Centralized Voltage Signal-Based Fault Detection and Classification for Islanded AC Microgrid

Abstract

Insignificant fault current in inverter-based islanded AC microgrids makes fault detection challenging. This paper introduces a voltage signal-based fault assessment method for islanded AC microgrids. It considers a new set of features such as instantaneous jumps in amplitude, phase angle and frequency of voltage signal for fault detection and classification. Hilbert transform is used to extract the above features in the time domain. The proposed method can detect any kind of disturbance occurring in the system including step changes in loads and generations and faults, within a cycle. It can also identify whether the detected disturbance is a fault or a non-fault disturbance, by considering the rate of change of frequency calculated over a cycle in addition to the instantaneous jumps in voltage. Fault type classification is performed with the introduced instantaneous features, where support vector machine and artificial neural network classifiers are trained separately, and their performances are tested with unknown test data. The proposed method is validated with balanced as well as unbalanced islanded AC microgrid systems. Further, the performance of the proposed method is verified with both clean and noisy data.