Interpretable hybrid machine learning models for renewable-powered smart grid stability prediction

P. Sirish Kumar, Challa Chandrika, P. Krishna Rao, P. Kameswara Rao, Sai Kiran Oruganti

Abstract


Power grids today operate under unpredictable and rapidly changing conditions, making it essential to develop reliable predictive systems for stability management. This study explores two hybrid learning frameworks that combine deep feature transformation with ensemble classification to improve grid stability prediction. Specifically, an autoencoder (AE) and a TabTransformer (TT) are used for feature encoding, followed by Extreme Gradient Boosting (XGBoost) classifiers. Additionally, two conventional ensemble models (Random Forest and standalone LightGBM) are evaluated for comparison. Models are assessed using standard classification metrics and stratified cross-validation. The autoencoder-based hybrid model outperforms others by producing enriched feature representations, while the standard LightGBM delivers stable and interpretable results. Although the TabTransformer-based model offers architectural novelty, it exhibits less consistency. These findings highlight that optimal grid stability prediction depends not solely on model complexity but on synergy between feature processing and learning architecture, supporting the development of confidence-aware models for smart grid decision systems.

 

Received: 25 July 2025

Accepted: 30 September 2025

Published: 21 October 2025


Keywords


Grid Stability Prediction; Random Forest; Autoencoder-XGBoost; TabTransformer; Ensemble Classifier; Light GBM

Full Text:

PDF

References


R. Islam, M. A. H. Rivin, S. Sultana, M. A. B. Asif, M. Mohammad, and M. Rahaman, “Machine learning for power system stability and control,” Results in Engineering, vol. 26, p. 105355, Jun. 2025, doi: 10.1016/j.rineng.2025.105355.

S. Song, S. Min, and S. Jung, “Steady-state data-driven dynamic stability assessment in the Korean power system,” Sci Rep, vol. 15, no. 1, p. 7756, Mar. 2025, doi: 10.1038/s41598-025-90798-3.

M. Marković, M. Bossart, and B.-M. Hodge, “Machine learning for modern power distribution systems: Progress and perspectives,” Journal of Renewable and Sustainable Energy, vol. 15, no. 3, May 2023, doi: 10.1063/5.0147592.

P. Lahon, A. B. Kandali, U. Barman, R. J. Konwar, D. Saha, and M. J. Saikia, “Deep Neural Network-Based Smart Grid Stability Analysis: Enhancing Grid Resilience and Performance,” Energies (Basel), vol. 17, no. 11, p. 2642, May 2024, doi: 10.3390/en17112642.

M. Singh and S. Chauhan, “Transient Stability Assessment of Power Systems Integrating Wind Energy Utilizing Detailed Models and a Hybrid Ensemble Technique,” Arab J Sci Eng, Mar. 2025, doi: 10.1007/s13369-025-10036-w.

Z. Wang, L. Zhao, D. Zhang, and C. Yan, “Study on dynamic prediction method for degradation state of electric drive system based on deep learning and uncertainty quantification,” Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, vol. 239, no. 1, 2025, doi: 10.1177/09544070231205063.

V. A. G. Raju, M. Mishra, J. G. Singh, J. Nayak, and P. B. Dash, “Smart grid stability prediction based on Bayesian-optimised LGBM for smarter energy management,” International Journal of Advanced Mechatronic Systems, vol. 11, no. 4, pp. 226–241, 2024, doi: 10.1504/IJAMECHS.2024.143382.

X. Yao, X. Fu, and C. Zong, “Short-Term Load Forecasting Method Based on Feature Preference Strategy and LightGBM-XGboost,” IEEE Access, vol. 10, pp. 75257–75268, 2022, doi: 10.1109/ACCESS.2022.3192011.

G. Porawagamage, K. Dharmapala, J. S. Chaves, D. Villegas, and A. Rajapakse, “A review of machine learning applications in power system protection and emergency control: opportunities, challenges, and future directions,” Frontiers in Smart Grids, vol. 3, Apr. 2024, doi: 10.3389/frsgr.2024.1371153.

J. Chen et al., “An integrative approach to enhance load forecasting accuracy in power systems based on multivariate feature selection and selective stacking ensemble modeling,” Energy, vol. 326, p. 136337, Jul. 2025, doi: 10.1016/j.energy.2025.136337.

A. Binbusayyis and M. Sha, “Stability Prediction in Smart Grid Using PSO Optimized XGBoost Algorithm with Dynamic Inertia Weight Updation,” Computer Modeling in Engineering & Sciences, vol. 142, no. 1, pp. 909–931, 2025, doi: 10.32604/cmes.2024.058202.

P. Singh, N. K. Singh, and A. K. Singh, “Intelligent hybrid method to predict generated power of solar PV system,” Renewable Energy and Sustainable Development, vol. 11, no. 1, p. 141, May 2025, doi: 10.21622/resd.2025.11.1.1264.

S. Kumar, R. Agarwal, and H. Subhadra, “Adaptive bayesian sparse polynomial chaos expansion for voltage balance of an isolated microgrid at peak load,” Renewable Energy and Sustainable Development, vol. 11, no. 1, p. 161, Jun. 2025, doi: 10.21622/resd.2025.11.1.1281.

A. Elhassouny, “Machine learning models for predicting spatiotemporal dynamics of groundwater recharge,” Renewable Energy and Sustainable Development, vol. 10, no. 2, pp. 319–344, 2024, doi: https://dx.doi.org/10.21622/resd.2024.10.2.933.

R. T. Moyo and M. Dewa, “The role of computational intelligence techniques in the advancements of solar photovoltaic systems for sustainable development: a review,” Renewable Energy and Sustainable Development, vol. 8, no. 2, p. 52, Dec. 2022, doi: 10.21622/resd.2022.08.2.052.

I. Alhamrouni et al., “A Comprehensive Review on the Role of Artificial Intelligence in Power System Stability, Control, and Protection: Insights and Future Directions,” Applied Sciences, vol. 14, no. 14, p. 6214, Jul. 2024, doi: 10.3390/app14146214.

Z. Zhang and D. K. Y. Yau, “CoRE: Constrained Robustness Evaluation of Machine Learning-Based Stability Assessment for Power Systems,” IEEE/CAA Journal of Automatica Sinica, vol. 10, no. 2, pp. 557–559, Feb. 2023, doi: 10.1109/JAS.2023.123252.

A. Lakshmanarao, A. Srisaila, T. Srinivasa Ravi Kiran, K. Vasanth Kumar, and C. Sekhar Koppireddy, “An efficient smart grid stability prediction system based on machine learning and deep learning fusion model,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 33, no. 2, p. 1293, Feb. 2024, doi: 10.11591/ijeecs.v33.i2.pp1293-1301.

D. Maizana, A. Rezky, S. Muthia Putri, H. Satria, and M. Mungkin, “Stability analysis of smart grid management system on campus building,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 30, no. 3, p. 1321, Jun. 2023, doi: 10.11591/ijeecs.v30.i3.pp1321-1330.

S. Oyucu, Ş. Sağıroğlu, A. Aksöz, and E. Biçer, “Estimating Smart Grid Stability with Hybrid RNN+LSTM Deep Learning Approach,” in 2024 12th International Conference on Smart Grid (icSmartGrid), IEEE, May 2024, pp. 738–741. doi: 10.1109/icSmartGrid61824.2024.10578179.

M. K. Boutahir, A. Hessane, Y. Farhaoui, and M. Azrour, “An Effective Ensemble Learning Model to Predict Smart Grid Stability Using Genetic Algorithms,” in Advances in Technology for Smart Environment and Energy, 2023, pp. 129–137. doi: 10.1007/978-3-031-25662-2_11.

D. R. Dipto, S. K. Shib, M. T. Rahman, and A. Shufian, “Predictive Analysis of Smart Grid Stability Using Diverse Machine Learning Algorithms,” in 2025 4th International Conference on Robotics, Electrical and Signal Processing Techniques (ICREST), IEEE, Jan. 2025, pp. 307–311. doi: 10.1109/ICREST63960.2025.10914368.

A. Chahal, P. Gulia, N. S. Gill, and J. M. Chatterjee, “Performance Analysis of an Optimized ANN Model to Predict the Stability of Smart Grid,” Complexity, vol. 2022, no. 1, Jan. 2022, doi: 10.1155/2022/7319010.

S. Mohsen, M. Bajaj, H. Kotb, M. Pushkarna, S. Alphonse, and S. S. M. Ghoneim, “Efficient Artificial Neural Network for Smart Grid Stability Prediction,” International Transactions on Electrical Energy Systems, vol. 2023, pp. 1–13, May 2023, doi: 10.1155/2023/9974409.

S. Nagaraju and B. Chandramouli, “Ant-Lion Optimization Algorithm Based Optimal Performance of Micro Grids,” Indonesian Journal of Electrical Engineering and Informatics (IJEEI), vol. 12, no. 1, Mar. 2024, doi: 10.52549/ijeei.v12i1.5119.

A. Zafar, Y. Che, M. Faheem, M. Abubakar, S. Ali, and M. S. Bhutta, “Machine learning autoencoder‐based parameters prediction for solar power generation systems in smart grid,” IET Smart Grid, vol. 7, no. 3, pp. 328–350, Jun. 2024, doi: 10.1049/stg2.12153.

M. Abd Elaziz, I. A. Fares, A. Dahou, and M. Shrahili, “Federated learning framework for IoT intrusion detection using tab transformer and nature-inspired hyperparameter optimization,” Front Big Data, vol. 8, May 2025, doi: 10.3389/fdata.2025.1526480.

F. K. Karim et al., “Optimized LSTM for Accurate Smart Grid Stability Prediction Using a Novel Optimization Algorithm,” Front Energy Res, vol. 12, Aug. 2024, doi: 10.3389/fenrg.2024.1399464.

A. Zafar, Y. Che, M. Ahmed, M. Sarfraz, A. Ahmad, and M. Alibakhshikenari, “Enhancing Power Generation Forecasting in Smart Grids Using Hybrid Autoencoder Long Short-Term Memory Machine Learning Model,” IEEE Access, vol. 11, pp. 118521–118537, 2023, doi: 10.1109/ACCESS.2023.3326415.




DOI: https://dx.doi.org/10.21622/resd.2025.11.2.1509

Refbacks



Copyright (c) 2025 P. Sirish Kumar, Challa chandrika, P. Krishna Rao, P. Kameswara Rao, Sai Kiran Oruganti

Renewable Energy and Sustainable Development

E-ISSN: 2356-8569

P-ISSN: 2356-8518

 

Published by:

Academy Publishing Center (APC)

Arab Academy for Science, Technology and Maritime Transport (AASTMT)

Alexandria, Egypt

resd@aast.edu