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)

1 RTE - Réseau de Transport d'Electricité [Paris]
2 TAU - TAckling the Underspecified
3 LRI - Laboratoire de Recherche en Informatique

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 ".

Domaines: Machine Learning [stat.ML]; Energie électrique

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. ⟨hal-01695793⟩