INTELLIGENT ELECTRICAL POWER PREDICTION AND OPERATIONAL RESPONSE O. PTIMIZATION FOR RELIABLE MICRO GAS TURBINE ENERGY GENERATION
DOI:
https://doi.org/10.69980/0s4fdy73Keywords:
micro gas turbine, electrical power prediction, operational optimization, voltage response, reliabilityAbstract
The accurate prediction of electrical power coupled with identification of the operating conditions that maintain high and stable output is essential for reliable operation of a micro gas turbine. This study characterized voltage-dependent electrical power behaviour, evaluated predictive models, and identified a balanced operating condition for reliable energy generation. Eight experimental runs with micro gas turbines were analysed, and six were used for the development of the model, while two were left for independent testing. Spearman correlation and linear/quadratic regression were used to study the voltage-power relationship, and the models Linear Regression, Random Forest and Gradient Boosting were compared based on the parameters MAE, RMSE and R². Predictor contributions and operating stability were also assessed. Electrical power showed a strong positive association with input voltage (ρ = 0.9163, p < 0.001), while the quadratic voltage-response model achieved R² = 0.8831. Linear Regression provided the strongest independent-test performance, achieving MAE = 8.0342, RMSE = 10.6132, and R² = 0.9998. Recent power-history variables contributed most strongly to predictive accuracy. Operational optimization identified 9.6316 V as the preferred condition, producing mean electrical power of 3101.5303 with a CV of 1.5943%. Through these findings, the advantages of using short-horizon power prediction in conjunction with operating-point optimization in order to ensure reliable energy generation for micro gas turbines are shown.
References
1. Banihabib, R., & Assadi, M. (2022). The role of micro gas turbines in energy transition. Energies, 15(21), 8084.
2. Banihabib, R., Skaug Fadnes, F., Assadi, M., & Bensmann, B. (2024). Optimizing micro gas turbine operation in a microgrid system with natural gas and hydrogen fuel: an artificial intelligence-based approach. Journal of Engineering for Gas Turbines and Power, 146(2), 021005.
3. Bielski, P., Kottonau, D., Bielski, P., & Bielski, P. (2024). Micro Gas Turbine Electrical Energy Prediction [Dataset]. UCI Machine Learning Repository. https://doi.org/10.24432/C58S4T
4. Blaabjerg, F., & Ma, K. (2017). Wind energy systems. Proceedings of the IEEE, 105(11), 2116-2131.
5. Bošnjaković, M., Katinić, M., Santa, R., & Marić, D. (2022). Wind turbine technology trends. Applied Sciences, 12(17), 8653.
6. De Robbio, R. (2023). Micro gas turbine role in distributed generation with renewable energy sources. Energies, 16(2), 704.
7. Dou, Y., Tan, S., & Xie, D. (2023). Comparison of machine learning and statistical methods in the field of renewable energy power generation forecasting: a mini review. Frontiers in Energy Research, 11, 1218603.
8. Du Toit, M., Engelbrecht, N., Oelofse, S. P., & Bessarabov, D. (2020). Performance evaluation and emissions reduction of a micro gas turbine via the co-combustion of H2/CH4/CO2 fuel blends. Sustainable Energy Technologies and Assessments, 39, 100718.
9. Ekechi, A. T. (2020). Conceptual framework for process optimization in gas turbine performance and energy efficiency. International Journal of Multidisciplinary Futuristic Development.
10. Firoozi, A. A., Hejazi, F., & Firoozi, A. A. (2024). Advancing wind energy efficiency: A systematic review of aerodynamic optimization in wind turbine blade design. Energies, 17(12), 2919.
11. Letcher, T. (Ed.). (2017). Wind energy engineering: A handbook for onshore and offshore wind turbines. Academic Press.
12. Li, Q., Zhang, Q., & Zhang, L. (2025). (Off-) Design performance analysis and prediction of micro gas turbine using hybrid fuels (NG & H2) based on dynamic model and neural network. Energy Conversion and Management, 346, 120473.
13. Machado, S., & Zhu, X. (2025). Statistical and Machine Learning Approaches for Electrical Energy Forecasting. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 15(3), e70033.
14. Olsson, T., Ramentol, E., Rahman, M., Oostveen, M., & Kyprianidis, K. (2021). A data-driven approach for predicting long-term degradation of a fleet of micro gas turbines. Energy and AI, 4, 100064.
15. Ssebabi, B., Dinter, F., van der Spuy, J., & Schatz, M. (2019). Predicting the performance of a micro gas turbine under solar-hybrid operation. Energy, 177, 121-135.
16. Strielkowski, W., Vlasov, A., Selivanov, K., Muraviev, K., & Shakhnov, V. (2023). Prospects and challenges of the machine learning and data-driven methods for the predictive analysis of power systems: A review. Energies, 16(10), 4025.
17. Wang, Y., Huang, Y., Wang, Y., Li, F., Zhang, Y., & Tian, C. (2018a). Operation optimization in a smart micro-grid in the presence of distributed generation and demand response. Sustainability, 10(3), 847.
18. Wang, Y., Huang, Y., Wang, Y., Zeng, M., Li, F., Wang, Y., & Zhang, Y. (2018b). Energy management of smart micro-grid with response loads and distributed generation considering demand response. Journal of cleaner production, 197, 1069-1083.
19. Wen, J., Lu, J., Spataru, C., Weng, Y., & Lv, X. (2024). Coordinated intelligent control strategy and power management for marine gas turbine under pulsed load using optimized neural network. Energy, 313, 133719.
20. Xu, X., Yan, Z., Shahidehpour, M., Wang, H., & Chen, S. (2017). Power system voltage stability evaluation considering renewable energy with correlated variabilities. IEEE Transactions on Power Systems, 33(3), 3236-3245.
21. Yang, R., Liu, Y., He, X., & Liu, Z. (2024). An innovative online adaptive high-efficiency controller for micro gas turbine: Design and simulation validation. Journal of Marine Science and Engineering, 12(12), 2150.
22. Yong, C., Li, Y., Zeng, Z., Zhang, Z., Zhang, Z., & Liu, Y. (2020). Coordinated active and reactive power optimization considering load characteristics for active distribution network. Chinese Journal of Electrical Engineering, 6(4), 97-105
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Vanshika Jain
This work is licensed under a Creative Commons Attribution 4.0 International License.
