Real-Time Risk Analysis with Optimization Proxies

TL;DR

This paper introduces a proxy-based method for real-time risk assessment in power systems, using machine learning to rapidly predict economic dispatch outcomes and enable quick risk evaluation amidst increasing renewable integration.

Contribution

It proposes a novel self-supervised learning framework for training optimization proxies that enable fast, accurate risk assessment in power systems.

Findings

Proxies predict economic dispatch outcomes in milliseconds.

The approach scales effectively to large power systems.

High accuracy of risk predictions demonstrated in numerical experiments.

Abstract

The increasing penetration of renewable generation and distributed energy resources requires new operating practices for power systems, wherein risk is explicitly quantified and managed. However, traditional risk-assessment frameworks are not fast enough for real-time operations, because they require numerous simulations, each of which requires solving multiple economic dispatch problems sequentially. The paper addresses this computational challenge by proposing proxy-based risk assessment, wherein optimization proxies are trained to learn the input-to-output mapping of an economic dispatch optimization solver. Once trained, the proxies make predictions in milliseconds, thereby enabling real-time risk assessment. The paper leverages self-supervised learning and end-to-end-feasible architecture to achieve high-quality sequential predictions. Numerical experiments on large systems demonstrate the scalability and accuracy of the proposed approach.