Short Bio

I am a research officer at RTE (Réseau de Transport d’Électricité) Research & Development. I mainly work on designing Graph Neural Networks to assist power grid operators.

I graduated from the École polytechnique (X2013) and Stanford University (MSc in Civil & Environmental Engineering). I obtained a PhD in Computer Science at Université Paris-Saclay and RTE R&D under the supervision of Isabelle Guyon, Marc Schoenauer, and Rémy Clément. I then worked as a postdoctoral researcher at Institut Montefiore (Université de Liège) with Louis Wehenkel.

I have a strong interest in the Energy domain and its environmental and societal implications, as well as in Artificial Intelligence, more specifically, Graph Neural Networks. My focus is on real-life and real-time Power Systems applications.

Lately, I’ve been working on the open-source package EnerGNN, which is now part of the Linux Foundation for Energy.

Selected Papers

• Antoine Martinez, Balthazar Donon, Louis Wehenkel and Efthymios Karangelos, Self-Supervised Graph Neural Networks for Optimal Substation Reconfiguration, PSCC 2026 (pdf)
• Balthazar Donon, Geoffroy Jamgotchian, Hugo Kulesza, Louis Wehenkel, Self-Supervised Graph Neural Networks for Full-Scale Tertiary Voltage Control, PSCC 2026 (pdf)
• Balthazar Donon, François Cubélier, Efthymios Karangelos, Louis Wehenkel, Laure Crochepierre, Camille Pache, Lucas Saludjian, Patrick Panciatici, Topology-Aware Reinforcement Learning for Tertiary Voltage Control, PSCC 2024 (pdf)
• Balthazar Donon, Deep Statistical Solvers & Power Systems Applications, Université Paris-Saclay 2022. (PhD Manuscript) (pdf)
• Balthazar Donon, Zhengying Liu, Wenzhuo Liu, Isabelle Guyon, Antoine Marot, Marc Schoenauer, Deep statistical solvers, NeurIPS 2020 (pdf)
• Balthazar Donon, Rémy Clément, Benjamin Donnot, Antoine Marot, Isabelle Guyon, Marc Schoenauer, Neural Networks for Power Flow: Graph Neural Solver, PSCC 2020 (pdf)