Machine Learning-Based Image Pattern Recognition Using Histogram of Oriented Gradient for Islanding Detection
A vital issue faced by the distribution network is the occurrence of unintentional islanding. The failure to identify unintentional islanding results in significant implications for both the power system and human lives. In this paper, a novel machine learning islanding detection method (IDM) based...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10975757/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850272249128419328 |
|---|---|
| author | Kumaresh Pal Kumari Namrata Ashok Kumar Akella Manoj Gupta Pannee Suanpang Aziz Nanthaamornphong |
| author_facet | Kumaresh Pal Kumari Namrata Ashok Kumar Akella Manoj Gupta Pannee Suanpang Aziz Nanthaamornphong |
| author_sort | Kumaresh Pal |
| collection | DOAJ |
| description | A vital issue faced by the distribution network is the occurrence of unintentional islanding. The failure to identify unintentional islanding results in significant implications for both the power system and human lives. In this paper, a novel machine learning islanding detection method (IDM) based on image classification utilizing the histogram of oriented gradient (HOG) feature is proposed. In particular, the set of parameters are utilized, namely total harmonic distortion (THD) of both three phase currents and voltages, and rate of change of negative sequence voltage, are first transformed into time-frequency representations (i.e., spectrograms via the short time Fourier transform, and scalograms through continuous wavelet transform). Then, the HOG features are extracted from these images and used to train the machine learning (ML) algorithms to distinguish between occurrences of islanding and non-islanding events. Performance metrics including F1 score, recall, accuracy, precision and misclassification error are employed in the assessment process. Numerical results show that our image-based detector achieves faster detection times and higher detection accuracy versus state-of-art methods, thus confirming the validity of such approach for identifying islanding events. |
| format | Article |
| id | doaj-art-4f7753dddc54468bb72f792ea0502ff4 |
| institution | OA Journals |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-4f7753dddc54468bb72f792ea0502ff42025-08-20T01:51:54ZengIEEEIEEE Access2169-35362025-01-0113743967441610.1109/ACCESS.2025.356414510975757Machine Learning-Based Image Pattern Recognition Using Histogram of Oriented Gradient for Islanding DetectionKumaresh Pal0https://orcid.org/0009-0009-3597-7202Kumari Namrata1https://orcid.org/0000-0002-2548-8239Ashok Kumar Akella2Manoj Gupta3https://orcid.org/0000-0002-4274-4927Pannee Suanpang4https://orcid.org/0000-0002-0059-2603Aziz Nanthaamornphong5https://orcid.org/0000-0002-1618-6001Department of Electrical Engineering, National Institute of Technology, Jamshedpur, Jharkhand, IndiaDepartment of Electrical Engineering, National Institute of Technology, Jamshedpur, Jharkhand, IndiaDepartment of Electrical Engineering, National Institute of Technology, Jamshedpur, Jharkhand, IndiaDepartment of Electrical Engineering, SOS-Engineering and Technology, Guru Ghasidas Vishwavidyalaya, Bilaspur, Chhattisgarh, IndiaDepartment of Information Technology, Faculty of Science and Technology, Suan Dusit University, Bangkok, ThailandCollege of Computing, Prince of Songkla University, Phuket Campus, Phuket, ThailandA vital issue faced by the distribution network is the occurrence of unintentional islanding. The failure to identify unintentional islanding results in significant implications for both the power system and human lives. In this paper, a novel machine learning islanding detection method (IDM) based on image classification utilizing the histogram of oriented gradient (HOG) feature is proposed. In particular, the set of parameters are utilized, namely total harmonic distortion (THD) of both three phase currents and voltages, and rate of change of negative sequence voltage, are first transformed into time-frequency representations (i.e., spectrograms via the short time Fourier transform, and scalograms through continuous wavelet transform). Then, the HOG features are extracted from these images and used to train the machine learning (ML) algorithms to distinguish between occurrences of islanding and non-islanding events. Performance metrics including F1 score, recall, accuracy, precision and misclassification error are employed in the assessment process. Numerical results show that our image-based detector achieves faster detection times and higher detection accuracy versus state-of-art methods, thus confirming the validity of such approach for identifying islanding events.https://ieeexplore.ieee.org/document/10975757/Total harmonics distortion (THD)histogram of oriented gradient (HOG)scalogram imagesspectrogram imagesmachine learning (ML) algorithm |
| spellingShingle | Kumaresh Pal Kumari Namrata Ashok Kumar Akella Manoj Gupta Pannee Suanpang Aziz Nanthaamornphong Machine Learning-Based Image Pattern Recognition Using Histogram of Oriented Gradient for Islanding Detection IEEE Access Total harmonics distortion (THD) histogram of oriented gradient (HOG) scalogram images spectrogram images machine learning (ML) algorithm |
| title | Machine Learning-Based Image Pattern Recognition Using Histogram of Oriented Gradient for Islanding Detection |
| title_full | Machine Learning-Based Image Pattern Recognition Using Histogram of Oriented Gradient for Islanding Detection |
| title_fullStr | Machine Learning-Based Image Pattern Recognition Using Histogram of Oriented Gradient for Islanding Detection |
| title_full_unstemmed | Machine Learning-Based Image Pattern Recognition Using Histogram of Oriented Gradient for Islanding Detection |
| title_short | Machine Learning-Based Image Pattern Recognition Using Histogram of Oriented Gradient for Islanding Detection |
| title_sort | machine learning based image pattern recognition using histogram of oriented gradient for islanding detection |
| topic | Total harmonics distortion (THD) histogram of oriented gradient (HOG) scalogram images spectrogram images machine learning (ML) algorithm |
| url | https://ieeexplore.ieee.org/document/10975757/ |
| work_keys_str_mv | AT kumareshpal machinelearningbasedimagepatternrecognitionusinghistogramoforientedgradientforislandingdetection AT kumarinamrata machinelearningbasedimagepatternrecognitionusinghistogramoforientedgradientforislandingdetection AT ashokkumarakella machinelearningbasedimagepatternrecognitionusinghistogramoforientedgradientforislandingdetection AT manojgupta machinelearningbasedimagepatternrecognitionusinghistogramoforientedgradientforislandingdetection AT panneesuanpang machinelearningbasedimagepatternrecognitionusinghistogramoforientedgradientforislandingdetection AT aziznanthaamornphong machinelearningbasedimagepatternrecognitionusinghistogramoforientedgradientforislandingdetection |