A Novel Microgrid Islanding Detection Algorithm Based on a Multi-Feature Improved LSTM
Islanding detection is one of the conditions necessary for the safe operation of the microgrid. The detection technology should provide the ability to differentiate islanded operations from power grid disturbances effectively. Given that it is difficult to set the fault threshold using the passive d...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/15/8/2810 |
| _version_ | 1797446618209845248 |
|---|---|
| author | Yan Xia Feihong Yu Xingzhong Xiong Qinyuan Huang Qijun Zhou |
| author_facet | Yan Xia Feihong Yu Xingzhong Xiong Qinyuan Huang Qijun Zhou |
| author_sort | Yan Xia |
| collection | DOAJ |
| description | Islanding detection is one of the conditions necessary for the safe operation of the microgrid. The detection technology should provide the ability to differentiate islanded operations from power grid disturbances effectively. Given that it is difficult to set the fault threshold using the passive detection method, and because the traditional active detection method affects the output power quality, a microgrid islanding detection method based on the Sliding Window Discrete Fourier Transform (SDFT)-Empirical Mode Decomposition (EMD) and Long Short-Term Memory (LSTM) network optimized by an attention mechanism is proposed. In this paper, the inverter output current and voltage at the point of common coupling (PCC) are transformed by the SDFT. The positive sequence, zero sequence, and negative sequence components of voltage and current harmonics are calculated and reconstructed by adopting the symmetrical component method (SCM). Meanwhile, the current and voltage are decomposed into a mono intrinsic mode function (IMF). The symmetric components of voltage, current, and IMFs are used as inputs to the deep learning algorithm. An LSTM with the features extracted to classify islanding and grid disturbance is proposed. By using the attention mechanism to set the weight values of the features of hidden states obtained by the LSTM network, the proportion of important features increases, which improves the classification effect. MATLAB/Simulink simulation results indicate that the proposed method can effectively classify the islanding state under different working conditions with an accuracy level of 98.4% and a loss value of 0.0725 with a maximal detection time of 66.94 ms. It can also reduce the non-detection zone (NDZ) and detection time and has a certain level of noise resistance. Meanwhile, the problem whereby the active method affects the microgrid power quality is avoided without disturbing the current or power of the microgrid. |
| first_indexed | 2024-03-09T13:43:12Z |
| format | Article |
| id | doaj.art-5853d3d071804c8c9bb04feaab39b0b4 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-09T13:43:12Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-5853d3d071804c8c9bb04feaab39b0b42023-11-30T21:03:37ZengMDPI AGEnergies1996-10732022-04-01158281010.3390/en15082810A Novel Microgrid Islanding Detection Algorithm Based on a Multi-Feature Improved LSTMYan Xia0Feihong Yu1Xingzhong Xiong2Qinyuan Huang3Qijun Zhou4School of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin 644000, ChinaSchool of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin 644000, ChinaSchool of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin 644000, ChinaSchool of Automation and Information Engineering, Sichuan University of Science & Engineering, Yibin 644000, ChinaState Grid Ganzi Electric Power Supply Company, Kangding 626700, ChinaIslanding detection is one of the conditions necessary for the safe operation of the microgrid. The detection technology should provide the ability to differentiate islanded operations from power grid disturbances effectively. Given that it is difficult to set the fault threshold using the passive detection method, and because the traditional active detection method affects the output power quality, a microgrid islanding detection method based on the Sliding Window Discrete Fourier Transform (SDFT)-Empirical Mode Decomposition (EMD) and Long Short-Term Memory (LSTM) network optimized by an attention mechanism is proposed. In this paper, the inverter output current and voltage at the point of common coupling (PCC) are transformed by the SDFT. The positive sequence, zero sequence, and negative sequence components of voltage and current harmonics are calculated and reconstructed by adopting the symmetrical component method (SCM). Meanwhile, the current and voltage are decomposed into a mono intrinsic mode function (IMF). The symmetric components of voltage, current, and IMFs are used as inputs to the deep learning algorithm. An LSTM with the features extracted to classify islanding and grid disturbance is proposed. By using the attention mechanism to set the weight values of the features of hidden states obtained by the LSTM network, the proportion of important features increases, which improves the classification effect. MATLAB/Simulink simulation results indicate that the proposed method can effectively classify the islanding state under different working conditions with an accuracy level of 98.4% and a loss value of 0.0725 with a maximal detection time of 66.94 ms. It can also reduce the non-detection zone (NDZ) and detection time and has a certain level of noise resistance. Meanwhile, the problem whereby the active method affects the microgrid power quality is avoided without disturbing the current or power of the microgrid.https://www.mdpi.com/1996-1073/15/8/2810islanding detectionsliding-window discrete Fourier transformmulti-featureempirical mode decompositionattention mechanismlong short-term memory network |
| spellingShingle | Yan Xia Feihong Yu Xingzhong Xiong Qinyuan Huang Qijun Zhou A Novel Microgrid Islanding Detection Algorithm Based on a Multi-Feature Improved LSTM Energies islanding detection sliding-window discrete Fourier transform multi-feature empirical mode decomposition attention mechanism long short-term memory network |
| title | A Novel Microgrid Islanding Detection Algorithm Based on a Multi-Feature Improved LSTM |
| title_full | A Novel Microgrid Islanding Detection Algorithm Based on a Multi-Feature Improved LSTM |
| title_fullStr | A Novel Microgrid Islanding Detection Algorithm Based on a Multi-Feature Improved LSTM |
| title_full_unstemmed | A Novel Microgrid Islanding Detection Algorithm Based on a Multi-Feature Improved LSTM |
| title_short | A Novel Microgrid Islanding Detection Algorithm Based on a Multi-Feature Improved LSTM |
| title_sort | novel microgrid islanding detection algorithm based on a multi feature improved lstm |
| topic | islanding detection sliding-window discrete Fourier transform multi-feature empirical mode decomposition attention mechanism long short-term memory network |
| url | https://www.mdpi.com/1996-1073/15/8/2810 |
| work_keys_str_mv | AT yanxia anovelmicrogridislandingdetectionalgorithmbasedonamultifeatureimprovedlstm AT feihongyu anovelmicrogridislandingdetectionalgorithmbasedonamultifeatureimprovedlstm AT xingzhongxiong anovelmicrogridislandingdetectionalgorithmbasedonamultifeatureimprovedlstm AT qinyuanhuang anovelmicrogridislandingdetectionalgorithmbasedonamultifeatureimprovedlstm AT qijunzhou anovelmicrogridislandingdetectionalgorithmbasedonamultifeatureimprovedlstm AT yanxia novelmicrogridislandingdetectionalgorithmbasedonamultifeatureimprovedlstm AT feihongyu novelmicrogridislandingdetectionalgorithmbasedonamultifeatureimprovedlstm AT xingzhongxiong novelmicrogridislandingdetectionalgorithmbasedonamultifeatureimprovedlstm AT qinyuanhuang novelmicrogridislandingdetectionalgorithmbasedonamultifeatureimprovedlstm AT qijunzhou novelmicrogridislandingdetectionalgorithmbasedonamultifeatureimprovedlstm |