Skip to Main content Skip to Navigation
Journal articles

Learning to run a power network challenge for training topology controllers

Abstract : For power grid operations, a large body of research focuses on using generation redispatching, load shedding or demand side management flexibilities. However, a less costly and potentially more flexible option would be grid topology reconfiguration, as already partially exploited by Coreso (European RSC) and RTE (French TSO) operations. Beyond previous work on branch switching, bus reconfigurations are a broader class of action and could provide some substantial benefits to route electricity and optimize the grid capacity to keep it within safety margins. Because of its non-linear and combinatorial nature, no existing optimal power flow solver can yet tackle this problem. We here propose a new framework to learn topology controllers through imitation and reinforcement learning. We present the design and the results of the first "Learning to Run a Power Network" challenge released with this framework. We finally develop a method providing performance upper-bounds (oracle), which highlights remaining unsolved challenges and suggests future directions of improvement.
Document type :
Journal articles
Complete list of metadata

https://hal.inria.fr/hal-03159692
Contributor : Marc Schoenauer <>
Submitted on : Thursday, March 4, 2021 - 4:25:13 PM
Last modification on : Thursday, April 8, 2021 - 3:41:03 AM

File

1912.04211.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Antoine Marot, Benjamin Donnot, Camilo Romero, Luca Veyrin-Forrer, Marvin Lerousseau, et al.. Learning to run a power network challenge for training topology controllers. Electric Power Systems Research, Elsevier, 2020, 189, pp.106635. ⟨10.1016/j.epsr.2020.106635⟩. ⟨hal-03159692⟩

Share

Metrics

Record views

67

Files downloads

394