Musirikare, Alexandre (2018) Artificial neural network-based modeling of directional overcurrent relay curve for use in radial distribution system with distributed generators. Masters thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
07111650017001_Master_Thesis.pdf - Published Version Download (4MB) | Preview |
Abstract
Accurate models of overcurrent relay curve help to find the proper adjustments of the relay settings suitable to the coordination requirements. The time multiplier setting (TMS) and the relay pickup current are very important parameters in modeling of directional overcurrent relay (DOCR) characteristics. These two parameters can be adjusted to move the time current characteristic (TCC) curve to the position suitable to the protection coordination.
Distributed generations (DGs) can cause change of fault current in the system and this can affect the protection coordination. In this thesis research, artificial neural network (ANN) based on Levenberg-Marquardt algorithm is used to model the DOCR characteristics where the trained ANN model is able to compute the time multiplier setting, the pickup current as well as the trip time of each DOCR based on the current status of the power sources connected to the system.
The research is conducted on radial distribution feeder of 7 buses penetrated by DGs. The system is designed and simulated in order to find the relevant training data. The training results are quite interesting and encouraging with a mean squared error (MSE) of 9.9894e-13. Finally, a sample of ANN outputs is implemented in ETAP software for further verification of the developed model and the test results are quite promising.
| Item Type: | Thesis (Masters) |
|---|---|
| Additional Information: | RTE 621.313 Mus a-1 |
| Uncontrolled Keywords: | Artificial Neural Network (ANN), Directional Overcurrent Relay (DOCR), Distributed Generation (DG), Radial distribution system, Time Current Characteristics (TCC) |
| Subjects: | Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) |
| Divisions: | Faculty of Electrical Technology > Electrical Engineering > 20101-(S2) Master Thesis |
| Depositing User: | - Davi Wah |
| Date Deposited: | 02 May 2019 08:55 |
| Last Modified: | 24 Apr 2024 05:38 |
| URI: | http://repository.its.ac.id/id/eprint/62910 |
Actions (login required)
 |
View Item |