A Framework Based on Machine Learning for Analytics of Voltage Quality Disturbances
This paper proposes a machine-learning-based framework for voltage quality analytics, where the space phasor model (SPM) of the three-phase voltages before, during, and after the event is applied as input data. The framework proceeds along with three main steps: (a) event extraction, (b) event chara...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/15/4/1283 |
| _version_ | 1797480821302493184 |
|---|---|
| author | Azam Bagheri Roger Alves de Oliveira Math H. J. Bollen Irene Y. H. Gu |
| author_facet | Azam Bagheri Roger Alves de Oliveira Math H. J. Bollen Irene Y. H. Gu |
| author_sort | Azam Bagheri |
| collection | DOAJ |
| description | This paper proposes a machine-learning-based framework for voltage quality analytics, where the space phasor model (SPM) of the three-phase voltages before, during, and after the event is applied as input data. The framework proceeds along with three main steps: (a) event extraction, (b) event characterization, and (c) additional information extraction. During the first step, it utilizes a Gaussian-based anomaly detection (GAD) technique to extract the event data from the recording. Principal component analysis (PCA) is adopted during the second step, where it is shown that the principal components correspond to the semi-minor and semi-major axis of the ellipse formed by the SPM. During the third step, these characteristics are interpreted to extract additional information about the underlying cause of the event. The performance of the framework was verified through experiments conducted on datasets containing synthetic and measured power quality events. The results show that the combination of semi-major axis, semi-minor axis, and direction of the major axis forms a sufficient base to characterize, classify, and eventually extract additional information from recorded event data. |
| first_indexed | 2024-03-09T22:05:40Z |
| format | Article |
| id | doaj.art-80f852520e2640d5bbe4d2f03dddb1e2 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-09T22:05:40Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-80f852520e2640d5bbe4d2f03dddb1e22023-11-23T19:41:36ZengMDPI AGEnergies1996-10732022-02-01154128310.3390/en15041283A Framework Based on Machine Learning for Analytics of Voltage Quality DisturbancesAzam Bagheri0Roger Alves de Oliveira1Math H. J. Bollen2Irene Y. H. Gu3AI & Future Technologies, Industrial and Digital Solutions, ÅF Pöyry AB (Afry), 411 19 Gothenburg, SwedenElectric Power Engineering, Luleå University of Technology, 931 87 Skellefteå, SwedenElectric Power Engineering, Luleå University of Technology, 931 87 Skellefteå, SwedenDepartment Electrical Engineering, Chalmers University of Technology, 412 96 Gothenburg, SwedenThis paper proposes a machine-learning-based framework for voltage quality analytics, where the space phasor model (SPM) of the three-phase voltages before, during, and after the event is applied as input data. The framework proceeds along with three main steps: (a) event extraction, (b) event characterization, and (c) additional information extraction. During the first step, it utilizes a Gaussian-based anomaly detection (GAD) technique to extract the event data from the recording. Principal component analysis (PCA) is adopted during the second step, where it is shown that the principal components correspond to the semi-minor and semi-major axis of the ellipse formed by the SPM. During the third step, these characteristics are interpreted to extract additional information about the underlying cause of the event. The performance of the framework was verified through experiments conducted on datasets containing synthetic and measured power quality events. The results show that the combination of semi-major axis, semi-minor axis, and direction of the major axis forms a sufficient base to characterize, classify, and eventually extract additional information from recorded event data.https://www.mdpi.com/1996-1073/15/4/1283anomaly detectionmachine learningpower qualityprincipal component analysisspace phasor model |
| spellingShingle | Azam Bagheri Roger Alves de Oliveira Math H. J. Bollen Irene Y. H. Gu A Framework Based on Machine Learning for Analytics of Voltage Quality Disturbances Energies anomaly detection machine learning power quality principal component analysis space phasor model |
| title | A Framework Based on Machine Learning for Analytics of Voltage Quality Disturbances |
| title_full | A Framework Based on Machine Learning for Analytics of Voltage Quality Disturbances |
| title_fullStr | A Framework Based on Machine Learning for Analytics of Voltage Quality Disturbances |
| title_full_unstemmed | A Framework Based on Machine Learning for Analytics of Voltage Quality Disturbances |
| title_short | A Framework Based on Machine Learning for Analytics of Voltage Quality Disturbances |
| title_sort | framework based on machine learning for analytics of voltage quality disturbances |
| topic | anomaly detection machine learning power quality principal component analysis space phasor model |
| url | https://www.mdpi.com/1996-1073/15/4/1283 |
| work_keys_str_mv | AT azambagheri aframeworkbasedonmachinelearningforanalyticsofvoltagequalitydisturbances AT rogeralvesdeoliveira aframeworkbasedonmachinelearningforanalyticsofvoltagequalitydisturbances AT mathhjbollen aframeworkbasedonmachinelearningforanalyticsofvoltagequalitydisturbances AT ireneyhgu aframeworkbasedonmachinelearningforanalyticsofvoltagequalitydisturbances AT azambagheri frameworkbasedonmachinelearningforanalyticsofvoltagequalitydisturbances AT rogeralvesdeoliveira frameworkbasedonmachinelearningforanalyticsofvoltagequalitydisturbances AT mathhjbollen frameworkbasedonmachinelearningforanalyticsofvoltagequalitydisturbances AT ireneyhgu frameworkbasedonmachinelearningforanalyticsofvoltagequalitydisturbances |