Islanding detection in a distributed generation based hybrid system using intelligent pattern recognition techniques

In this paper, islanding in a distributed generation (DG) based hybrid system is presented based on extracted features of wavelet transform (WT), S-transform (ST), Hyperbolic S-transform (HST) and TT-Transform. The hybrid system comprises of DG resources like photovoltaic (PV), fuel cell (FC) and wind energy systems (WES) connected to the grid. The negative sequence component of the voltage signal extracted at the point of common coupling (PCC) is considered for detection of islanding of these resources from the grid. The study for different scenarios of DG system is presented in the form of time-frequency analysis. The energy content and standard deviation (STD) of HST contour is also reported in order to validate the graphical results. The results demonstrate the advantages of HS-transform, TT-Transform over wavelet transform and S-transform in detection of islanding events under noise-free as well as noisy scenarios.