The aim of the presented work was to examine the reliability assessment model on the example of a selected power grid object. The analyzed object was tested based on assumptions about technological breaks that were caused by overvoltage, among others. The study was conducted to check the reliability of integral elements of the power grid object and to assess the change in reliability level as a function of the frequency of inspections. The test results are to determine the optimal frequency of inspections of individual power grid objects in order to increase its reliability. In addition, the possibility of correlating optimal inspection periods resulting from the findings of this paper with periodic inspections of power network facilities was assessed.

Accurate network fault diagnosis in smart substations is key to strengthening grid security. To solve fault classification problems and enhance classification accuracy, we propose a hybrid optimization algorithm consisting of three parts: anti-noise processing (ANP), an improved separation interval method (ISIM), and a genetic algorithm-particle swarm optimization (GA-PSO) method. ANP cleans out the outliers and noise in the dataset. ISIM uses a support vector machine (SVM) architecture to optimize SVM kernel parameters. Finally, we propose the GA-PSO algorithm, which combines the advantages of both genetic and particle swarm optimization algorithms to optimize the penalty parameter. The experimental results show that our proposed hybrid optimization algorithm enhances the classification accuracy of smart substation network faults and shows stronger performance compared with existing methods.