Hybrid Machine Learning Models for Classifying Power Quality Disturbances: A Comparative Study
The economic impact associated with power quality (PQ) problems in electrical systems is increasing, so PQ improvement research becomes a key task. In this paper, a Stockwell transform (ST)-based hybrid machine learning approach was used for the recognition and classification of power quality distur...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/13/11/2761 |
| _version_ | 1797566409397501952 |
|---|---|
| author | Juan Carlos Bravo-Rodríguez Francisco J. Torres María D. Borrás |
| author_facet | Juan Carlos Bravo-Rodríguez Francisco J. Torres María D. Borrás |
| author_sort | Juan Carlos Bravo-Rodríguez |
| collection | DOAJ |
| description | The economic impact associated with power quality (PQ) problems in electrical systems is increasing, so PQ improvement research becomes a key task. In this paper, a Stockwell transform (ST)-based hybrid machine learning approach was used for the recognition and classification of power quality disturbances (PQDs). The ST of the PQDs was used to extract significant waveform features which constitute the input vectors for different machine learning approaches, including the K-nearest neighbors’ algorithm (K-NN), decision tree (DT), and support vector machine (SVM) used for classifying the PQDs. The procedure was optimized by using the genetic algorithm (GA) and the competitive swarm optimization algorithm (CSO). To test the proposed methodology, synthetic PQD waveforms were generated. Typical single disturbances for the voltage signal, as well as complex disturbances resulting from possible combinations of them, were considered. Furthermore, different levels of white Gaussian noise were added to the PQD waveforms while maintaining the desired accuracy level of the proposed classification methods. Finally, all the hybrid classification proposals were evaluated and the best one was compared with some others present in the literature. The proposed ST-based CSO-SVM method provides good results in terms of classification accuracy and noise immunity. |
| first_indexed | 2024-03-10T19:27:21Z |
| format | Article |
| id | doaj.art-0c1ca82203fe43178206874208fd4901 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T19:27:21Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-0c1ca82203fe43178206874208fd49012023-11-20T02:25:40ZengMDPI AGEnergies1996-10732020-06-011311276110.3390/en13112761Hybrid Machine Learning Models for Classifying Power Quality Disturbances: A Comparative StudyJuan Carlos Bravo-Rodríguez0Francisco J. Torres1María D. Borrás2Escuela Politécnica Superior, Universidad de Sevilla, c/ Virgen de África 9, 41011 Sevilla, SpainEscuela Politécnica Superior, Universidad de Sevilla, c/ Virgen de África 9, 41011 Sevilla, SpainEscuela Politécnica Superior, Universidad de Sevilla, c/ Virgen de África 9, 41011 Sevilla, SpainThe economic impact associated with power quality (PQ) problems in electrical systems is increasing, so PQ improvement research becomes a key task. In this paper, a Stockwell transform (ST)-based hybrid machine learning approach was used for the recognition and classification of power quality disturbances (PQDs). The ST of the PQDs was used to extract significant waveform features which constitute the input vectors for different machine learning approaches, including the K-nearest neighbors’ algorithm (K-NN), decision tree (DT), and support vector machine (SVM) used for classifying the PQDs. The procedure was optimized by using the genetic algorithm (GA) and the competitive swarm optimization algorithm (CSO). To test the proposed methodology, synthetic PQD waveforms were generated. Typical single disturbances for the voltage signal, as well as complex disturbances resulting from possible combinations of them, were considered. Furthermore, different levels of white Gaussian noise were added to the PQD waveforms while maintaining the desired accuracy level of the proposed classification methods. Finally, all the hybrid classification proposals were evaluated and the best one was compared with some others present in the literature. The proposed ST-based CSO-SVM method provides good results in terms of classification accuracy and noise immunity.https://www.mdpi.com/1996-1073/13/11/2761power quality disturbancesclassificationfeature selectionswarm optimizationsupport vector machinegenetic algorithm |
| spellingShingle | Juan Carlos Bravo-Rodríguez Francisco J. Torres María D. Borrás Hybrid Machine Learning Models for Classifying Power Quality Disturbances: A Comparative Study Energies power quality disturbances classification feature selection swarm optimization support vector machine genetic algorithm |
| title | Hybrid Machine Learning Models for Classifying Power Quality Disturbances: A Comparative Study |
| title_full | Hybrid Machine Learning Models for Classifying Power Quality Disturbances: A Comparative Study |
| title_fullStr | Hybrid Machine Learning Models for Classifying Power Quality Disturbances: A Comparative Study |
| title_full_unstemmed | Hybrid Machine Learning Models for Classifying Power Quality Disturbances: A Comparative Study |
| title_short | Hybrid Machine Learning Models for Classifying Power Quality Disturbances: A Comparative Study |
| title_sort | hybrid machine learning models for classifying power quality disturbances a comparative study |
| topic | power quality disturbances classification feature selection swarm optimization support vector machine genetic algorithm |
| url | https://www.mdpi.com/1996-1073/13/11/2761 |
| work_keys_str_mv | AT juancarlosbravorodriguez hybridmachinelearningmodelsforclassifyingpowerqualitydisturbancesacomparativestudy AT franciscojtorres hybridmachinelearningmodelsforclassifyingpowerqualitydisturbancesacomparativestudy AT mariadborras hybridmachinelearningmodelsforclassifyingpowerqualitydisturbancesacomparativestudy |