Fast Power system security analysis with Guided Dropout

Benjamin Donnot 1, 2, 3 Isabelle Guyon 3, 2 Marc Schoenauer 2, 3 Antoine Marot 1 Patrick Panciatici 1
2 TAU - TAckling the Underspecified
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
Abstract : We propose a new method to efficiently compute load-flows (the steady-state of the power-grid for given productions, consumptions and grid topology), substituting conventional simulators based on differential equation solvers. We use a deep feed-forward neural network trained with load-flows precomputed by simulation. Our architecture permits to train a network on so-called " n-1 " problems, in which load flows are evaluated for every possible line disconnection, then generalize to " n-2 " problems without retraining (a clear advantage because of the combinatorial nature of the problem). To that end, we developed a technique bearing similarity with " dropout " , which we named " guided dropout ".
Type de document :
Communication dans un congrès
26th European Symposium on Artificial Neural Networks, Apr 2018, Bruges, Belgium. Electronic Proceedings ESANN 2018. 〈https://www.elen.ucl.ac.be/esann/proceedings/papers.php?ann=2018〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01695793
Contributeur : Benjamin Donnot <>
Soumis le : lundi 29 janvier 2018 - 17:16:36
Dernière modification le : jeudi 7 février 2019 - 14:49:35
Document(s) archivé(s) le : vendredi 25 mai 2018 - 14:32:51

Fichiers

main.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01695793, version 1
  • ARXIV : 1801.09870

Citation

Benjamin Donnot, Isabelle Guyon, Marc Schoenauer, Antoine Marot, Patrick Panciatici. Fast Power system security analysis with Guided Dropout. 26th European Symposium on Artificial Neural Networks, Apr 2018, Bruges, Belgium. Electronic Proceedings ESANN 2018. 〈https://www.elen.ucl.ac.be/esann/proceedings/papers.php?ann=2018〉. 〈hal-01695793〉

Partager

Métriques

Consultations de la notice

612

Téléchargements de fichiers

143