A Study on Deep Neural Network-Based DC Offset Removal for Phase Estimation in Power Systems
The purpose of this paper is to remove the exponentially decaying DC offset in fault current waveforms using a deep neural network (DNN), even under harmonics and noise distortion. The DNN is implemented using the TensorFlow library based on Python. Autoencoders are utilized to determine the number...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-04-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/12/9/1619 |
| _version_ | 1798006131807748096 |
|---|---|
| author | Sun-Bin Kim Vattanak Sok Sang-Hee Kang Nam-Ho Lee Soon-Ryul Nam |
| author_facet | Sun-Bin Kim Vattanak Sok Sang-Hee Kang Nam-Ho Lee Soon-Ryul Nam |
| author_sort | Sun-Bin Kim |
| collection | DOAJ |
| description | The purpose of this paper is to remove the exponentially decaying DC offset in fault current waveforms using a deep neural network (DNN), even under harmonics and noise distortion. The DNN is implemented using the TensorFlow library based on Python. Autoencoders are utilized to determine the number of neurons in each hidden layer. Then, the number of hidden layers is experimentally decided by comparing the performance of DNNs with different numbers of hidden layers. Once the optimal DNN size has been determined, intensive training is performed using both the supervised and unsupervised training methodologies. Through various case studies, it was verified that the DNN is immune to harmonics, noise distortion, and variation of the time constant of the DC offset. In addition, it was found that the DNN can be applied to power systems with different voltage levels. |
| first_indexed | 2024-04-11T12:50:12Z |
| format | Article |
| id | doaj.art-e06f71a8317241648d72eb10667b9828 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-04-11T12:50:12Z |
| publishDate | 2019-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-e06f71a8317241648d72eb10667b98282022-12-22T04:23:14ZengMDPI AGEnergies1996-10732019-04-01129161910.3390/en12091619en12091619A Study on Deep Neural Network-Based DC Offset Removal for Phase Estimation in Power SystemsSun-Bin Kim0Vattanak Sok1Sang-Hee Kang2Nam-Ho Lee3Soon-Ryul Nam4Department of Electrical Engineering, Myongji University, Yongin 17058, KoreaDepartment of Electrical Engineering, Myongji University, Yongin 17058, KoreaDepartment of Electrical Engineering, Myongji University, Yongin 17058, KoreaKorea Electric Power Research Institute, Daejeon 34056, KoreaDepartment of Electrical Engineering, Myongji University, Yongin 17058, KoreaThe purpose of this paper is to remove the exponentially decaying DC offset in fault current waveforms using a deep neural network (DNN), even under harmonics and noise distortion. The DNN is implemented using the TensorFlow library based on Python. Autoencoders are utilized to determine the number of neurons in each hidden layer. Then, the number of hidden layers is experimentally decided by comparing the performance of DNNs with different numbers of hidden layers. Once the optimal DNN size has been determined, intensive training is performed using both the supervised and unsupervised training methodologies. Through various case studies, it was verified that the DNN is immune to harmonics, noise distortion, and variation of the time constant of the DC offset. In addition, it was found that the DNN can be applied to power systems with different voltage levels.https://www.mdpi.com/1996-1073/12/9/1619autoencoderexponentially decaying DC offsetdeep neural networks (DNNs)optimal sizesupervised trainingTensorflowunsupervised training |
| spellingShingle | Sun-Bin Kim Vattanak Sok Sang-Hee Kang Nam-Ho Lee Soon-Ryul Nam A Study on Deep Neural Network-Based DC Offset Removal for Phase Estimation in Power Systems Energies autoencoder exponentially decaying DC offset deep neural networks (DNNs) optimal size supervised training Tensorflow unsupervised training |
| title | A Study on Deep Neural Network-Based DC Offset Removal for Phase Estimation in Power Systems |
| title_full | A Study on Deep Neural Network-Based DC Offset Removal for Phase Estimation in Power Systems |
| title_fullStr | A Study on Deep Neural Network-Based DC Offset Removal for Phase Estimation in Power Systems |
| title_full_unstemmed | A Study on Deep Neural Network-Based DC Offset Removal for Phase Estimation in Power Systems |
| title_short | A Study on Deep Neural Network-Based DC Offset Removal for Phase Estimation in Power Systems |
| title_sort | study on deep neural network based dc offset removal for phase estimation in power systems |
| topic | autoencoder exponentially decaying DC offset deep neural networks (DNNs) optimal size supervised training Tensorflow unsupervised training |
| url | https://www.mdpi.com/1996-1073/12/9/1619 |
| work_keys_str_mv | AT sunbinkim astudyondeepneuralnetworkbaseddcoffsetremovalforphaseestimationinpowersystems AT vattanaksok astudyondeepneuralnetworkbaseddcoffsetremovalforphaseestimationinpowersystems AT sangheekang astudyondeepneuralnetworkbaseddcoffsetremovalforphaseestimationinpowersystems AT namholee astudyondeepneuralnetworkbaseddcoffsetremovalforphaseestimationinpowersystems AT soonryulnam astudyondeepneuralnetworkbaseddcoffsetremovalforphaseestimationinpowersystems AT sunbinkim studyondeepneuralnetworkbaseddcoffsetremovalforphaseestimationinpowersystems AT vattanaksok studyondeepneuralnetworkbaseddcoffsetremovalforphaseestimationinpowersystems AT sangheekang studyondeepneuralnetworkbaseddcoffsetremovalforphaseestimationinpowersystems AT namholee studyondeepneuralnetworkbaseddcoffsetremovalforphaseestimationinpowersystems AT soonryulnam studyondeepneuralnetworkbaseddcoffsetremovalforphaseestimationinpowersystems |