Improved LS-SVM using aco to estimate flashover voltage of polluted insulators

The reliability of insulators under polluted environment is one of the guiding factors in the insulation coordination of high voltage transmission lines. in order to improve understanding of the flashover phenomenon in polluted insulators,several experimental studies and mathematical approaches have been made in last year’s. in this paper,the critical flashover voltage behavior of polluted insulators has been calculated and a hybrid model between machine learning (ml) and optimization technique has been proposed. for this purpose,firstly the ant colony optimization (aco) technique is utilized to optimize the hyper-parameters needed in least squares support vector machines (ls-svm). then,a ls-svm-aco model is designed to establish a nonlinear model between the characteristics of the insulator and the critical flashover voltage. the data used to train the model and test its performance is derived from experimental measurements and a mathematical model. the results obtained from the proposed model are in good accord with other mathematical and experimental results of previous researchers. © school of engineering,taylor’s university.