FOREX Press I. J. of Electrical & Electronics Research
Support Open Access
  • Home/
  • IJEER-140226

Review Article |

Evaluation of Random Forest Algorithm Performance in Predicting the Flashover Voltage of Polluted Insulators

Author(s): Rama Alkhtiar1*, Professor Jamal Alnasseir2, Professor George Isber3

Published In : International Journal of Electrical and Electronics Research (IJEER)        Volume 14, Issue 2

Publisher : FOREX Publication

Published : 30 June 2026

e-ISSN : 2347-470X

Page(s) : 507-516

DOI: https://doi.org/10.37391/IJEER.140226

Abstract

This study aims to evaluate the capability of the Random Forest model to predict the flashover voltage of polluted insulators, with particular emphasis on the effect of hyperparameter tuning strategies on model accuracy and stability. A two-stage methodology was adopted. In the first stage, Grid Search and Particle Swarm Optimization were compared for tuning the model hyperparameters using a published dataset of cap-and-pin insulators. The results showed close agreement between the two methods in terms of the mean root mean square error, with a slight accuracy advantage for Particle Swarm Optimization, whereas Grid Search provided higher stability and greater computational simplicity. Accordingly, the Grid Search–tuned Random Forest model was adopted in the second stage, where its performance was evaluated after merging the published data with local laboratory measurements obtained at the High Voltage Laboratory of Damascus University, Syria. The model demonstrated high predictive performance under 70/30 and 80/20 training/testing splits. In addition, ten-fold cross-validation confirmed the stability of the model performance across different data partitions. The feature-importance analysis revealed that surface conductivity was the most influential factor affecting flashover voltage, followed by the geometrical characteristics of the insulator. The results confirm that the Grid Search–tuned Random Forest model provides an effective and initially generalizable tool for predicting the flashover voltage of polluted insulators. However, further expansion of the laboratory database is recommended to improve the reliability of practical applications.

Keywords: Polluted Insulators, Flashover Voltage, Random Forest, Grid Search, Particle Swarm Optimization, Surface Conductivity.




Rama Alkhtiar, PhD Candidate, Department of Electrical Engineering, University of Latakia, Syria; Email: rama.alkhtiar@latakia-univ.edu.sy

Professor Jamal Alnasseir, Professor, Department of Electrical Power, Faculty of Mechanical and Electrical Engineering, Damascus University, Damascus, Syria; Email: jamal.nassier@damascusuniversity.edu.sy

Professor George Isber, Professor, Department of Electrical Power, Faculty of Mechanical and Electrical Engineering, Latakia University, Latakia, Syria; Email: George.Isber@latakia-univ.edu.sy

    [1] L. Taibaoui, A. Mahdjoubi, and B. Zegnini, "Optimizing artificial neural networks with particle swarm optimization for accurate prediction of insulator flashover voltage under dry and rainy conditions," ITEGAM-JETIA, vol. 11, no. 51, pp. 213-219, 2025. doi: 10.5935/jetia.v11i51.1467.
    [2] D. Doufene, S. Benharat, S. Bouazabia, and S. A. Bessedik, "Hybrid Grey Wolf and Finite Element Method (GWO-FEM) Algorithm for Enhancing High Voltage Insulator String Performance in Wet Pollution Conditions," Engineering, Technology & Applied Science Research, vol. 12, no. 3, pp. 8765-8771, Jun. 2022. doi: 10.48084/etasr.4978.
    [3] L. Taibaoui, A. Mahdjoubi, and B. Zegnini, "Optimizing the prediction of lightning impulse withstand voltage for glass insulators using ANFIS enhanced with particle swarm optimization (PSO)," TEM Journal, vol. 14, no. 2, pp. 1725-1732, 2025. doi: 10.18421/TEM142-70.
    [4] F. V. Topalis, I. F. Gonos, and I. A. Stathopulos, "Dielectric behaviour of polluted porcelain insulators," IEE Proceedings - Generation, Transmission and Distribution, vol. 148, no. 4, pp. 269-274, Jul. 2001. doi: 10.1049/ip-gtd:20010258.
    [5] S. Kherfane, R. L. Kherfane, M. A. Moussa, and B. Toual, "Determining critical flashover voltage for various contaminated insulators using a hybrid approach of whale optimization and particle swarm optimization," Gongcheng Kexue Yu Jishu/Advanced Engineering Science, vol. 55, no. 2, pp. 260-274, Sep. 2023. doi: 10.5281/zenodo.4651203.
    [6] R. Zahedi Khatir, M. Mirzaie, and H. Mahdavi, "Analysis of Flashover Voltage of Porcelain and Glass Insulators under Different Temperatures with Various Levels of Pollution and Humidity," Journal of Operation and Automation in Power Engineering, vol. 14, no. 4, pp. 257–266, Dec. 2026. doi: 10.22098/JOAPE.2025.15614.2201. [Online]. Available: https://joape.uma.ac.ir/article_4248.html
    [7] A. Ali, A. R. Bhatti, A. Rasool, F. U. Rehman, M. A. Khan, A. Ali, and A. Sherefa, "Performance analysis of high voltage disc insulators with different profiles in clean and polluted environments using flashover, withstand voltage tests and finite element analysis," Scientific Reports, vol. 14, no. 1, p. 20299, 2024. doi: 10.1038/s41598-024-71392-5.
    [8] A. A. Gialketsi, V. T. Kontargyri, I. F. Gonos, and I. A. Stathopulos, "Estimation of the flashover voltage on insulators using artificial neural networks," WSEAS Transactions on Circuits and Systems, vol. 4, no. 5, pp. 373-378, May 2005.
    [9] S. Al Alawi, M. A. Salam, A. A. Maqrashi, and H. Ahmad, "Prediction of flashover voltage of contaminated insulator using artificial neural networks," Electric Power Components and Systems, vol. 34, no. 8, pp. 831-840, Aug. 2006. doi: 10.1080/15325000600561563.
    [10] V. T. Kontargyri, G. J. Tsekouras, A. A. Gialketsi, and P. A. Kontaxis, "Comparison between artificial neural networks algorithms for the estimation of the flashover voltage on insulators," in Proc. 9th WSEAS Int. Conf. Neural Networks (NN'08), Sofia, Bulgaria, May 2008, pp. 225-230.
    [11] B. Zegnini, M. Belkheiri, and D. Mahi, "Modeling flashover voltage (FOV) of polluted HV insulators using artificial neural networks (ANNs)," in Proc. Int. Conf. Electrical and Electronics Engineering (ELECO), Bursa, Turkey, Dec. 2009, pp. I-336-I-340. doi: 10.1109/ELECO.2009.5355301.
    [12] U. Sajjad, A. Arshad, J. Ahmad, and S. Shoaib, "Application of artificial neural network in predicting flashover behaviour of outdoor insulators under polluted conditions," in Proc. IEEE Conf. Russian Young Researchers in Electrical and Electronic Engineering (ElConRus), St. Petersburg, Russia, Jan. 2021, pp. 2868-2873. doi: 10.1109/ElConRus51938.2021.9396388.
    [13] K. Erenturk, "Adaptive-network-based fuzzy inference system application to estimate the flashover voltage on insulator," Instrumentation Science & Technology, vol. 37, no. 4, pp. 446-461, Jul. 2009. doi: 10.1080/10739140903087873.
    [14] S. A. Bessedik and H. Hadi, "Prediction of flashover voltage of insulators using adaptive neuro-fuzzy inference system," Journal of Electrical Engineering, vol. 13, no. 1, pp. 1-8, Jan. 2013.
    [15] G. E. Asimakopoulou, V. T. Kontargyri, G. J. Tsekouras, C. N. Elias, F. E. Asimakopoulou, and I. A. Stathopulos, "A fuzzy logic optimization methodology for the estimation of the critical flashover voltage on insulators," Electric Power Systems Research, vol. 81, no. 2, pp. 580-588, Feb. 2011. doi: 10.1016/j.epsr.2010.10.024.
    [16] Y. Bourek, N. M'Ziou, and H. Benguesmia, "Prediction of flashover voltage of high-voltage polluted insulator using artificial intelligence," Transactions on Electrical and Electronic Materials, vol. 19, no. 1, pp. 1-10, Jan. 2018. doi: 10.1007/s42341-018-0010-3.
    [17] B. Zegnini, A. H. Mahdjoubi, and M. Belkheiri, "A least squares support vector machines (LS-SVM) approach for predicting critical flashover voltage of polluted insulators," in Proc. IEEE Conf. Electrical Insulation and Dielectric Phenomena (CEIDP), Cancun, Mexico, Oct. 2011, pp. 403-406. doi: 10.1109/CEIDP.2011.6232680.
    [18] A. Mahdjoubi, B. Zegnini, and M. Belkheiri, "A LS-SVM (least squares support vector machines) approach for predicting critical flashover voltage of polluted insulators," Journal of Energy and Power Engineering, vol. 7, no. 2, pp. 355-360, Feb. 2013.
    [19] A. Mahdjoubi, B. Zegnini, and M. Belkheiri, "Kernels functions for squares support vector machines (LS-SVM) to diagnose HV polluted insulator," in Proc. 9ème Conf. Nationale sur la Haute Tension (CNHT'2013), Laghouat, Algeria, Apr. 2013, pp. 269-274.
    [20] A. Mahdjoubi, B. Zegnini, M. Belkheiri, and T. Seghier, "Fixed least squares support vector machines for flashover modelling of outdoor insulators," Electric Power Systems Research, vol. 173, pp. 29-37, Aug. 2019. doi: 10.1016/j.epsr.2019.03.010.
    [21] A. Mahdjoubi, B. Zegnini, and M. Belkheiri, "Prediction of critical flashover voltage of polluted insulators under sec and rain conditions using least squares support vector machines (LS-SVM)," Diagnostyka, vol. 20, no. 1, pp. 49-54, Nov. 2019. doi: 10.29354/diag/99854.
    [22] H. Zhao, "Prediction of pollution flashover voltage of insulators based on genetic algorithm," in Proc. 2020 Int. Symp. Advances in Informatics, Electronics and Education (ISAIEE 2020), Dec. 2020, pp. 46-53. doi: 10.25236/isaiee.2020.010.
    [23] S. A. Bessedik and H. Hadi, "Prediction of flashover voltage of insulators using least squares support vector machine with particle swarm optimisation," Electric Power Systems Research, vol. 104, pp. 87-92, Nov. 2013. doi: 10.1016/j.epsr.2013.06.013.
    [24] S. A. Bessedik, H. Hadi, and R. Djekidel, "Improved least squares support vector machines to estimate flashover voltage of insulators," in Proc. 4th Int. Conf. Electrical Engineering (ICEE), Apr. 2016.
    [25] S. Kherfane, R. L. Kherfane, A. Amari, N. Kherfane, F. Khoudja, B. Toual, and M. A. Moussa, "Estimation of the critical flashover voltage for different polluted insulators by particle swarm optimization," International Journal of Advanced Studies in Computer Science & Engineering, vol. 11, no. 7, pp. 1-8, 2022.
    [26] L. Taibaoui, A. Mahdjoubi, and B. Zegnini, "LS-SVM improvement using PSO and GWO to determine flashover voltage of polluted insulators," in 1st International Conference on Innovative Academic Studies (ICIAS), Konya, Turkey, Sep. 2022.
    [27] L. Taibaoui, A. Mahdjoubi, and B. Zegnini, "Enhanced prediction of insulator flashover voltage using artificial neural networks optimized with particle swarm optimization," Engineering, Technology & Applied Science Research, vol. 15, no. 4, pp. 25710-25718, Aug. 2025. doi: 10.48084/etasr.10330.
    [28] S. He, Y. Han, Z. Zhao, W. Huang, et al., “Experimental database and prediction model of insulators flashover under lightning impulse,” IEEE Transactions on Instrumentation and Measurement, vol. PP, no. 99, pp. 1–1, Jan. 2025, doi: 10.1109/TIM.2025.3568940.
    [29] S. He, Y. Han, Z. Zhao, G. Liu, L. Qu, Z. Huang, Y. Zhang, B. Liu, Z. Wu, and L. Li, "Intelligent prediction of 110kV insulator lightning flashover criteria based on random forest," Electric Power Systems Research, vol. 232, p. 110423, Jul. 2024, doi: 10.1016/j.epsr.2024.110423.
    [30] L. Breiman, “Random Forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
    [31] R. M. Alkhtiar, J. Alnassier, G. Isber, and I. Alwazah, "Flashover Voltage Prediction of Polluted Insulators Using Extreme Gradient Boosting (XGBoost)," in Proc. 2026 8th Int. Youth Conf. Radio Electronics, Electrical and Power Engineering (REEPE), 2026, doi: 10.1109/REEPE69046.2026.11481319.

Rama Alkhtiar, Jamal Alnasseir, and George Isber (2026), Evaluation of Random Forest Algorithm Performance in Predicting the Flashover Voltage of Polluted Insulators . IJEER 14(2), 507-516. DOI: 10.37391/IJEER.140226.