Green Machine Learning for Smart Grid Stability Prediction: Performance and Energy-Efficient Evaluation

Authors

Atmane Hadji
LISI Laboratory, Computer Science Department, University Center A. Boussouf Mila, 43000 Mila, Algeria
Farid Boumaza
Computer Science Department, University of Mohamed El Bachir El Ibrahimi, Bordj Bou Arreridj 34030, Algeria. LAPECI Laboratory , University of Oran1, Oran 31000, Algeria
Fatah Hadji
Fundamental Department of Science and Technology , University of Jijel, 18000 Jijel, Algeria University of Bejaia, Faculty of Technology , Laboratory of Mechanics, Materials and Energetic, 06000 Bejaia, Algeria
DOI: https://doi.org/10.52549/ijeei.v14i1.7377
Download PDF
Published: 31-03-2026 • Issue: Vol. 14 No. 1: March 2026 • Section: Regular paper

Abstract

The increasing complexity of modern smart grids necessitates intelligent and sustainable predictive models that ensure system stability while minimizing computational energy consumption. This study explores the concept of Green Machine Learning (GML), which integrates high predictive accuracy with energy-efficient computation to promote sustainability in smart grid systems. Unlike conventional benchmarking studies, we propose a sustainability-oriented evaluation framework based on a dual-metric approach (GreenScore and GreenScore*), enabling the joint assessment of predictive accuracy and computational efficiency. This framework serves as a decision-support tool for selecting models under energy and operational constraints. The results demonstrate that MLP has reached the highest level predictive performance (F1 = 0.9736, AUC = 0.9957), while LightGBM offered the best compromise between accuracy and computational efficiency (F1 = 0.9685, AUC = 0.9941). Although Logistic Regression exhibited minimal energy consumption (execution time = 0.03 s), its accuracy was relatively low (0.8027). According to GreenScore and GreenScore*, LightGBM (GreenScore = 0.66, GreenScore* = 0.2646) and Extra Trees (GreenScore = 1.24, GreenScore* = 0.9449) demonstrate superior energy sustainability, while MLP (GreenScore* = 0.0161) and CatBoost (GreenScore* = 0.2171) reflect lower efficiency. Logistic Regression, despite very low computational cost, has a high GreenScore* (533.8422) due to its extremely low execution time but poor predictive performance. Overall, the study confirms that Green Machine Learning enables a multi-objective optimization between predictive performance and energy efficiency, advancing the development of sustainable smart grid management systems.
Keywords: Green Machine Learning; Smart grid; GreenScore*; Predection stability; Computational Energy; Sustainability

References

S. J. Yeboah, S. Nunoo, J. C. Attachie, W. D. Asihene, et E. Y. Asuamah, “Impact and integration techniques of renewable energy sources on smart grid operations: A systematic review,†Sci. Afr., vol. 2025, no. e02845, 2025.

P. Kumar, K. Kumar, N. Adhikary, et E. L. Tesfaye, “Analysis of control and computational strategies for green energy integration for sociotechnical ecological power infrastructure in Indian and African markets,†Sci. Rep., vol. 15, no. 1, p. 13953, 2025.

F. Ahmed, D. Al Kez, S. McLoone, R. J. Best, C. Cameron, et A. Foley, “Dynamic grid stability in low carbon power systems with minimum inertia,†Renew. Energy, vol. 210, pp. 486–506, 2023.

N. Khosravi, D. Çelik, H. Bevrani, et al., “Microgrid stability: A comprehensive review of challenges, trends, and emerging solutions,†Electr. Power Energy Syst., vol. 170, no. 11082, p. 9, 2025.

M. Shobanke, M. Bhatt, et E. Shittu, “Advancements and future outlook of artificial intelligence in energy and climate change modeling,†Adv. Appl. Energy, p. 100211, 2025.

D. H. Rasheed et S. B. Tambe, “Advancing energy efficiency with smart grids and IoT-based solutions for a sustainable future,†Estidamaa, pp. 36–42, 2024.

A. R. Battula, S. Vuddanti, et S. R. Salkuti, “Review of energy management system approaches in microgrids,†Energies, vol. 14, p. 5459, 2021.

H. M. Soliman, E. Bayoumi, A. Al-Hinai, et M. Soliman, “Robust decentralized tracking voltage control for islanded microgrids by invariant ellipsoids,†Energies, vol. 13, p. 5756, 2020.

A. Swain, S. R. Salkuti, et K. Swain, “An optimized and decentralized energy provision system for smart cities,†Energies, vol. 14, p. 1451, 2021.

V. Veeramsetty, A. Mohnot, G. Singal, et S. R. Salkuti, “Short-term active power load prediction on a 33/11 kV substation using regression models,†Energies, vol. 14, p. 2981, 2021.

A. Musengimana, H. Li, X. Zheng, et Y. Yu, “Small-signal model and stability control for grid-connected PV inverter to a weak grid,†Energies, vol. 14, no. 13, p. 3907, 2021.

H. Benbouhenni et N. Bizon, “Third-order sliding mode applied to the direct field-oriented control of the asynchronous generator for variable-speed contra-rotating wind turbine generation systems,†Energies, vol. 14, p. 5877, 2021.

S. M. Dubey, H. M. Dubey, M. Pandit, et S. R. Salkuti, “Multiobjective scheduling of hybrid renewable energy system using equilibrium optimization,†Energies, vol. 14, p. 6376, 2021.

W. Lee, M. Chae, et D. Won, “Optimal scheduling of energy storage system considering life-cycle degradation cost using reinforcement learning,†Energies, vol. 15, p. 2795, 2022.

F. H. Ezzahra, M. Aatila, M. Lachgar, et al., “Predicting smart grid stability using Machine Learning algorithms,†in Proc. 11th Int. Symp. Signal, Image Video Commun. (ISIVC), IEEE, 2022, pp. 1–6,2022.

G. R. Kumar Reddy, A. Arora, M. S. Kumar, et al., “Smart grid stability prediction using Machine Learning,†in Proc. KILBY 100 7th Int. Conf. Comput. Sci., 2023.

S. Mohsen, M. Bajaj, H. Kotb, et al., “Efficient artificial neural network for smart grid stability prediction,†Int. Trans. Electr. Energy Syst., vol. 2023, no. 1, p. 9974409, 2023.

B. Franović, S. Baressi Šegota, N. Anđelić, et Z. Car, “Decentralized smart grid stability modeling with Machine Learning,†Energies, vol. 16, no. 22, p. 7562, 2023.

X. Wang, X. Zhang, F. Zhou, et al., “Smart grid stability prediction using artificial intelligence: A study based on the UCI smart grid stability dataset,†Sustain. Comput.: Inform. Syst., vol. 2025, p. 101175, 2025.

S. Rai et M. De, “Analysis of classical and Machine Learning based short-term and mid-term load forecasting for smart grid,†Int. J. Sustain. Energy, vol. 40, no. 9, pp. 821–839, 2021.

M. Alazab, S. Khan, S. Krishnan, Q. Pham, M. Reddy, et T. Gadekallu, “A multidirectional LSTM model for predicting the stability of a smart grid,†IEEE Access, vol. 8, pp. 85454–85463, 2020.

A. Ghosh et A. Kole, “A comparative analysis of enhanced Machine Learning algorithms for smart grid stability prediction,†TechRxiv, 2021.

A. Bashir, S. Khan, B. Prabadevi, N. Deepa, W. Alnumay, T. Gadekallu, et P. Maddikunta, “Comparative analysis of Machine Learning algorithms for prediction of smart grid stability,†Int. Trans. Electr. Energy Syst., vol. 31, no. 9, pp. 1–23, 2021.

H. M. Soliman, E. Bayoumi, A. Al-Hinai, et M. Soliman, “Robust decentralized tracking voltage control for islanded microgrids by invariant ellipsoids,†Energies, vol. 13, no. 21, p. 5756, 2020.

R. Wang, Y. Liu, X. Ye, Q. Tang, J. Gou, M. Huang, et Y. Wen, “Power system transient stability assessment based on Bayesian optimized LightGBM,†in Proc. IEEE 3rd Conf. Energy Internet Energy Syst. Integr. (EI2), Changsha, China, pp. 263–268, 2019.

J. Ma, S. Feuerborn, C. Black, et V. Venkatasubramanian, “A comprehensive software suite for power grid stability monitoring based on synchrophasor measurements,†in Proc. IEEE PES Innovative Smart Grid Technol. Conf., Washington, USA, pp. 1–5, 2017.

V. Malbasa, C. Zheng, P. Chen, T. Popovic, et M. Kezunovic, “Voltage stability prediction using active Machine Learning,†IEEE Trans. Smart Grid, vol. 8, no. 6, pp. 3117–3124, 2017.

D. Panda et S. Das, “Regression analysis of grid stability under decentralized control,†in Proc. Int. Conf. Eng. Sci. Ind. Appl., Tokyo, Japan, pp. 1–6, 2019.

M. Gorzałczany, J. Piekoszewski, et F. Rudziński, “A modern data-mining approach based on genetically optimized fuzzy systems for interpretable and accurate smart-grid stability prediction,†Energies, vol. 13, no. 10, pp. 25–59, 2020.

P. Dayananda, et al., “A Machine Learning-based smart grid protection and control framework using Kalman filters for enhanced power management,†J. Eur. Syst. Autom., vol. 57, no. 3, 2024.

M. F. S. Turja, M. M. Hasan, M. Khan, M. N. Rahman, A. Irin, S. Ahmed, et M. M. Islam, “Python under the microscope: A comparative energy analysis of execution methods,†IEEE Access, vol. 13, pp. 191323–191342, 2025.

A. Hadji et M. K. Kholladi, “Disaster information extraction: Evaluation of NLP techniques using JAPE rules, ontologies and Machine Learning approaches,†in Proc. Int. Conf. Comput. Sci. Complex Syst. Appl. (CCSA), Cham: Springer, pp. 294–313, 2024. [Online]. Available: https://link.springer.com/chapter/10.1007/978-3-031-90758-6_22

A. Hadji, F. Boumaza, et D. S. Bali, “Sentiment analysis of digital currency discussions: A Machine Learning and ontology approaches,†in Proc. Int. Conf. Informatics Appl. Math. (IAM), CEUR Workshop Proc., vol. 2239, pp. 22–35, Dec. 2024. [Online]. Available: https://ceur-ws.org/Vol-3922/paper3.pdf

A. Hadji, M. K. Kholladi, et N. Borisova, “Enhancing spatial information extraction from Arabic text: A hybrid approach with ontology and rule-based,†Ingénierie Syst. Inf., vol. 29, no. 4, p. 1261, 2024.

A. Hadji, F. Boumaza, and F. Hadji, “Enhancing smart grid management through machine learning-based hourly energy forecast,†ITEGAM-Journal of Engineering and Technology for Industrial Applications, vol. 11, no. 56, pp. 136–147, 2025.

F. Boumaza, A. Hadji, and A. Aroui, “Efficient allocation of computationally intensive application tasks in NoC-based heterogeneous MPSoCs,†Informatica, vol. 50, no. 6, 2026.

Author Biographies

Atmane Hadji
Dr. Hadji Atmane is an Assistant Professor in the Department of Computer Science at the University Center A. Boussouf, Mila, Algeria. He received a Magister in Computer Science (2012, University of Ouargla) and a Ph.D. in 2025 from the University of Béjaïa. A member of the Laboratory of Intelligent Systems and Informatics, his research interests include machine learning, big data, deep learning, natural language processing, ontologies and the semantic web, information extraction, and sentiment analysis.
Farid Boumaza
Dr. Farid Boumaza is an Assistant Professor in the Department of Computer Science at the University of Mohamed El Bachir El Ibrahimi, Bordj Bou Arreridj, Algeria, where he has been teaching since 2013. He received his Magister degree in Computer Science in 2012 from the University of Oran1, Algeria, and earned his Ph.D. in 2024. He is a member of the LAPECI Laboratory at the University of Oran1, Oran, Algeria. His research interests include Artificial Intelligence, Engineering Optimization, Metaheuristics, Big Data Optimization, and Software Engineering.
Fatah Hadji
Dr. Hadji Fatah is an Assistant Professor in the Department of Fundamental Sciences and Technology at the University of Jijel, Algeria. He earned a Magister in Materials Engineering (2015, University of Jijel) and a Ph.D. (2025, University of Bejaia). A member of the Laboratory of Mechanics, Materials, and Energetics in Bejaia, he has over eight years of experience in industrial energy. His research interests focus on material characterization, nanomaterials, eco-friendly green synthesis, and energetic.

How to Cite

[1]
A. Hadji, F. Boumaza, and F. Hadji, “Green Machine Learning for Smart Grid Stability Prediction: Performance and Energy-Efficient Evaluation”, IJEEI, vol. 14, no. 1, pp. 246–263, Mar. 2026, doi: 10.52549/ijeei.v14i1.7377.