Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/10251
Title: | Neural network based monitoring and genetic algorithm based enhancement of voltage stability |
Researcher: | Jayasankar V |
Guide(s): | Kamaraj, N. |
Keywords: | Neural network, genetic algorithm, Thyristor Controlled Series Capacitor, Forward Back Propagation Network |
Upload Date: | 31-Jul-2013 |
University: | Anna University |
Completed Date: | |
Abstract: | Voltage stability assessment and improvement form the core function in a modern power system operation and control. The voltage stability can be identified through various stability factors. In this work, line stability index is used to calculate the stability of each line in the considered IEEE test systems by using the conventional power flow algorithm. When this index value changes from 0 to 1, the voltage stability of the system relatively decreases. In order to improve the system voltage stability the Thyristor Controlled Series Capacitor (TCSC) is installed in the most severe line, which is identified from the line stability index. Due to the non-linear nature of the voltage stability assessment problem, neural networks can be used for voltage stability monitoring. In this work, a single Feed Forward Back Propagation Network (FFBPN) with minimal number of neurons is used. From the results obtained the severe lines are determined. The effectiveness of this method has been demonstrated on the two IEEE test systems. Based on the ranking of the lines under various load conditions, this work identifies the optimal location of TCSC among the severe lines for the voltage stability improvement. Genetic algorithm approach is also investigated for the voltage stability analysis and its enhancement. Using Genetic Algorithm (GA), the optimal line for TCSC placement and the optimal value of capacitive reactance of TCSC to be inserted are identified based on the minimization of the maximum value of line stability index under normal and under different single line contingencies with varying load conditions. Moreover, the GA parameters such as mutation rate, crossover rate and population size are also optimized in this work. This algorithm has been tested successfully on the considered IEEE test systems. From the simulation results of proposed approaches, it has been ascertained that there is considerable improvement in voltage stability after placing TCSC. newline |
Pagination: | xx, 132 |
URI: | http://hdl.handle.net/10603/10251 |
Appears in Departments: | Faculty of Electrical and Electronics Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
01_title.pdf | Attached File | 49.71 kB | Adobe PDF | View/Open |
02_certificates.pdf | 1 MB | Adobe PDF | View/Open | |
03_abstract.pdf | 13.04 kB | Adobe PDF | View/Open | |
04_acknowledgement.pdf | 13.5 kB | Adobe PDF | View/Open | |
05_contents.pdf | 43.17 kB | Adobe PDF | View/Open | |
06_chapter 1.pdf | 562.8 kB | Adobe PDF | View/Open | |
07_chapter 2.pdf | 72.27 kB | Adobe PDF | View/Open | |
08_chapter 3.pdf | 210.73 kB | Adobe PDF | View/Open | |
09_chapter 4.pdf | 295.53 kB | Adobe PDF | View/Open | |
10_chapter 5.pdf | 503.14 kB | Adobe PDF | View/Open | |
11_chapter 6.pdf | 75.98 kB | Adobe PDF | View/Open | |
12_chapter 7.pdf | 29.03 kB | Adobe PDF | View/Open | |
13_annexure 1 and 2.pdf | 113.74 kB | Adobe PDF | View/Open | |
14_referneces.pdf | 43.87 kB | Adobe PDF | View/Open | |
15_publications.pdf | 16.71 kB | Adobe PDF | View/Open | |
16_vitae.pdf | 13.55 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: