Adversarial optimization leads to over-optimistic security-constrained dispatch, but sampling can help

TL;DR

This paper reveals that adversarial optimization in security-constrained dispatch can overestimate system robustness due to local minima, and proposes a sampling method to improve reliability and prevent overconfidence.

Contribution

The paper introduces a novel adversarial sampling approach that enhances robustness estimation and mitigates overconfidence in security-constrained dispatch.

Findings

Sampling improves robustness of dispatch solutions

Method accurately predicts voltage collapse likelihood

Overconfidence is reduced with the new approach

Abstract

To ensure safe, reliable operation of the electrical grid, we must be able to predict and mitigate likely failures. This need motivates the classic security-constrained AC optimal power flow (SCOPF) problem. SCOPF is commonly solved using adversarial optimization, where the dispatcher and an adversary take turns optimizing a robust dispatch and adversarial attack, respectively. We show that adversarial optimization is liable to severely overestimate the robustness of the optimized dispatch (when the adversary encounters a local minimum), leading the operator to falsely believe that their dispatch is secure. To prevent this overconfidence, we develop a novel adversarial sampling approach that prioritizes diversity in the predicted attacks. We find that our method not only substantially improves the robustness of the optimized dispatch but also avoids overconfidence, accurately characterizing the likelihood of voltage collapse under a given threat model. We demonstrate a proof-of-concept on small-scale transmission systems with 14 and 57 nodes.