Maximal Load Shedding Verification for Neural Network Models of AC Line Switching

TL;DR

This paper presents a verification method for neural network models used in AC line switching, ensuring their worst-case load shedding impact is accurately bounded through a convex relaxation and local search, enhancing reliability in power grid operations.

Contribution

Introduces a bilevel verification approach combining convex relaxation and local search to bound worst-case load shedding of neural network models in power systems.

Findings

Optimization-based approach finds larger load shedding than random sampling.

Method provides guaranteed lower bounds on worst-case load shedding.

Applicable to large neural network models with over 10 million parameters.

Abstract

Solving for globally optimal line switching decisions in AC transmission grids can be intractability slow. Machine learning (ML) models, meanwhile, can be trained to predict near-optimal decisions at a fraction of the speed. Verifying the performance and impact of these ML models on network operation, however, is a critically important step prior to their actual deployment. In this paper, we train a Neural Network (NN) to solve the optimal power shutoff line switching problem. To assess the worst-case load shedding induced by this model, we propose a bilevel attacker-defender verification approach that finds the NN line switching decisions that cause the highest quantity of network load shedding. Solving this problem to global optimality is challenging (due to AC power flow and NN nonconvexities), so our approach exploits a convex relaxation of the AC physics, combined with a local NN search, to find a guaranteed lower bound on worst--case load shedding. These under-approximation bounds are solved via MathOptAI.jl. We benchmark against a random sampling approach, and we find that our optimization-based approach always finds larger load shedding. Test results are collected on multiple PGLib test cases and on trained NN models which contain more than 10 million model parameters.