IDM based on image classification with CNN. Issue 10 (12th June 2019)

• Record Type: Journal Article
• Authors: Manikonda, Santhosh K.G.; Gaonkar, Dattatraya N.
• Is Part Of: Journal of engineering. Volume 2019:Issue 10(2019)
• Page Start: 7256
• Page End: 7262
• Publication Date: 2019-06-12
• Subjects: support vector machines -- image classification -- learning (artificial intelligence) -- power distribution faults -- time series -- distributed power generation -- convolutional neural nets; time‐series data -- IDM -- support vector machine -- deep learning technique -- detection accuracy -- image classification -- distributed generation -- energy demand -- distributed sources -- DG sources -- operation complex -- islanding detection method -- deep learning approach -- convolution neural network -- CNN; Engineering -- Periodicals; Engineering; Electronic journals; Periodicals; 620.005
• DOI: 10.1049/joe.2019.0025
• Languages: English
• ISSNs: 2051-3305

Abstract

Abstract : Distributed generation (DG) has seen tremendous growth to meet the needs of ever‐increasing energy demand. Most of these distributed sources are renewable in nature and connected at the consumer end. The increasing penetration of DG sources has made their control and operation complex. One of the issues that are responsible for this increased complexity is islanding. This study presents a new islanding detection method (IDM) that is based on deep learning approach, using a convolution neural network (CNN). The proposed method first converts time‐series data to images and then uses them to train and test the designed CNN. A CNN is specifically designed to perform islanding detection. The results using the designed CNN are compared with IDMs based on artificial NN and support vector machine. These comparisons show that islanding detection performed using deep learning technique has better detection accuracy. Also, the proposed method performs well even for noisy data.