Generating adversarial inputs for a graph neural network model of AC power flow
This work addresses the vulnerability of neural network surrogate models in power systems, which is an incremental step toward improving verification and robustness.
The paper tackled the problem of generating adversarial inputs for a graph neural network model of AC power flow, resulting in errors as large as 3.4 per-unit in reactive power and 0.08 per-unit in voltage magnitude, with minimal perturbations of 0.04 per-unit in voltage magnitude on a single bus.
This work formulates and solves optimization problems to generate input points that yield high errors between a neural network's predicted AC power flow solution and solutions to the AC power flow equations. We demonstrate this capability on an instance of the CANOS-PF graph neural network model, as implemented by the PF$Δ$ benchmark library, operating on a 14-bus test grid. Generated adversarial points yield errors as large as 3.4 per-unit in reactive power and 0.08 per-unit in voltage magnitude. When minimizing the perturbation from a training point necessary to satisfy adversarial constraints, we find that the constraints can be met with as little as an 0.04 per-unit perturbation in voltage magnitude on a single bus. This work motivates the development of rigorous verification and robust training methods for neural network surrogate models of AC power flow.