OPF-Learn: An Open-Source Framework for Creating Representative AC Optimal Power Flow Datasets

TL;DR

OPF-Learn is an open-source framework that efficiently generates comprehensive and representative datasets for AC optimal power flow, enhancing the training and benchmarking of data-driven power system models.

Contribution

The paper introduces OPF-Learn, a novel framework for creating diverse, representative AC OPF datasets using convex set sampling and infeasibility certificates, addressing dataset creation challenges.

Findings

Generated datasets are more representative of the feasible space.

Improved machine learning model performance on power flow tasks.

Framework is computationally efficient and open-source.

Abstract

Increasing levels of renewable generation motivate a growing interest in data-driven approaches for AC optimal power flow (AC OPF) to manage uncertainty; however, a lack of disciplined dataset creation and benchmarking prohibits useful comparison among approaches in the literature. To instill confidence, models must be able to reliably predict solutions across a wide range of operating conditions. This paper develops the OPF-Learn package for Julia and Python, which uses a computationally efficient approach to create representative datasets that span a wide spectrum of the AC OPF feasible region. Load profiles are uniformly sampled from a convex set that contains the AC OPF feasible set. For each infeasible point found, the convex set is reduced using infeasibility certificates, found by using properties of a relaxed formulation. The framework is shown to generate datasets that are more representative of the entire feasible space versus traditional techniques seen in the literature, improving machine learning model performance.