Spatial Network Decomposition for Fast and Scalable AC-OPF Learning

TL;DR

This paper introduces a two-stage spatial decomposition machine learning method for fast, scalable, and accurate prediction of AC-OPF solutions, addressing topology variability and reducing training time.

Contribution

It presents a novel spatial decomposition approach that enables parallel training and prediction for large power networks, significantly improving speed and fidelity over existing methods.

Findings

High-fidelity AC-OPF predictions with minor violations

Rapid training times for large-scale networks

Predictions enable near-optimal feasible solutions

Abstract

This paper proposes a novel machine-learning approach for predicting AC-OPF solutions that features a fast and scalable training. It is motivated by the two critical considerations: (1) the fact that topology optimization and the stochasticity induced by renewable energy sources may lead to fundamentally different AC-OPF instances; and (2) the significant training time needed by existing machine-learning approaches for predicting AC-OPF. The proposed approach is a 2-stage methodology that exploits a spatial decomposition of the power network that is viewed as a set of regions. The first stage learns to predict the flows and voltages on the buses and lines coupling the regions, and the second stage trains, in parallel, the machine-learning models for each region. Experimental results on the French transmission system (up to 6,700 buses and 9,000 lines) demonstrate the potential of the approach. Within a short training time, the approach predicts AC-OPF solutions with very high fidelity and minor constraint violations, producing significant improvements over the state-of-the-art. The results also show that the predictions can seed a load flow optimization to return a feasible solution within 0.03% of the AC-OPF objective, while reducing running times significantly.