Can I read Fast Power system security analysis with Guided Dropout on EtoBox?

Fast Power system security analysis with Guided Dropout by Donnot, Benjamin; Guyon, Isabelle; Schoenauer, Marc; Marot, Antoine; Panciatici, Patrick is a scholarly article available to read on EtoBox.

What is Fast Power system security analysis with Guided Dropout about?

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".

Author

Donnot, Benjamin; Guyon, Isabelle; Schoenauer, Marc; Marot, Antoine; Panciatici, Patrick

Published

2018

Language

EN