Power System Cascading Outages Assessment Based On Pattern Recognition

Large-scale blackouts of electrical power systems have been concerned around the world in recent years. Most of the blackouts are caused by cascading outage, the study of which has been a popular issue nowadays. This paper brings forward an evaluation method of the power system cascading outages based on the Pattern Recognition. We have built cascading outage process simulating platform using software, Delphi and BPA. The platform can simulate the main process of the cascading outages to get enough sample data. Then, the paper presents a power system cascading outage assessment methods based on BP neural networks and the Support Vector Machine (SVM) technology. The main aim of the methods is to research that whether the different flow level will influence the incidence of the cascading outage and compare the two different results from the models. The validity of this method has been proved by the test result got from the application on the IEEE 39 nodes system.