Fast Power system security analysis with Guided Dropout
This addresses the combinatorial challenge of power grid security analysis for grid operators, though it appears incremental as it builds on existing neural network and dropout techniques.
The paper tackles the problem of efficiently computing load-flows in power systems by replacing conventional simulators with a deep neural network trained on precomputed data, achieving generalization from 'n-1' to 'n-2' problems without retraining.
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".