This paper presents a deep-learning based method for the classification of transient events of the power system using the data collected by a standard Phasor Measurement Unit (PMU). Although transient power system events are high-frequency variations of the voltages and currents, it leaves a trace in the PMU time-series data, which are collected at relatively much lower-frequencies. The main motivation of this study is to use low-frequency data recorded by PMU devices, widely used in the industry, for the classification of transient events, which would normally require the use of high-cost power quality analyzers. In the proposed method, PMU data are converted into 2D data by Gramian Angular Field (GAF) image transformation method to increase the classification performance. Then, the GAF matrices corresponding to PMU time-series data are classified by a Convolutional Neural Network (CNN) based deep learning method. Transient event data used in this research work includes different numbers of frequency and angle time series of three different events, Line Trip, Generation Trip and Load Shedding, obtained from the Frequency Disturbance Recorders (FDR) developed at Virginia Tech. FDRs are connected to the FNET/GridEye network hosted by the University of Tennessee. Classification performances on the three power system events show that using only the frequency data gives the best performance results compared to that using angle only and both frequency and angle. Impact of the training data amount is examined for all cases and future work is proposed. Although there are similar studies in the literature, contribution of this research work is revealing the effect of PMU data type and size of training set in detail.
Keyword: convolutional neural network; frequency disturbance recorder; gramian angular field; phasor measurement unit; power quality; power system transient; transient event classification
Publication Name (dc.title) | Classification of high frequency transient events buried in low frequency sampled PMU data |
Author/s (dc.contributor.yazarlar) | Görkem Gök, Özgül Salor, Müslüm Cengiz Taplamacıoğlu |
Publication type (dc.type) | Konferans Bildirisi |
Language (dc.language) | İngilizce |
Publication year (dc.date.issued) | 2023 |
National/International (dc.identifier.ulusaluluslararasi) | Uluslararası |
Source (dc.relation.journal) | Proceedings |
Additional source name / Conference information (dc.identifier.kaynakadiekbilgi) | 2023 10th International Conference on Electrical and Electronics Engineering (ICEEE).- May 8 2023 to May 10 2023.- Istanbul, Turkiye |
Page (dc.identifier.startpage) | 90-94 |
ISSN/ISBN (dc.identifier.issn) | ISBN: 979-8-3503-0429-9 |
Publisher (dc.publisher) | Institute of Electrical and Electronics Engineers Inc. |
Databases (dc.contributor.veritaban) | Scopus |
Databases (dc.contributor.veritaban) | IEEE Computer Society Dijital Library |
Index Type (dc.identifier.index) | Scopus |
Abstract (dc.description.abstract) | This paper presents a deep-learning based method for the classification of transient events of the power system using the data collected by a standard Phasor Measurement Unit (PMU). Although transient power system events are high-frequency variations of the voltages and currents, it leaves a trace in the PMU time-series data, which are collected at relatively much lower-frequencies. The main motivation of this study is to use low-frequency data recorded by PMU devices, widely used in the industry, for the classification of transient events, which would normally require the use of high-cost power quality analyzers. In the proposed method, PMU data are converted into 2D data by Gramian Angular Field (GAF) image transformation method to increase the classification performance. Then, the GAF matrices corresponding to PMU time-series data are classified by a Convolutional Neural Network (CNN) based deep learning method. Transient event data used in this research work includes different numbers of frequency and angle time series of three different events, Line Trip, Generation Trip and Load Shedding, obtained from the Frequency Disturbance Recorders (FDR) developed at Virginia Tech. FDRs are connected to the FNET/GridEye network hosted by the University of Tennessee. Classification performances on the three power system events show that using only the frequency data gives the best performance results compared to that using angle only and both frequency and angle. Impact of the training data amount is examined for all cases and future work is proposed. Although there are similar studies in the literature, contribution of this research work is revealing the effect of PMU data type and size of training set in detail. |
Abstract (dc.description.abstract) | Keyword: convolutional neural network; frequency disturbance recorder; gramian angular field; phasor measurement unit; power quality; power system transient; transient event classification |
URL (dc.rights) | https://www.computer.org/csdl/proceedings-article/iceee/2023/042900a090/1RR1qFpPm3m |
DOI (dc.identifier.doi) | 10.1109/ICEEE59925.2023.00024 |
Faculty / Institute (dc.identifier.fakulte) | Mühendislik Fakültesi |
Department (dc.identifier.bolum) | Elektrik-Elektronik Mühendisliği Bölümü |
Author(s) in the Institution (dc.contributor.author) | Özgül SALOR-DURNA |
Kayıt No (dc.identifier.kayitno) | BLF6F606AC |
Record Add Date (dc.date.available) | 2023-12-14 |
Notes (Publication year) (dc.identifier.notyayinyili) | 2023 |
Subject Headings (dc.subject) | convolutional neural network |
Subject Headings (dc.subject) | frequency disturbance recorder |
Subject Headings (dc.subject) | gramian angular field |
Subject Headings (dc.subject) | phasor measurement unit |
Subject Headings (dc.subject) | power quality |
Subject Headings (dc.subject) | power system transient |
Subject Headings (dc.subject) | transient event classification |