Load Encoding for Learning AC-OPF

TL;DR

This paper introduces a load encoding scheme to improve the scalability and accuracy of deep learning models for solving large-scale AC-OPF problems in power systems.

Contribution

It proposes a novel load compression embedding method that significantly enhances training efficiency and prediction accuracy for deep learning models in AC-OPF applications.

Findings

Order of magnitude improvement in training convergence

Enhanced prediction accuracy on large-scale test cases

Effective scalability for real-world power grids

Abstract

The AC Optimal Power Flow (AC-OPF) problem is a core building block in electrical transmission system. It seeks the most economical active and reactive generation dispatch to meet demands while satisfying transmission operational limits. It is often solved repeatedly, especially in regions with large penetration of wind farms to avoid violating operational and physical limits. Recent work has shown that deep learning techniques have huge potential in providing accurate approximations of AC-OPF solutions. However, deep learning approaches often suffer from scalability issues, especially when applied to real life power grids. This paper focuses on the scalability limitation and proposes a load compression embedding scheme to reduce training model sizes using a 3-step approach. The approach is evaluated experimentally on large-scale test cases from the PGLib, and produces an order of magnitude improvements in training convergence and prediction accuracy.