A novel method to detect and classify High Impedance Fault in EV integrated distribution system

With the growing adoption of electric vehicles (EVs) and the integration of renewable energy sources in power distribution systems, the need to ensure safe and reliable operation becomes paramount. High Impedance Faults (HIFs) are a particular concern due to their elusive nature and potential to cause electrical fires and equipment damage. This abstract presents a study on the diagnosis of HIFs in distribution systems integrated with electric vehicles. The proposed diagnosis method combines advanced monitoring techniques, fault detection algorithms, and machine learning approaches to accurately identify and locate HIFs. By leveraging the data collected from smart meters, phasor measurement units, and EV charging infrastructure, a comprehensive system-level analysis is performed to distinguish HIFs from other faults and normal operation. In this paper, a novel method based on RADWT & SVM is used to detect and classify high impedance faults in electrical distribution system. Rational dilation wavelet transform is used for feature extraction and SVM is used for fault detection and classification. Necessary simulations are carried out in MATLAB and verified with experimental setup.