Robust ensemble learning for smart grid stability prediction under operating variability

P. Sirish Kumar, K. Kavitha, Ch. Rajasekhar, M.D.R. Siva Santhosh, M.S.R Naidu, Sai Kiran Oruganti

Abstract


The rapid integration of renewable energy sources has made modern smart grids more dynamic and sensitive to fluctuations in generation and demand. Under such conditions, maintaining grid stability requires prediction models that remain reliable not only during normal operation but also under increased variability. This study presents a comparative perturbation-robustness assessment of four advanced ensemble learning models for smart grid stability prediction: Light Gradient Boosting Machine (LightGBM), Extreme Gradient Boosting (XGBoost), a Hybrid LightGBM–XGBoost model (Hybrid-LXGB), and an Out-of-Fold Stacking ensemble (OOF-Stacking). To represent perturbation-driven operating uncertainty, Gaussian perturbation-based variability was introduced at multiple severity levels. Model performance was evaluated using predictive accuracy, relative degradation, error amplification behavior, and sensitivity analysis. The results indicate that all models perform strongly under standard conditions; however, clear differences emerge as variability increases. XGBoost delivers marginally higher overall predictive performance, while LightGBM demonstrates greater resistance to performance degradation under more challenging scenarios. The Hybrid-LXGB and OOF-Stacking models also achieve competitive and stable results, confirming the effectiveness of ensemble learning approaches for smart grid stability prediction applications. Further analysis reveals that severe variability is the primary source of performance loss, leading to accuracy reductions exceeding 22% across the evaluated models. This observation highlights the importance of assessing prediction systems beyond clean benchmark settings. The findings suggest that model selection for smart grid stability prediction applications should consider perturbation robustness alongside conventional accuracy metrics. Overall, this study provides a variability-oriented evaluation framework for analyzing ensemble learning behavior in smart grid stability prediction applications.

 

Received: 11 May 2026

Accepted: 02 September 2026

Published: 14 September 2026


Keywords


Ensemble Learning, LightGBM, Perturbation Robustness, Smart Grid Stability, Variability Analysis, XGBoost.

Full Text:

PDF

References


M. B. Prasad, P. Ganesh, K. V. Kumar, P. A. Mohanarao, A. Swathi, and V. Manoj, “Renewable Energy Integration in Modern Power Systems: Challenges and Opportunities,” in International Conference on Renewable Energy Resources and Applications (ICRERA-2024), E3S Web of Conferences, Jan. 2024, pp. 1–10. Accessed: Sep. 08, 2026. [Online]. Available: https://typeset.io/papers/renewable-energy-integration-in-modern-power-systems-9byobzb5myno

S. Singh and S. Singh, “Advancements and Challenges in Integrating Renewable Energy Sources Into Distribution Grid Systems: A Comprehensive Review,” Journal of energy resources technology, vol. 146, no. 9, pp. 1–37, May 2024, doi: 10.1115/1.4065503.

M. Cavus, “Advancing Power Systems With Renewable Energy and Intelligent Technologies: A Comprehensive Review on Grid Transformation and Integration,” Electronics, vol. 14, no. 6, p. 1159, 2025, doi: 10.3390/electronics14061159.

P. Das et al., “Data-Driven Demand Response Optimization With Hybrid Forecasting and AC Power Flow Validation in Renewable-Integrated Distribution Systems,” Renewable Energy and Sustainable Development, vol. 12, no. 1, p. 216, Jun. 2026, doi: 10.21622/resd.2026.12.1.1913.

N. A. Sharma, “Current Trends and Future Directions in Renewable Energy Systems,” International Journal for Research Publication and Seminars, vol. 15, no. 2, pp. 186–198, Jun. 2024, doi: 10.36676/jrps.v15.i2.1408.

M. Khalil and S. A. Sheikh, “Advancing Green Energy Integration in Power Systems for Enhanced Sustainability: A Review,” IEEE Access, vol. 12, pp. 151669–151692, Jan. 2024, doi: 10.1109/access.2024.3472843.

M. S. Eltohamy et al., “Enhancing Electric Grid Flexibility for the Integration of Variable Renewable Energy: Challenges, Innovations, and Future Directions,” IEEE Access, vol. 14, pp. 23080–23109, 2026, doi: 10.1109/access.2026.3660837.

A. Joshan, “Emerging Trends and Advanced Techniques in Power System Optimization for Future Smart Grids POWER,” CONTROL AND DATA PROCESSING SYSTEMS, vol. 2, no. 2, pp. 26–38, 2025, doi: 10.30511/pcdp.2025.2060096.1022.

J. J. Moreno Escobar, O. Morales Matamoros, R. Tejeida Padilla, I. Lina Reyes, and H. Quintana Espinosa, “A Comprehensive Review on Smart Grids: Challenges and Opportunities,” Sensors, vol. 21, no. 21, p. 6978, Oct. 2021, doi: 10.3390/s21216978.

S. K. Fasogbon et al., “Optimization of Energy Grid Efficiency With Machine Learning: A Comprehensive Review of Challenges and Opportunities,” Renewable and Sustainable Energy Reviews, vol. 223, p. 115980, Jul. 2025, doi: 10.1016/j.rser.2025.115980.

A. Sundaramurthy, K. Ramasamy, D. Velusamy, and C. Vaithiyalingam, “Enhancing Smart Grid Stability: Data-Driven Predictive Modeling in Distribution Systems,” International Journal of Electrical and Electronics Research, vol. 12, no. 2, pp. 623–631, Jun. 2024, doi: 10.37391/ijeer.120239.

M. Esmaeili Shayan, M. Petrollese, S. H. Rouhani, S. Mobayen, A. Zhilenkov, and C. L. Su, “An Innovative Two-Stage Machine Learning-Based Adaptive Robust Unit Commitment Strategy for Addressing Uncertainty in Renewable Energy Systems,” International Journal of Electrical Power & Energy Systems, vol. 160, p. 110087, Sep. 2024, doi: 10.1016/j.ijepes.2024.110087.

P. N. Papadopoulos, S. Chatzivasileiadis, and A. Marot, “Can Machine Learning Help Keep the System Secure?: Power Systems and Change Addressing the Increasing Complexity and Uncertainty During the Energy Transition,” IEEE Power and Energy Magazine, vol. 22, no. 6, pp. 100–111, Nov. 2024, doi: 10.1109/mpe.2024.3421388.

A. M. Ali, O. K. Dawoud, O. A. Ghoneim, and M. Abdel-Basset, “Machine Learning Models for Smart Grid Stability Prediction: A Comparative Analysis,” Scientific Reports, vol. 16, no. 1, p. 12694, Apr. 2026, doi: 10.1038/s41598-026-47385-x.

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, p. 1371153, Apr. 2024, doi: 10.3389/frsgr.2024.1371153.

A. Al-Ataby and H. Attia, “Deep Learning-Based Stability Prediction for Electrical Grids: A Data-Driven Approach,” in 2024 17th International Conference on Development in eSystem Engineering (DeSE), Khorfakkan, United Arab Emirates, Nov. 2024, pp. 574–578. Accessed: Sep. 08, 2026. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/10912018/

J. Li, S. Zhou, Y. Xu, M. Zhu, and L. Ye, “A Multi-Band Uncertainty Set Robust Method for Unit Commitment With Wind Power Generation,” International Journal of Electrical Power & Energy Systems, vol. 131, p. 107125, Oct. 2021, doi: 10.1016/j.ijepes.2021.107125.

S. Chatzivasileiadis, A. Venzke, J. Stiasny, and G. Misyris, “Machine Learning in Power Systems: Is It Time to Trust It?,” IEEE Power and Energy Magazine, vol. 20, no. 3, pp. 32–41, May 2022, doi: 10.1109/mpe.2022.3150810.

M. Sasmal, P. Das, B. Pal, S. Ghosh, and S. Dutta, “Quantum-Based Hybrid Framework for Adaptive Congestion Management in Smart Grids With Stochastic Renewable Penetration,” Renewable Energy and Sustainable Development, vol. 12, no. 1, p. 173, May 2026, doi: 10.21622/resd.2026.12.1.1910.

R. R. Elbanna, M. H. ElMessmary, H. Diab, and M. Abdelsalam, “A Smart Hybrid Optimization Model for DSSE in Renewable Energy-Powered Distribution Networks,” Renewable Energy and Sustainable Development, vol. 11, no. 2, p. 314, Sep. 2025, doi: 10.21622/resd.2025.11.2.1271.

J. Oelhaf et al., “A Scoping Review of Machine Learning Applications in Power System Protection and Disturbance Management,” International Journal of Electrical Power & Energy Systems, vol. 172, p. 111257, Oct. 2025, doi: 10.1016/j.ijepes.2025.111257.

M. K. Boutahir, A. Hessane, Y. Farhaoui, and M. Azrour, “An Effective Ensemble Learning Model to Predict Smart Grid Stability Using Genetic Algorithms,” in Advanced Technology for Smart Environment and Energy, J. Mabrouki, A. Mourade, A. Irshad, and S. Chaudhry, Eds., Cham, Switzerland: Springer, 2023, pp. 129–137.

E. Marevac, E. Kadusic, C. Ruland, and N. Zivic, “Application of Deep Learning and Neural Networks for Smart Grid Stability Predictions,” in 2024 IEEE 12th International Conference on Smart Energy Grid Engineering (SEGE), Oshawa, ON, Canada, Aug. 2024, pp. 84–89.

P. S. Kumar, C. Chandrika, P. K. Rao, P. K. Rao, and S. K. Oruganti, “Interpretable Hybrid Machine Learning Models for Renewable-Powered Smart Grid Stability Prediction,” Renewable Energy and Sustainable Development, vol. 11, no. 2, p. 397, Oct. 2025, doi: 10.21622/resd.2025.11.2.1509.

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.

G. Ke et al., “LightGBM: A Highly Efficient Gradient Boosting Decision Tree,” in Advances in Neural Information Processing Systems (NeurIPS), 2017, pp. 3146–3154.

T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD ’16, vol. 1, no. 1, pp. 785–794, Aug. 2016, doi: 10.1145/2939672.2939785.

L. Rokach, “Ensemble-Based Classifiers,” Artificial Intelligence Review, vol. 33, no. 1, pp. 1–39, Nov. 2009, doi: 10.1007/s10462-009-9124-7.

V. Coscrato, M. H. de A. Inácio, and R. Izbicki, “The NN-Stacking: Feature Weighted Linear Stacking Through Neural Networks,” Neurocomputing, vol. 399, pp. 141–152, Jul. 2020, doi: 10.1016/j.neucom.2020.02.073.

C. Yarramsetty, T. Moger, and D. Jena, “A Hybrid Model of Convolutional Neural Network and an Extreme Gradient Boosting for Reliability Evaluation in Composite Power Systems Integrated With Renewable Energy Resources,” Electrical Engineering, vol. 107, no. 3, pp. 3495–3510, Sep. 2024, doi: 10.1007/s00202-024-02683-3.

J. Bergstra and Yoshua Bengio, “Random Search for Hyper-Parameter Optimization,” Journal of machine learning research, vol. 13, no. 10, pp. 281–305, 2017, doi: 10.5555/2503308.2188395.

I. Goodfellow, J. Shlens, and C. Szegedy, “Explaining and Harnessing Adversarial Examples,” arXiv, Dec. 2014, doi: 10.48550/arxiv.1412.6572.

T. A. Rajaperumal and C. C. Columbus, “Enhanced Wind Power Forecasting Using Machine Learning, Deep Learning Models and Ensemble Integration.,” PubMed, vol. 15, no. 1, pp. 20572–20572, Jul. 2025, doi: 10.1038/s41598-025-05250-3.

P. Breviglieri, T. Erdem, and S. Eken, “Predicting Smart Grid Stability With Optimized Deep Models,” SN Computer Science, vol. 2, no. 2, Feb. 2021, doi: 10.1007/s42979-021-00463-5.

V. Arzamasov, K. Bohm, and P. Jochem, “Towards Concise Models of Grid Stability,” in 2018 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), Aalborg, Denmark, Oct. 2018, pp. 1–6.

F. Meißner, T. Sous, C. Ziesemann, P. Wirtz, F. Klein-Helmkamp, and A. Moser, “Developing a Benchmark Grid Model for Future Congestion Management and Stability Analysis,” in 2024 IEEE PES Innovative Smart Grid Technologies Europe (ISGT EUROPE), Dubrovnik, Croatia, Oct. 2024, pp. 1–5.

C. U. Osuagwu, “Advanced Grid Management Strategies for Mitigating Stability Challenges in High Renewable Energy Penetration Scenarios,” CogNexus, vol. 1, no. 02, pp. 119–139, May 2025, doi: 10.63084/cognexus.v1i02.93.

B. Schäfer, D. Witthaut, M. Timme, and V. Latora, “Dynamically Induced Cascading Failures in Power Grids,” Nature Communications, vol. 9, no. 1, p. 1975, May 2018, doi: 10.1038/s41467-018-04287-5.




DOI: https://dx.doi.org/10.21622/resd.2026.12.2.2146

Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 P. Sirish Kumar, K. Kavitha, Ch. Rajasekhar, M.D.R. Siva Santhosh, M.S.R Naidu, 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