Constraint-Informed Active Learning for End-to-End ACOPF Optimization Proxies

TL;DR

This paper presents a novel active sampling framework for training machine learning models to predict ACOPF solutions, improving their generalization and reliability by generating diverse, realistic training data using optimization-specific features.

Contribution

Introduces a constraint-informed active sampling method that enhances training data quality for ACOPF proxies, leading to better generalization and trustworthiness.

Findings

Superior generalization over existing methods

Effective use of active constraint sets

Significant improvement with same training budget

Abstract

This paper studies optimization proxies, machine learning (ML) models trained to efficiently predict optimal solutions for AC Optimal Power Flow (ACOPF) problems. While promising, optimization proxy performance heavily depends on training data quality. To address this limitation, this paper introduces a novel active sampling framework for ACOPF optimization proxies designed to generate realistic and diverse training data. The framework actively explores varied, flexible problem specifications reflecting plausible operational realities. More importantly, the approach uses optimization-specific quantities (active constraint sets) that better capture the salient features of an ACOPF that lead to the optimal solution. Numerical results show superior generalization over existing sampling methods with an equivalent training budget, significantly advancing the state-of-practice for trustworthy ACOPF optimization proxies.