Self-Supervised Graph Neural Networks for Full-Scale Tertiary Voltage Control
This addresses the problem of inefficient real-time voltage control for power grid operators, though it is incremental as it builds on existing GNN and optimization methods for a specific domain.
The paper tackles the scalability issue of Tertiary Voltage Control (TVC) in power grids by framing it as an amortized optimization problem and using a self-supervised Graph Neural Network (GNN) to minimize voltage violations, resulting in a significant reduction in the average number of voltage violations after training on one year of full-scale French grid data.
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.