April, Tuesday 3rd
14:30 (room 2014, 'Digiteo Shannon' 660 building) (see location)Benjamin Donnot
(TAU team)Title: Fast Power system security analysis with Guided Dropout
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 differ-
ential 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 eval-
uated for every possible line disconnection, then generalize to ”n-2” prob-
lems without re-training (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”.
Contact: guillaume.charpiat at inria.fr
All TAU seminars: here