“21st PSCC 2020 papers submission and review platform

Full Program »

Learning to run a power network challenge for training topology controllers

View File
PDF
2.0MB

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 actions 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.

Author(s):

Antoine Marot    
RTE
France

Benjamin Donnot    
RTE
France

Marvin Lerousseau    
CentraleSupelec
France

Camilo Romero    
RTE
France

Isabelle Guyon    
UPSud/INRIA Universi´e Paris-Saclay
France

Luca Veyrin-Forrer    
UPSud/INRIA Universi´e Paris-Saclay
France

Balthazar Donon    
RTE
France

 

Powered by OpenConf®
Copyright ©2002-2014 Zakon Group LLC