Adversarial Training for a Continuous Robustness Control Problem in Power Systems

TL;DR

This paper introduces an efficient adversarial training method for power system controllers that enhances robustness against cyber-physical threats, tested on a realistic power network simulation.

Contribution

It presents a novel adversarial training approach with a fixed opponent policy for power system control, improving online robustness and computational efficiency.

Findings

Adversarial training improves agent robustness in power systems.

Some agents exhibit preventive behaviors against N-1 contingencies.

Method is computationally efficient for online use.

Abstract

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.