LEAP nets for system identification and application to power systems
| Autor: | Patrick Panciatici, Antoine Marot, Benjamin Donnot, Zhengying Liu, Marc Schoenauer, Isabelle Guyon, Balthazar Donon |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
0209 industrial biotechnology
Operating point Power transmission Theoretical computer science Artificial neural network Computer science Cognitive Neuroscience System identification 02 engineering and technology Computer Science Applications Electric power system 020901 industrial engineering & automation Artificial Intelligence Causal inference 0202 electrical engineering electronic engineering information engineering Reinforcement learning 020201 artificial intelligence & image processing Transfer of learning |
| Zdroj: | Neurocomputing. 416:316-327 |
| ISSN: | 0925-2312 |
| Popis: | Using neural network modeling, we address the problem of system identification for continuous multivariate systems, whose structures vary around an operating point. Structural changes in the system are of combinatorial nature, and some of them may be very rare; they may be actionable for the purpose of controlling the system. Although our ultimate goal is both system identification and control, we only address the problem of identification in this paper. We propose and study a novel neural network architecture called LEAP net, for Latent Encoding of Atypical Perturbation. Our method maps system structure changes to neural net structure changes, using structural actionable variables. We demonstrate empirically that LEAP nets can be trained with a natural observational distribution, very concentrated around a “reference” operating point of the system, and yet generalize to rare (or unseen) structural changes. We validate the generalization properties of LEAP nets theoretically in particular cases. We apply our technique to power transmission grids, in which high voltage lines are disconnected and re-connected with one-another from time to time, either accidentally or willfully. We discuss extensions of our approach to actionable variables, which are continuous (instead of discrete, in the case of our application) and make connections between our problem setting, transfer learning, causal inference, and reinforcement learning. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect