Application of artificial neural network for voltage stability monitoring / Valerian Shem
This project is about monitoring the voltage stability of a system bus. Voltage stability problem has been one of the major concerns for electric utilities as a result of system heavy loading and needs to be solved. A 6-system bus is used as input variables, which consists of real power value (PL...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
2003
|
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my-uitm-ir.1003 |
|---|---|
| record_format |
uketd_dc |
| spelling |
my-uitm-ir.10032017-04-19T04:13:33Z Application of artificial neural network for voltage stability monitoring / Valerian Shem 2003 Shem, Valerian This project is about monitoring the voltage stability of a system bus. Voltage stability problem has been one of the major concerns for electric utilities as a result of system heavy loading and needs to be solved. A 6-system bus is used as input variables, which consists of real power value (PL) and reactive power (QL). This system analyzes the concerned variables and shows the stabilized value for load power (L) as the output. To solve this problem, this simulation implements the Artificial Neural Network approach using both standard back-propagation technique and hybrid technique (standard backpropagation and genetic algorithm (GA)). The latter technique requires GA to find the optimal value for each weight of the neural network. A comparative study is conducted to measure the performance of the neural network using different types of parameters. By completing this project, we should be able to have an idea on how to monitor voltage stability from any system bus and to make machine learns like human does. 2003 Thesis https://ir.uitm.edu.my/id/eprint/1003/ degree Universiti Teknologi MARA Faculty of Information Technology & Quantitative Sciences |
| institution |
Universiti Teknologi MARA |
| collection |
UiTM Institutional Repository |
| description |
This project is about monitoring the voltage stability of a system bus. Voltage stability
problem has been one of the major concerns for electric utilities as a result of system
heavy loading and needs to be solved. A 6-system bus is used as input variables, which
consists of real power value (PL) and reactive power (QL). This system analyzes the
concerned variables and shows the stabilized value for load power (L) as the output. To
solve this problem, this simulation implements the Artificial Neural Network approach
using both standard back-propagation technique and hybrid technique (standard backpropagation
and genetic algorithm (GA)). The latter technique requires GA to find the
optimal value for each weight of the neural network. A comparative study is conducted
to measure the performance of the neural network using different types of parameters.
By completing this project, we should be able to have an idea on how to monitor
voltage stability from any system bus and to make machine learns like human does. |
| format |
Thesis |
| qualification_level |
Bachelor degree |
| author |
Shem, Valerian |
| spellingShingle |
Shem, Valerian Application of artificial neural network for voltage stability monitoring / Valerian Shem |
| author_facet |
Shem, Valerian |
| author_sort |
Shem, Valerian |
| title |
Application of artificial neural network for voltage stability monitoring / Valerian Shem |
| title_short |
Application of artificial neural network for voltage stability monitoring / Valerian Shem |
| title_full |
Application of artificial neural network for voltage stability monitoring / Valerian Shem |
| title_fullStr |
Application of artificial neural network for voltage stability monitoring / Valerian Shem |
| title_full_unstemmed |
Application of artificial neural network for voltage stability monitoring / Valerian Shem |
| title_sort |
application of artificial neural network for voltage stability monitoring / valerian shem |
| granting_institution |
Universiti Teknologi MARA |
| granting_department |
Faculty of Information Technology & Quantitative Sciences |
| publishDate |
2003 |
| _version_ |
1783732955463548928 |