Heterogeneous Multi-ml Approach Implemented in Hvdc Transmission Line

Abstract

The research article describes a system of machine architecture for protection of transmission lines of HVDC, in which multiple models of ML (KNN and SVM) are employed for fault classification and recognition. The K-Nearest Neighbor classifier is intended to serve two functions. It detects the type of fault as well which serves as a backup module for the starting unit's doubtful fault declaration. From a single-end single measurement, a feature vector consisting of standard deviations gradients and of DC and harmonic current, DC voltage, and correlation coefficients is retrieved. By simulating different states that are non-fault and fault states on a data set having training and test cases are obtained. The ML algorithm is trained in MATLAB and evaluated on a total of 2220 severe instances. The acquired results demonstrated the efficacy of the suggested method in detecting and distinguishing between various internal and external/pseudo problems.In this paper we will discuss how the ANN model Simulink in the MATLAB is used for researching, collecting, and evaluating 456 data sets.