#artificial intelligence
May 2026
Scalable Heterogeneous Graph Foundation Models for Data-Driven Optimal Power Flow in Smart Grids
A large-scale heterogeneous graph-learning workflow, built on HydraGNN, for data-driven OPF surrogate modeling and graph foundation-model (GFM) development and shows that partial fine-tuning provides the strongest balance between predictive performance and computational requirements.
Massimiliano Lupo Pasini, Yi-Jiang Li, Kibaek Kim et al.
· arXiv.org · 2 citations