Machine Learning Classifiers for Steady State Security Evaluation in Power System
Deregulation of power system in recent years has turned static security assessment (SSA) into a challenging task for which acceptably fast and accurate assessment methodology is essential. The objective of this paper is to investigate the reliability of the SSA in determining the security level of power system from serious interference during operation. Artificial Intelligence Classifiers are implemented to classify the security status in the test power system, comparison are made in terms of computation time and accuracy of the networks. Data obtained from Newton Raphson Load Flow (NRLF) analysis method are used for the training and testing purposes of the proposed AI techniques. The data are used also as a benchmark to validate the results from AI techniques to achieve high speed of execution and good classification accuracy. A new methodology of feature selection technique based on extracting variables has also been applied. The proposed techniques have been extended and tested on 5, 30, 57 and 118 IEEE test systems. Generally, the proposed AI techniques have successfully been applied to evaluate SSA for various IEEE test system.
Keywords: Steady State Security Assessment, Artificial Intelligence Classifiers, Power System
Download Full-Text
ABOUT THE AUTHORS
Ibrahim Saeh
Universiti Technologi Malaysia,UTM
M.W.Mustafa
Universiti Technologi Malaysia,UTM
Ibrahim Saeh
Universiti Technologi Malaysia,UTM
M.W.Mustafa
Universiti Technologi Malaysia,UTM
