Learning to run a power network challenge for training topology controllers

被引:37
作者
Marot, Antoine [1 ]
Donnot, Benjamin [1 ]
Romero, Camilo [1 ]
Donon, Balthazar [1 ]
Lerousseau, Marvin [2 ,3 ,4 ]
Veyrin-Forrer, Luca [5 ]
Guyon, Isabelle [5 ]
机构
[1] Reseau Transport Elect Paris, Paris, France
[2] INSERM, Paris, France
[3] CVN Cent Supelec, Paris, France
[4] INRIA, Paris, France
[5] Univ Paris Saclay, TAU Grp, Lab Res Informat UPSud, INRIA, Paris, France
关键词
Artificial intelligence; Control; Power flow; Reinforcement learning; Competition;
D O I
10.1016/j.epsr.2020.106635
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
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.
引用
收藏
页数:8
相关论文
共 17 条
[11]  
Lerousseau M.
[12]  
Sutton R.S., Barto A.G., Reinforcement learning an introduction, MIT press, (2018)
[13]  
Mnih V., Badia A.P., Et al., Asynchronous methods for deep reinforcement learning, CoRR, abs/1602.01783, (2016)
[14]  
Wang Z., de Freitas N., Lanctot M., Dueling network architectures for deep reinforcement learning, CoRR, abs/1511.06581, (2015)
[15]  
Mnih V., al, Human-level control through deep reinforcement learning, Nature, 518, 7540, pp. 529-533, (2015)
[16]  
Rahwan I., al, Machine behaviour, Nature, (2019)
[17]  
Osband I., (2019)