DeepONet-Grid-UQ: A Trustworthy Deep Operator Framework for Predicting the Power Grid's Post-Fault Trajectories

TL;DR

This paper introduces DeepONet-Grid-UQ, a novel operator learning framework for accurately predicting power grid post-fault trajectories with integrated uncertainty quantification, enhancing reliability in power system analysis.

Contribution

It presents a new DeepONet-based method for power grid trajectory prediction that incorporates uncertainty quantification using Bayesian and probabilistic approaches.

Findings

Accurately predicts post-fault trajectories in IEEE 16-machine 68-bus system.

Demonstrates effective uncertainty quantification with two novel methods.

Enhances reliability and trustworthiness of power system predictions.

Abstract

This paper proposes a new data-driven method for the reliable prediction of power system post-fault trajectories. The proposed method is based on the fundamentally new concept of Deep Operator Networks (DeepONets). Compared to traditional neural networks that learn to approximate functions, DeepONets are designed to approximate nonlinear operators. Under this operator framework, we design a DeepONet to (1) take as inputs the fault-on trajectories collected, for example, via simulation or phasor measurement units, and (2) provide as outputs the predicted post-fault trajectories. In addition, we endow our method with a much-needed ability to balance efficiency with reliable/trustworthy predictions via uncertainty quantification. To this end, we propose and compare two methods that enable quantifying the predictive uncertainty. First, we propose a \textit{Bayesian DeepONet} (B-DeepONet) that uses stochastic gradient Hamiltonian Monte-Carlo to sample from the posterior distribution of the DeepONet parameters. Then, we propose a \textit{Probabilistic DeepONet} (Prob-DeepONet) that uses a probabilistic training strategy to equip DeepONets with a form of automated uncertainty quantification, at virtually no extra computational cost. Finally, we validate the predictive power and uncertainty quantification capability of the proposed B-DeepONet and Prob-DeepONet using the IEEE 16-machine 68-bus system.