Mechanism Analysis of Power Grid Cascading Failures Based on Data Mining Algorithm

The defects of the present fault chain model of power grid cascading failures have been summarized and a defined method for forecasting cascading failures is presented based on a fault chain model and Fuzzy C-Means. First, in order to reduce the workload and overcome the limitation of present means, this method selects a number of lines with the high value of predictive index to be the next outage lines during fault chain forecasting. Then, this paper analyzes the correlations among lines. Finally, taking IEEE 39-bus system as example, the rationality of the method proposed is verified based on comparison with other means.