Hybrid Islanding Detection in Microgrid with Multiple Connection Points to Smart Grids Using Fuzzy-Neural Network
© 1969-2012 IEEE. This paper presents a new hybrid islanding detection approach for microgrids (MGs) with multiple connection points to smart grids (SGs) which is based on the probability of islanding (PoI) calculated at the SG side and sent to the central control for microgrid (CCMG). The PoI value...
| Main Authors: | , , , |
|---|---|
| Format: | Journal Article |
| Published: |
Institute of Electrical and Electronics Engineers
2017
|
| Online Access: | http://hdl.handle.net/20.500.11937/55483 |
| _version_ | 1848759633112465408 |
|---|---|
| author | Kermany, S. Joorabian, M. Deilami, Sara Masoum, Mohammad Sherkat |
| author_facet | Kermany, S. Joorabian, M. Deilami, Sara Masoum, Mohammad Sherkat |
| author_sort | Kermany, S. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | © 1969-2012 IEEE. This paper presents a new hybrid islanding detection approach for microgrids (MGs) with multiple connection points to smart grids (SGs) which is based on the probability of islanding (PoI) calculated at the SG side and sent to the central control for microgrid (CCMG). The PoI values are determined using a combination of passive, active, and communication islanding detection approaches based on the utility signals measured at the SGs sides which are processed by discrete wavelet transform using an artificial neural network (ANN). If {\text{PoI}}-{{\rm{ANN}}} is larger than the threshold value (indicating high possibility of islanding) then a more accurate approach based on fuzzy network is used to recompute it ({\text{PoI}}-{{\rm{FUZZY}}}) where the fuzzy parameters are determined by an adaptive neuro-fuzzy inference system. In the proposed technique, an active islanding is only performed when PoI is high and the amplitudes of the disturb signals are proportional to {\text{PoI}}-{{\rm{FUZZY}}}. Furthermore, if the PoI is not correctly received by CCMG, two auxiliary tests will be performed in the MG side to detect islanding. These tests include an intentional passive islanding detection in a short preset time and an active islanding detection with disturb signals proportional to the calculated PoI. Detailed simulations are performed and analyzed to evaluate the performance of the proposed method. |
| first_indexed | 2025-11-14T10:02:59Z |
| format | Journal Article |
| id | curtin-20.500.11937-55483 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T10:02:59Z |
| publishDate | 2017 |
| publisher | Institute of Electrical and Electronics Engineers |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-554832019-08-06T05:54:39Z Hybrid Islanding Detection in Microgrid with Multiple Connection Points to Smart Grids Using Fuzzy-Neural Network Kermany, S. Joorabian, M. Deilami, Sara Masoum, Mohammad Sherkat © 1969-2012 IEEE. This paper presents a new hybrid islanding detection approach for microgrids (MGs) with multiple connection points to smart grids (SGs) which is based on the probability of islanding (PoI) calculated at the SG side and sent to the central control for microgrid (CCMG). The PoI values are determined using a combination of passive, active, and communication islanding detection approaches based on the utility signals measured at the SGs sides which are processed by discrete wavelet transform using an artificial neural network (ANN). If {\text{PoI}}-{{\rm{ANN}}} is larger than the threshold value (indicating high possibility of islanding) then a more accurate approach based on fuzzy network is used to recompute it ({\text{PoI}}-{{\rm{FUZZY}}}) where the fuzzy parameters are determined by an adaptive neuro-fuzzy inference system. In the proposed technique, an active islanding is only performed when PoI is high and the amplitudes of the disturb signals are proportional to {\text{PoI}}-{{\rm{FUZZY}}}. Furthermore, if the PoI is not correctly received by CCMG, two auxiliary tests will be performed in the MG side to detect islanding. These tests include an intentional passive islanding detection in a short preset time and an active islanding detection with disturb signals proportional to the calculated PoI. Detailed simulations are performed and analyzed to evaluate the performance of the proposed method. 2017 Journal Article http://hdl.handle.net/20.500.11937/55483 10.1109/TPWRS.2016.2617344 Institute of Electrical and Electronics Engineers restricted |
| spellingShingle | Kermany, S. Joorabian, M. Deilami, Sara Masoum, Mohammad Sherkat Hybrid Islanding Detection in Microgrid with Multiple Connection Points to Smart Grids Using Fuzzy-Neural Network |
| title | Hybrid Islanding Detection in Microgrid with Multiple Connection Points to Smart Grids Using Fuzzy-Neural Network |
| title_full | Hybrid Islanding Detection in Microgrid with Multiple Connection Points to Smart Grids Using Fuzzy-Neural Network |
| title_fullStr | Hybrid Islanding Detection in Microgrid with Multiple Connection Points to Smart Grids Using Fuzzy-Neural Network |
| title_full_unstemmed | Hybrid Islanding Detection in Microgrid with Multiple Connection Points to Smart Grids Using Fuzzy-Neural Network |
| title_short | Hybrid Islanding Detection in Microgrid with Multiple Connection Points to Smart Grids Using Fuzzy-Neural Network |
| title_sort | hybrid islanding detection in microgrid with multiple connection points to smart grids using fuzzy-neural network |
| url | http://hdl.handle.net/20.500.11937/55483 |