Immune-based technique for online security evaluation in power system / Saiful Izwan Suliman
Voltage instability has recently become a challenging problem for many power system operators. This phenomenon could lead to the occurrence of voltage collapse or blackout to the whole system. Voltage stability monitoring in power system operation is a suggested solution for this problem so that the...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2006
|
| Subjects: | |
| Online Access: | https://ir.uitm.edu.my/id/eprint/104742/1/104742.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Voltage instability has recently become a challenging problem for many power system operators. This phenomenon could lead to the occurrence of voltage collapse or blackout to the whole system. Voltage stability monitoring in power system operation is a suggested solution for this problem so that the occurrence of voltage collapse due to voltage instability could be avoided. This thesis presents the application of Artificial Immune Systems (AIS) for online voltage stability evaluation which could be used as an early warmng system to the power system operator so that necessary action could be taken in order to avoid the occurrence of voltage collapse. Based on the literature review, it has been found that no research has yet been conducted in analyzing voltage stability condition of a power system using AIS, indirectly showing that this new technique provides an alternative way in solving this problem based on voltage stability index evaluation. Key features of the proposed method are the implementation of clonal selection principle that has the capability in performing pattern recognition task and the implementation of multistage programming concept which has steered the developed system to complete the computation at a rate faster and enhanced the efficiency of the training process in terms of the accuracy of the prediction. The proposed method was developed using C++ programming language and was tested on the IEEE 6-bus and 30-bus power system. Fast performance with accurate prediction for voltage stability index has been obtained. A comparative study also had been conducted with another Artificial Neural Network-based system developed for the similar purpose. The results obtained have shown the potential of AIS as an alternative method in solving pattern recognitionrelated task and in this case recognizing the voltage stability condition based on the loading condition of a system. This new technique promises many advantages in producing good solutions and has the potential to be a valuable tool for fast real-time voltage stability assessment in a power system. |
|---|