Adversarial Training for a Continuous Robustness Control Problem in Power Systems
This work addresses the problem of designing robust and computationally efficient controllers for cyber-physical power systems, which is crucial for grid stability and security.
This paper proposes an adversarial training approach for designing robust controllers for cyber-physical power systems. The method is computationally efficient online and demonstrates useful robustness properties, particularly preventive behaviors against continuous N-1 problems in a synthetic power network environment.
We propose a new adversarial training approach for injecting robustness when designing controllers for upcoming cyber-physical power systems. Previous approaches relying deeply on simulations are not able to cope with the rising complexity and are too costly when used online in terms of computation budget. In comparison, our method proves to be computationally efficient online while displaying useful robustness properties. To do so we model an adversarial framework, propose the implementation of a fixed opponent policy and test it on a L2RPN (Learning to Run a Power Network) environment. This environment is a synthetic but realistic modeling of a cyber-physical system accounting for one third of the IEEE 118 grid. Using adversarial testing, we analyze the results of submitted trained agents from the robustness track of the L2RPN competition. We then further assess the performance of these agents in regards to the continuous N-1 problem through tailored evaluation metrics. We discover that some agents trained in an adversarial way demonstrate interesting preventive behaviors in that regard, which we discuss.