Real-time power system dynamic security assessment based on advanced feature selection for decision tree classifiers

• Main Authors: Al-Gubri, Qusay, Mohd Ariff, Mohd Aifaa
• Format: Article
• Language: English
• Published: The Scientific and Technological Research Council of Turkey 2017
• Subjects: TK1001-1841 Production of electric energy or power. Powerplants. Central stations
• Online Access: http://eprints.uthm.edu.my/3958/1/AJ%202017%20%28546%29.pdf; http://eprints.uthm.edu.my/3958/; https://dx.doi.org/10.3906/elk-1705-268
• Institution: Universiti Tun Hussein Onn Malaysia

This paper proposed a novel algorithm based on advanced feature selection technique for decision tree (DT) classifier to assess the dynamic security in power system. The proposed methodology utilized symmetrical uncertainty (SU) to reduce the data redundancy in a dataset for DT classifier based dynamic security assessment (DSA) tools. The results show that SU reduces the dimension of the dataset used for DSA significantly. Subsequently, the approach improves the performance of DT classifier. The effectiveness of the proposed technique is demonstrated on modified IEEE 30-bus test system model. The results show that the DT classifier with SU outperform the DT classifier without SU. The performance of the proposed algorithm indicates that the DT classifier with SU is able to assess the dynamic security of the system in near real-time. Therefore, it is able to provide vital information for protection and control application in power system operation.