Self-Supervised Graph Neural Networks for Full-Scale Tertiary Voltage Control

TL;DR

This paper introduces a self-supervised GNN approach to improve real-time tertiary voltage control by reducing voltage violations in large-scale power grids, bypassing traditional optimization limitations.

Contribution

It presents a novel self-supervised GNN method for TVC that effectively reduces voltage violations without requiring optimality guarantees, suitable for large-scale systems.

Findings

Trained on one year of French power grid data.

Significantly reduces average voltage violations.

Operates as a proxy for existing forecasting pipelines.

Abstract

A growing portion of operators workload is dedicated to Tertiary Voltage Control (TVC), namely the regulation of voltages by means of adjusting a series of setpoints and connection status. TVC may be framed as a Mixed Integer Non Linear Program, but state-of-the-art optimization methods scale poorly to large systems, making them impractical for real-scale and real-time decision support. Observing that TVC does not require any optimality guarantee, we frame it as an Amortized Optimization problem, addressed by the self-supervised training of a Graph Neural Network (GNN) to minimize voltage violations. As a first step, we consider the specific use case of post-processing the forecasting pipeline used by the French TSO, where the trained GNN would serve as a TVC proxy. After being trained on one year of full-scale HV-EHV French power grid day-ahead forecasts, our model manages to significantly reduce the average number of voltage violations.