Dual Conic Proxies for AC Optimal Power Flow

TL;DR

This paper introduces a novel machine learning architecture for AC-OPF that provides valid dual bounds by embedding a differentiable feasibility recovery within a convex relaxation, improving efficiency and scalability.

Contribution

It proposes a new architecture for SOC relaxation of AC-OPF that yields valid dual bounds and uses self-supervised learning to reduce training data needs.

Findings

The method efficiently predicts dual bounds for medium- and large-scale power grids.

It outperforms existing approaches in scalability and accuracy.

The approach reduces the need for costly data generation.

Abstract

In recent years, there has been significant interest in the development of machine learning-based optimization proxies for AC Optimal Power Flow (AC-OPF). Although significant progress has been achieved in predicting high-quality primal solutions, no existing learning-based approach can provide valid dual bounds for AC-OPF. This paper addresses this gap by training optimization proxies for a convex relaxation of AC-OPF. Namely, the paper considers a second-order cone (SOC) relaxation of AC-OPF, and proposes \revision{a novel architecture} that embeds a fast, differentiable (dual) feasibility recovery, thus providing valid dual bounds. The paper combines this new architecture with a self-supervised learning scheme, which alleviates the need for costly training data generation. Extensive numerical experiments on medium- and large-scale power grids demonstrate the efficiency and scalability of the proposed methodology.