In today’s power system, distributed generation (DG) penetration level has increased to match the ever-increasing demand for energy. DG integration introduces peculiar challenges to the entire power system. Due to the increased DG penetration, these challenges have become technically and economically very important. Effective and fast islanding detection is necessary to prevent power quality degradation, equipment loss, and human life loss. In this study, an islanding detection model based on convolutional neural network (CNN) is proposed. The method utilizes the ability of CNN to perform accurate image classification. It identifies islanding by classifying scalogram images obtained by applying wavelet transform to the concatenated voltage waveforms for each event. The islanding detection model is trained with well-processed images to improve classification accuracy. Noise is incorporated into the data to investigate the susceptibility of the method to noise. The results obtained prove that the proposed islanding detection model can handle the problem of islanding detection.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.