Deep learning approaches for fault detection and classifications in the electrical secondary distribution network: Methods comparison and recurrent neural network accuracy comparison
The electrical power system comprises of several complex interrelated and dynamic elements, that are usually susceptible to electrical faults. Due to their critical impacts, faults on the electrical power system in the secondary distribution network should be immediately detected, classified, and ur...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2020-01-01
|
| Series: | Cogent Engineering |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/23311916.2020.1857500 |
| _version_ | 1797717030227410944 |
|---|---|
| author | Daudi Mnyanghwalo Herald Kundaeli Ellen Kalinga Ndyetabura Hamisi |
| author_facet | Daudi Mnyanghwalo Herald Kundaeli Ellen Kalinga Ndyetabura Hamisi |
| author_sort | Daudi Mnyanghwalo |
| collection | DOAJ |
| description | The electrical power system comprises of several complex interrelated and dynamic elements, that are usually susceptible to electrical faults. Due to their critical impacts, faults on the electrical power system in the secondary distribution network should be immediately detected, classified, and urgently cleared. Several studies have endeavored to determine appropriate methods for electrical power systems faults detection and classifications using a mathematical approach, expert systems, and normal artificial neural network-integrated with Supervisory Control and Data Acquisition (SCADA) and Phasor Measurement Units (PMU) systems as the sensing element. However, limited studies have explored the application of deep learning approaches in fault detection and classifications. In this study, several deep learning approaches were compared including Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Feed Forward Neural Network (FFNN), and Artificial Neural Network (ANN) to determine the appropriate approach for implementation. The simulation results have shown that the RNN deep learning approach is efficient in detecting and classifying faults in the electrical secondary distribution network, whilst the accuracy increases as the complexity increases. The study takes advantage of the developments in sensors and the Internet of Things (IoT) technologies to capture and preprocess data along with the secondary distribution network. The research used the challenge-driven education approach where Tanzania Electric Supply Company Limited (TANESCO) was the case study and source of the training data. |
| first_indexed | 2024-03-12T08:31:22Z |
| format | Article |
| id | doaj.art-f0c0aa6e8c2446e4acd095d71113664e |
| institution | Directory Open Access Journal |
| issn | 2331-1916 |
| language | English |
| last_indexed | 2024-03-12T08:31:22Z |
| publishDate | 2020-01-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Cogent Engineering |
| spelling | doaj.art-f0c0aa6e8c2446e4acd095d71113664e2023-09-02T17:45:50ZengTaylor & Francis GroupCogent Engineering2331-19162020-01-017110.1080/23311916.2020.18575001857500Deep learning approaches for fault detection and classifications in the electrical secondary distribution network: Methods comparison and recurrent neural network accuracy comparisonDaudi Mnyanghwalo0Herald Kundaeli1Ellen Kalinga2Ndyetabura Hamisi3University of Dar es SalaamUniversity of Dar es SalaamUniversity of Dar es SalaamUniversity of Dar es SalaamThe electrical power system comprises of several complex interrelated and dynamic elements, that are usually susceptible to electrical faults. Due to their critical impacts, faults on the electrical power system in the secondary distribution network should be immediately detected, classified, and urgently cleared. Several studies have endeavored to determine appropriate methods for electrical power systems faults detection and classifications using a mathematical approach, expert systems, and normal artificial neural network-integrated with Supervisory Control and Data Acquisition (SCADA) and Phasor Measurement Units (PMU) systems as the sensing element. However, limited studies have explored the application of deep learning approaches in fault detection and classifications. In this study, several deep learning approaches were compared including Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Feed Forward Neural Network (FFNN), and Artificial Neural Network (ANN) to determine the appropriate approach for implementation. The simulation results have shown that the RNN deep learning approach is efficient in detecting and classifying faults in the electrical secondary distribution network, whilst the accuracy increases as the complexity increases. The study takes advantage of the developments in sensors and the Internet of Things (IoT) technologies to capture and preprocess data along with the secondary distribution network. The research used the challenge-driven education approach where Tanzania Electric Supply Company Limited (TANESCO) was the case study and source of the training data.http://dx.doi.org/10.1080/23311916.2020.1857500deep learningfaults detectionfaults classificationssecondary distribution networkiotchallenge-driven education |
| spellingShingle | Daudi Mnyanghwalo Herald Kundaeli Ellen Kalinga Ndyetabura Hamisi Deep learning approaches for fault detection and classifications in the electrical secondary distribution network: Methods comparison and recurrent neural network accuracy comparison Cogent Engineering deep learning faults detection faults classifications secondary distribution network iot challenge-driven education |
| title | Deep learning approaches for fault detection and classifications in the electrical secondary distribution network: Methods comparison and recurrent neural network accuracy comparison |
| title_full | Deep learning approaches for fault detection and classifications in the electrical secondary distribution network: Methods comparison and recurrent neural network accuracy comparison |
| title_fullStr | Deep learning approaches for fault detection and classifications in the electrical secondary distribution network: Methods comparison and recurrent neural network accuracy comparison |
| title_full_unstemmed | Deep learning approaches for fault detection and classifications in the electrical secondary distribution network: Methods comparison and recurrent neural network accuracy comparison |
| title_short | Deep learning approaches for fault detection and classifications in the electrical secondary distribution network: Methods comparison and recurrent neural network accuracy comparison |
| title_sort | deep learning approaches for fault detection and classifications in the electrical secondary distribution network methods comparison and recurrent neural network accuracy comparison |
| topic | deep learning faults detection faults classifications secondary distribution network iot challenge-driven education |
| url | http://dx.doi.org/10.1080/23311916.2020.1857500 |
| work_keys_str_mv | AT daudimnyanghwalo deeplearningapproachesforfaultdetectionandclassificationsintheelectricalsecondarydistributionnetworkmethodscomparisonandrecurrentneuralnetworkaccuracycomparison AT heraldkundaeli deeplearningapproachesforfaultdetectionandclassificationsintheelectricalsecondarydistributionnetworkmethodscomparisonandrecurrentneuralnetworkaccuracycomparison AT ellenkalinga deeplearningapproachesforfaultdetectionandclassificationsintheelectricalsecondarydistributionnetworkmethodscomparisonandrecurrentneuralnetworkaccuracycomparison AT ndyetaburahamisi deeplearningapproachesforfaultdetectionandclassificationsintheelectricalsecondarydistributionnetworkmethodscomparisonandrecurrentneuralnetworkaccuracycomparison |