Radial Basis Function Neural Network (RBFNN) Based Islanding Detection Technique for distribution Network Connected with Mini Hydro Type Distributed Generation (ME Thesis) (Record no. 58705)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 02804nam a22001337a 4500 |
| 100 ## - MAIN ENTRY--AUTHOR NAME | |
| Personal name | Asad Ali Chandio |
| -- | 16MPE08 |
| -- | Supervisor - Dr. Javeed Ahmed Laghari |
| 245 ## - TITLE STATEMENT | |
| Title | Radial Basis Function Neural Network (RBFNN) Based Islanding Detection Technique for distribution Network Connected with Mini Hydro Type Distributed Generation (ME Thesis) |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. (IMPRINT) | |
| Place of publication | Nawabshah: |
| Name of publisher | QUEST, |
| Year of publication | 2018. |
| 300 ## - PHYSICAL DESCRIPTION | |
| Number of Pages | 61p. |
| 500 ## - GENERAL NOTE | |
| General note | ABSTRACT<br/><br/><br/>The demand of the electricity is growing day by day due to the depletion of fossil fuels. The load demand is increasing exponentially in the power system. This enhanced demand of electricity can be full filled with the help of Distributed Generation technology. In order to investigate the benefits of of DGs, few technical problems need to address. Among the technical problems, the Islanding Condition is one of the major issues. Islanding is a condition that is cause by Isolation or shutdown of the main Grid from the remainder of the distribution network connected with the DGs and yet supplied by the distributed generators. The detection of islanding condition is extremely important for reliable operation of distribution network. For this purpose, several islanding detection methods have been suggested. Among them, hybrid islanding detection techniques are preferred due to their minimum effects on the power system. However, hybrid islanding detection techniques also suffer from few limitations. They still degrade the power quality, depend upon the threshold setting, and also take comparatively large time to detect the islanding phenomenon. Thus, fast detection, threshold setting limitation and power quality degradation issues are still not solved by hybrid islanding detection techniques. To address these issues, this research proposes radial basis function neural network (RBFNN) based islanding detection technique using rate of change of reactive power.<br/><br/>This work uses radial basis function neural networks classifier to distinguish between islanding and non-islanding event. The appropriate database of several islanding and non-islanding events is generated by performing the offline simulations on distribution system in PSCAT/EMTDC software v4.2. 1 . Th i database is used for training and testing the RBFNN in MATLAB version R2013a software. The simulation results have shown that proposed islanding detection technique can detect islanding and non-islanding events accurately with in one cycle without degrading the power quality of the system and is independent of there hold setting making it suitable for real time implementation.<br/><br/><br/><br/><br/><br/> |
| 700 ## - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Department of Electrical Engineering |
| 856 ## - ELECTRONIC LOCATION AND ACCESS | |
| Uniform Resource Identifier | http://tinyurl.com/4jyxnn7j |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Koha item type | Thesis and Dissertation |
| Withdrawn status | Lost status | Home library | Current library | Date acquired | Accession Number | Koha item type |
|---|---|---|---|---|---|---|
| Research Section | Reference Section | 26/02/2019 | MP/39-417 | Thesis and Dissertation | ||
| Research Section | Research Section | 13/09/2018 | MP/36-393 | Thesis and Dissertation | ||
| Research Section | Research Section | 14/12/2023 | MP/51-617 | Thesis and Dissertation |