High Impedance Fault Detection on Microgrids Considering the Impact of VSC Based Generation

This paper presents an evaluation of the impacts simulation models for high impedance faults detection in microgrids with distributed generators interfaced by voltage source converters. Detailed are used to consider frequency switching power electronics and, consequently, associated harmonic distortions. Thus, systems a higher degradation current sine waveform, fault characteristics such as nonlinearity, asymmetry, and randomness may remain hidden, compromising performance some existing techniques. Such not commonly literature. To evaluate impact model’s complexity, pretrained deep convolutional neural networks on imageNet database is adapted classify waveform based time-frequency representation image. The proposed method designed tested using microgrid model CIGRE European medium distribution network benchmark. data set considers operating islanded connected manner, radial ring topology, transients at different locations network. results indicate that methods converters need be detailed achieve better accuracy, classifier presented accurate robust detection.