Application of Various Supervised Machine Learning Techniques for Real Time Fault Detection in Power System

The field of power systems has been greatly impacted by machine learning for fault detection in power lines with the goal of making the current techniques more accurate and efficient. The primary objective is to address the limitations of traditional approaches by developing a more precise and faster fault detection method. The methodology involves the use of MATLAB and Python for designing and training machine learning models. The data undergoes preprocessing to ensure its suitability for model training. Various supervised machine learning methods are explored to identify the most effective model for fault detection. The findings of this study demonstrate that the Gradient Boosting model exhibits a high level of accuracy in recognizing and identifying power line issues with superior speed compared to conventional line fault detection techniques.