An image classification based approach for islanding detection in a sustainable distributed generation system using convolutional neural network

ADENUGBA, FAVOUR TOLUWANIMI and Orovwode, H. E. and Ademola, O. F. (2021) An image classification based approach for islanding detection in a sustainable distributed generation system using convolutional neural network. In: 5th International Conference on Science and Sustainable Development, 2021, Online.

PDF Download (1MB)

Abstract

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.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Scalogram, distributed generation (DG), unintentional islanding, convolutional neural network (CNN), islanding detection.
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions:	Faculty of Engineering, Science and Mathematics > School of Electronics and Computer Science
Depositing User:	Patricia Nwokealisi
Date Deposited:	02 Dec 2024 15:22
Last Modified:	02 Dec 2024 15:22
URI:	http://eprints.covenantuniversity.edu.ng/id/eprint/18630

Actions (login required)

View Item