Physics-Informed Gradient Estimation for Accelerating Deep Learning based AC-OPF

TL;DR

This paper introduces a physics-informed gradient estimation method to accelerate neural network-based solutions for the AC optimal power flow problem, enabling faster and more reliable real-time power grid management.

Contribution

It presents a novel semi-supervised learning framework with data augmentation and new gradient estimation techniques to improve the speed and feasibility of neural network solutions for AC-OPF.

Findings

Neural networks with the proposed gradient estimators achieve feasible, near-optimal solutions.

The approach reduces training complexity and data preparation time.

Numerical simulations confirm the method's effectiveness for real-time applications.

Abstract

The optimal power flow (OPF) problem can be rapidly and reliably solved by employing responsive online solvers based on neural networks. The dynamic nature of renewable energy generation and the variability of power grid conditions necessitate frequent neural network updates with new data instances. To address this need and reduce the time required for data preparation time, we propose a semi-supervised learning framework aided by data augmentation. In this context, ridge regression replaces the traditional solver, facilitating swift prediction of optimal solutions for the given input load demands. Additionally, to accelerate the backpropagation during training, we develop novel batch-mean gradient estimation approaches along with a reduced branch set to alleviate the complexity of gradient computation. Numerical simulations demonstrate that our neural network, equipped with the proposed gradient estimators, consistently achieves feasible and near-optimal solutions. These results underline the effectiveness of our approach for practical implementation in real-time OPF applications.