Protection of high voltage transmission line connected large scale solar photovoltaic plant using green anaconda optimized machine learning method

Abstract

Transmission lines are widely used engineering systems designed to transport large amounts of power across a country from one location to the furthest points in the other direction. Transmission line protection is a significant concern in power system engineering since transmission lines account for the vast majority of power system faults (85–87%). This paper presents a hybrid artificial neural network and support vector machine technique to detect and classify faults on a transmission line. MATLAB/Simulink software is utilized to simulate various fault and operating conditions on high-voltage transmission lines. The empirical wavelet transform is used to decompose fault transients due to its capability to extract information from the transient signal. This method's optimal hyper-parameter selection is obtained by using the green Anaconda optimization algorithm. The results showed that the proposed technique acquired a high accuracy of 99.86%, precision of 99.23%, sensitivity of 99.23%, specificity of 99.92%, recall of 99.23%, F1-score of 99.23%, Mean Square Error of 0.187, Root Mean Square Error of 0.433 and Mean Absolute Error of 0.031. The proposed technique has been shown to be highly efficient and accurate, making it a reliable classifier for fault identification.