PNNL

Abstract

This paper has delved into the pressing need for intelligent emergency control in large-scale power systems, which are experiencing significant transformations and are operating closer to their limits with more uncertainties and less inertia. Learning-based control methods are promising and have shown effectiveness for intelligent power system control. However, when they are applied for large-scale power systems, there are the multifaceted challenges such as scalability, adaptiveness, and security posed by the complex power system landscape. The paper proposes and instantiates a convergence framework integrating power systems physics, machine learning, advanced computing, and grid control to realize intelligent grid control at a large scale. Our developed methods and platform based on this convergence framework has been applied on a large (more than 3000 buses) synthetic Texas system, and tested with an unprecedented 56000 scenarios. Our work achieved 26\% reduction in load shedding on average, and outperformed existing rule-based control in 99.7\% of the test scenarios. The results demonstrated the potential of proposed convergence framework and DRL-based intelligent control for future grid.