A
Antoine Marot
Researcher at Réseau de Transport d'Électricité
Publications - 40
Citations - 360
Antoine Marot is an academic researcher from Réseau de Transport d'Électricité. The author has contributed to research in topics: Grid & Computer science. The author has an hindex of 8, co-authored 34 publications receiving 196 citations.
Papers
More filters
Journal ArticleDOI
Neural Networks for Power Flow : Graph Neural Solver
TL;DR: A novel artificial neural network architecture that achieves a more suitable balance between computational speed and accuracy in this context and is robust to variations of injections, power grid topology, and line characteristics.
Proceedings ArticleDOI
Graph Neural Solver for Power Systems
TL;DR: A neural network architecture that emulates the behavior of a physics solver that solves electricity differential equations to compute electricity flow in power grids (so-called "load flow") and learns to solve the load flow problem without overfitting to a specific instance of the problem.
Journal ArticleDOI
Learning to run a power network challenge for training topology controllers
Antoine Marot,Benjamin Donnot,Camilo Romero,Balthazar Donon,Marvin Lerousseau,Luca Veyrin-Forrer,Isabelle Guyon +6 more
TL;DR: In this article, the authors propose a new framework to learn topology controllers through imitation and reinforcement learning, which can provide substantial benefits to route electricity and optimize the grid capacity to keep it within safety margins.
Introducing machine learning for power system operation support
TL;DR: In this article, the authors address the problem of assisting human dispatchers in operating power grids in today's changing context using machine learning, with the goal of increasing security and reducing costs.
Posted Content
Learning to run a power network challenge for training topology controllers.
Antoine Marot,Benjamin Donnot,Camilo Romero,Luca Veyrin-Forrer,Marvin Lerousseau,Balthazar Donon,Isabelle Guyon +6 more
TL;DR: A new framework to learn topology controllers through imitation and reinforcement learning is proposed, which develops a method providing performance upper-bounds (oracle), which highlights remaining unsolved challenges and suggests future directions of improvement.