Learning the Evolution of Correlated Stochastic Power System Dynamics

TL;DR

This paper introduces a machine learning approach to model and quantify uncertainty in power system dynamics influenced by correlated stochastic forces, using PDEs for probability densities, suitable for high-dimensional systems.

Contribution

The novel method learns PDEs for probability densities in power systems with correlated stochastic inputs, addressing high-dimensional challenges and uncertainty quantification.

Findings

Effective modeling of correlated stochastic power system dynamics.

Reduces computational complexity for high-dimensional systems.

Provides a framework for uncertainty quantification in power systems.

Abstract

A machine learning technique is proposed for quantifying uncertainty in power system dynamics with spatiotemporally correlated stochastic forcing. We learn one-dimensional linear partial differential equations for the probability density functions of real-valued quantities of interest. The method is suitable for high-dimensional systems and helps to alleviate the curse of dimensionality.