Graph neural networks for power grid operational risk assessment under evolving unit commitment

Abstract

This article investigates the ability of graph neural networks (GNNs) to identify risky conditions in a power grid over the subsequent few hours, without explicit, high-resolution information regarding future generator on/off status or power dispatch decisions. The GNNs are trained using supervised learning to predict the power grid’s aggregated bus-level (either zonal or system-level) or individual branch-level state under different power supply and demand conditions. The variability of the stochastic grid variables (wind/solar generation and load demand), and their statistical correlations, are considered while generating the inputs for the training data. The outputs in the training data include system-level, zonal and transmission line-level quantities of interest (QoIs). The ground truth of QoIs are obtained by numerically solving deterministic optimization problems (e.g., security-constrained unit commitment) with the same inputs. The GNN predictions are used to conduct hours-ahead, sampling-based reliability and risk assessment w.r.t. zonal and system-level (load shedding) as well as branch-level (overloading) failure events. The proposed methodology is demonstrated for three synthetic grids with sizes ranging from 118 to 2848 buses. Our results demonstrate that GNNs are capable of providing fast and accurate prediction of QoIs and can be good proxies for computationally expensive optimization algorithms. The excellent accuracy of GNN-based reliability and risk assessment suggests that GNN models can substantially improve situational awareness by enabling quick, high-resolution reliability and risk estimation.