LEAP nets for power grid perturbations
This work addresses the challenge of rapid assessment of emergency actions for power grid operators, though it appears incremental as it builds on existing transfer learning methods.
The authors tackled the problem of modeling power transmission grids with atypical perturbations by proposing LEAP nets, a neural network embedding approach that uses transfer learning to generalize to new domains without training examples, achieving viability for assessing curative actions in emergency situations using real historical data from the French high voltage grid.
We propose a novel neural network embedding approach to model power transmission grids, in which high voltage lines are disconnected and reconnected with one-another from time to time, either accidentally or willfully. We call our architeture LEAP net, for Latent Encoding of Atypical Perturbation. Our method implements a form of transfer learning, permitting to train on a few source domains, then generalize to new target domains, without learning on any example of that domain. We evaluate the viability of this technique to rapidly assess cu-rative actions that human operators take in emergency situations, using real historical data, from the French high voltage power grid.