Objectives
This project will develop a framework using advanced machine learning techniques to be integrated with PNNL’s Dynamic Contingency Analysis Tool (DCAT) database module to assess impacts of extreme contingencies in future grid scenarios on cascading failures. The aim of this work is to assess the security of the future grid by developing advanced machine learning methods for analyzing the diverse scenarios that are not part of the present system and help the power system engineers to perform numerous planning studies. Adding advanced machine learning to DCAT simulations will enable enhanced analytics of large volumes of results and direct the selection of scenarios.