(2), 289.
[17] Pérez-Rosero DA, Pineda-Quintero S, Álvarez-Barreto JC, Álvarez-Meza AM, Castellanos-Dominguez G. An interpretable artificial intelligence approach for reliability and regulation-aware decision support in power systems. Computation. 2026, 14(1), 2.
[18] Nevisi MM, Shoeibi M, Hernando-Gallego F, Martín D, Khatami SS. An evolutionary deep reinforcement learning-based framework for efficient anomaly detection in smart power distribution grids. Energies. 2025, 18(10), 2435.
[19] Dong J, Li Y, Wang H, et al. AI-based faster-than-real-time stability assessment of large power systems with applications on WECC system. Energies. 2023, 16(3), 1401.
[20] Tapia EA, Colomé DG, Rueda Torres JL. Recurrent convolutional neural network-based assessment of power system transient stability and short-term voltage stability. Energies. 2022, 15(23), 9240.
[21] Madjovski D, Dumancic I, Tranchita C. Dynamic modeling of distribution power systems with renewable generation for stability analysis. Energies. 2024, 17(20), 5178.
[22] Lahon P, Kandali AB, Barman U, Konwar RJ, Saha D, Saikia MJ. Deep neural network-based smart grid stability analysis: Enhancing grid resilience and performance. Energies. 2024, 17(11), 2642.
[23] Luo J, Guo J, Zhao G, Shao Y, Yin Z, Li G. Design of an intelligent inspection system for power equipment based on multi-technology integration. Electronics. 2026, 15(4), 827.
[24] Tuan DH, Tran DT, Nguyen Ngoc Thanh V, Huynh VV. Load frequency control based on gray wolf optimizer algorithm for modern power systems. Energies. 2025, 18(4), 815.
[25] Senyuk M, Safaraliev M, Kamalov F, Sulieman H. Power system transient stability assessment based on machine learning algorithms and grid topology. Mathematics. 2023, 11(3), 525.
[26] Okasha AA, Mansour DEA, Zaky AB, Suehiro J, Megahed TF. A novel IoT-based controlled islanding strategy for enhanced power system stability and resilience. Smart Cities. 2024, 7(6), 3871–3894.
[27] Badrudeen TU, Nwulu NI, Gbadamosi SL. Neural network based approach for steady-state stability assessment of power systems. Sustainability. 2023, 15(2), 1667.
[28] Sahu PR, Lenka RK, Khadanga RK, Hota PK, Panda S, Ustun TS. Power system stability improvement of FACTS controller and PSS design: A time-delay approach. Sustainability. 2022, 14(21), 14649.
[29] Garcés HO, Godoy J, Riffo G, Sepúlveda NF, Espinosa E, Ahmed MA. Development of an IoT-enabled smart electricity meter for real-time energy monitoring and efficiency. Electronics. 2025, 14(6), 1173.
[30] Adhikari A, Naetiladdanon S, Sangswang A. Real-time short-term voltage stability assessment using combined temporal convolutional neural network and long short-term memory neural network. Applied Sciences. 2022, 12(13), 6333.
[31] Bachanek KH, Drożdż W, Kolon M. Development of renewable energy sources in Poland and stability of power grids—Challenges, technologies, and adaptation strategies. Energies. 2025, 18(8), 2036.
[32] Gül O. Dynamic load flow in modern power systems: Renewables, crypto mining, and electric vehicles. Sustainability. 2025, 17(6), 2515.
[33] Kazemi Naeini H, Shomali R, Pishahang A, Hasanzadeh H, Asadi S, Gholizadeh Lonbar A. PINN-DT: Optimizing energy consumption in smart building using hybrid physics-informed neural networks and digital twin framework with blockchain security. Sensors. 2025, 25(19), 6242.
[34] Lobos-Cornejo S, Grisales-Noreña LF, Andrade F, Montoya OD, Sanin-Villa D. Smart energy strategy for AC microgrids to enhance economic performance in grid-connected and standalone operations: A gray wolf optimizer approach. Sci. 2025, 7(2), 73.
[35] Smart Grid Stability. Kaggle Dataset. 2026. Available from: https://www.kaggle.com/datasets/pcbreviglieri/smart-grid-stability
[36] Azhar IF, Putranto LM, Irnawan R. Development of PMU-based transient stability detection methods using CNN-LSTM considering time series data measurement. Energies. 2022, 15(21), 8241.
[37] Cheng S, Yu Z, Liu Y, Zuo X. Power system transient stability assessment based on the multiple paralleled convolutional neural network and gated recurrent unit. Protection and Control of Modern Power Systems. 2022, 7(1), 39.
[38] Huang D, Liu H, Bi T, Yang Q. GCN-LSTM spatiotemporal-network-based method for post-disturbance frequency prediction of power systems. Global Energy Interconnection. 2022, 5(1), 96–107.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Zhanjie Liu, Xiaonan Gao, Jiaqi Yuan, Yixin Sun
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
