English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper proposes a new data-driven method for the reliable prediction ofpower system post-fault trajectories. The proposed method is based on thefundamentally new concept of Deep Operator Networks (DeepONets). Compared totraditional neural networks that learn to approximate functions, DeepONets aredesigned to approximate nonlinear operators. Under this operator framework, wedesign a DeepONet to (1) take as inputs the fault-on trajectories collected,for example, via simulation or phasor measurement units, and (2) provide asoutputs the predicted post-fault trajectories. In addition, we endow our methodwith a much-needed ability to balance efficiency with reliable/trustworthypredictions via uncertainty quantification. To this end, we propose and comparetwo methods that enable quantifying the predictive uncertainty. First, wepropose a \textit{Bayesian DeepONet} (B-DeepONet) that uses stochastic gradientHamiltonian Monte-Carlo to sample from the posterior distribution of theDeepONet parameters. Then, we propose a \textit{Probabilistic DeepONet}(Prob-DeepONet) that uses a probabilistic training strategy to equip DeepONetswith a form of automated uncertainty quantification, at virtually no extracomputational cost. Finally, we validate the predictive power and uncertaintyquantification capability of the proposed B-DeepONet and Prob-DeepONet usingthe IEEE 16-machine 68-bus system.

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