Predicting voltage abnormality using power systems dynamic response

The purpose of this paper is to analyze dynamic behavior of a stressed power system and to correlate the dynamic responses to the future system voltage abnormality. A pattern recognition method called Regularized Least Square Classification (RLSC) was used to correlate dynamic behavior to system voltage abnormality. This research utilizes PSSE dynamic simulation tool to simulate the stressed cases for dynamic response and uses RLSC method to predict system voltage abnormality in future time after the occurrence of specific contingencies. Dynamics of a stressed IEEE 39 Bus test system is captured by introducing numerous contingencies and by driving the system to the point of abnormal operation and by identifying those simulated contingencies that cause system voltage abnormality. This research will determine the prominent features and parameters in the process of classification of voltage normal and voltage abnormal cases from dynamic simulation data.