Skip to content

qsrmlhj/L2RPN-2021

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

L2RPN

The fourth place solution for Learning to Run a Power Network - ICAPS 2021 Competition

Competition Link

Approach

For the operational part, we train a DDQN model to select an appropriate action from the action space. When we have a overflow in power network. If there is not appropriate action, we will choose action from the additional action space.

For the alarm part, we use flow entrophy of power network to decide whether or not to trigger the alarm in the current timestep.

License

This content is released under the Mozilla Public License (MPL) v2.0.

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages