Deep Convolutional Neural Network for Power System N-1 Contingency Screening and Cascading Outage Screening

In this chapter, a data-driven method is proposed for fast N-1 contingency screening and further cascading outage screening in power systems. The proposed method is a combination of a deep convolutional neural network (CNN) and a depth-first search (DFS) algorithm. First, deep CNN is constructed as a security assessment tool to evaluate the system security status based on observable information. Second, a scenario tree is built to represent the potential operation scenarios and the associated cascading outages. The DFS algorithm is further applied to traverse the tree and to calculate the expected security index value for each cascading outage path on the tree based on the estimated security status from deep CNN. The simulation results of applying the proposed deep CNN and the DFS algorithm on standard test cases verify their accuracy and that their computational efficiency is thousands of times faster than the model-based traditional approach, which implies the great potential of the proposed algorithm for online applications.