A Fast Response Fault Detection Technique for HVAC Transmission Line Using Machine Learning

High voltage alternating current (HVAC) transmission lines are the only way to transmit electrical energy from the power plant to the utilities. There are several types of transmission line faults that can interrupt the power supply, sometimes even resulting in national blackout. To ensure a highly reliable power supply system, detecting the faults in the quickest of time is crucial. This research used machine learning and neural network algorithm to find five different types of faults using data from a real power transmission line in Bangladesh. Apart from the accuracy of the methods, the focus was given on the response time in identifying the faults. The two boosting methods CatBoost and XGBoost stood out as the most precise among all the algorithms, achieving excellent accuracy and detection time in between 20 ms to 30 ms. The response time of all the methods was found to be in millisecond range, making them perfect for not only long term faults, but also to be implied in transient fault analysis.