Physics-Aware Heterogeneous GNN Architecture for Real-Time BESS Optimization in Unbalanced Distribution Systems

TL;DR

This paper introduces a physics-aware heterogeneous GNN architecture that accurately models three-phase unbalanced distribution systems with BESS, ensuring feasible and reliable real-time dispatch by embedding grid physics and constraints.

Contribution

It develops a novel GNN-based approach with physics-informed loss functions that explicitly incorporate three-phase grid details and battery constraints for improved BESS dispatch.

Findings

Achieves high-accuracy network state predictions with low voltage errors.

Ensures near-zero violations of battery SoC and C-rate constraints.

Demonstrates effectiveness on the CIGRE 18-bus system.

Abstract

Battery energy storage systems (BESS) have become increasingly vital in three-phase unbalanced distribution grids for maintaining voltage stability and enabling optimal dispatch. However, existing deep learning approaches often lack explicit three-phase representation, making it difficult to accurately model phase-specific dynamics and enforce operational constraints--leading to infeasible dispatch solutions. This paper demonstrates that by embedding detailed three-phase grid information--including phase voltages, unbalanced loads, and BESS states--into heterogeneous graph nodes, diverse GNN architectures (GCN, GAT, GraphSAGE, GPS) can jointly predict network state variables with high accuracy. Moreover, a physics-informed loss function incorporates critical battery constraints--SoC and C-rate limits--via soft penalties during training. Experimental validation on the CIGRE 18-bus distribution system shows that this embedding-loss approach achieves low prediction errors, with bus voltage MSEs of 6.92e-07 (GCN), 1.21e-06 (GAT), 3.29e-05 (GPS), and 9.04e-07 (SAGE). Importantly, the physics-informed method ensures nearly zero SoC and C-rate constraint violations, confirming its effectiveness for reliable, constraint-compliant dispatch.