Using trajectory clusters to define the most relevant features for transient stability prediction based on machine learning method

Abstract

To achieve rapid real-time transient stability prediction, a power system transient stability prediction method based on the extraction of the post-fault trajectory cluster features of generators is proposed. This approach is conducted using data-mining techniques and support vector machine (SVM) models. First, the post-fault rotor angles and generator terminal voltage magnitudes are considered as the input vectors. Second, we construct a high-confidence dataset by extracting the 27 trajectory cluster features obtained from the chosen databases. Then, by applying a filter-wrapper algorithm for feature selection, we obtain the final feature set composed of the eight most relevant features for transient stability prediction, called the global trajectory clusters feature subset (GTCFS), which are validated by receiver operating characteristic (ROC) analysis. Comprehensive simulations are conducted on a New England 39-bus system under various operating conditions, load levels and topologies, and the transient stability predicting capability of the SVM model based on the GTCFS is extensively tested. The experimental results show that the selected GTCFS features improve the prediction accuracy with high computational efficiency. The proposed method has distinct advantages for transient stability prediction when faced with incomplete Wide Area Measurement System (WAMS) information, unknown operating conditions and unknown topologies and significantly improves the robustness of the transient stability prediction system.