Dynamic vulnerability assessment due to transient instability based on data mining analysis for Smart Grid applications

In recent years, some Smart Grid applications have been designed in order to perform timely Self-Healing and adaptive reconfiguration actions based on system-wide analysis, with the objective of reducing the risk of power system blackouts. Real time dynamic vulnerability assessment (DVA) has to be done in order to decide and coordinate the appropriate corrective control actions, depending on the event evolution. This paper presents a novel approach for carrying out real time DVA, focused on Transient Stability Assessment (TSA), based on some time series data mining techniques (Multichannel Singular Spectrum Analysis MSSA, and Principal Component Analysis PCA), and a machine learning tool (Support Vector Machine Classifier SVM-C). In addition, a general overview of the state of the art of the methods to perform vulnerability assessment, with emphasis in the potential use of PMUs for post-contingency DVA, is described. The developed methodology is tested in the IEEE 39 bus New England test system, where the simulated cause of vulnerability is transient instability. The results show that time series data mining tools are useful to find hidden patterns in electric signals, and SVM-C can use those patterns for effectively classifying the system vulnerability status.