Flow-Aware GNN for Transmission Network Reconfiguration via Substation Breaker Optimization

TL;DR

This paper presents OptiGridML, a flow-aware GNN framework that efficiently optimizes power grid topologies by predicting breaker configurations, significantly improving power exports and inference speed over traditional methods.

Contribution

The paper introduces a novel flow-aware GNN architecture that replaces complex MIP solves with fast neural predictions for power grid reconfiguration.

Findings

Achieves up to 18% increase in power exports.

Reduces inference time from hours to milliseconds.

Demonstrates effectiveness on synthetic networks with up to 1,000 breakers.

Abstract

This paper introduces OptiGridML, a machine learning framework for discrete topology optimization in power grids. The task involves selecting substation breaker configurations that maximize cross-region power exports, a problem typically formulated as a mixed-integer program (MIP) that is NP-hard and computationally intractable for large networks. OptiGridML replaces repeated MIP solves with a two-stage neural architecture: a line-graph neural network (LGNN) that approximates DC power flows for a given network topology, and a heterogeneous GNN (HeteroGNN) that predicts breaker states under structural and physical constraints. A physics-informed consistency loss connects these components by enforcing Kirchhoff's law on predicted flows. Experiments on synthetic networks with up to 1,000 breakers show that OptiGridML achieves power export improvements of up to 18% over baseline topologies, while reducing inference time from hours to milliseconds. These results demonstrate the potential of structured, flow-aware GNNs for accelerating combinatorial optimization in physical networked systems.