Using “optimization” technique

Warning

This page is in progress. We welcome any contribution :-)

See some examples in:

  • “l2rpn-baselines”, for example the OptimCVXPY agent

  • Jan Hendrick Menke PP_Baseline an optimizer based on pandapower OPF available here PandapowerOPFAgent

  • An optimizer developed by RTE able to change the topology MILP Agent

Basically an “optimizer” agent looks like (from a very high level):

  1. have a simplification of the “MDP” / decision process in the shape of an optimziation problem

  2. make a formulation of this problem using a “framework” preferably in python (eg using pandapower, cvxpy or or-tools)

  3. update the “formulation” using the observation received

  4. run a solver to solve the “problem”

  5. convert back the “decisions” (output) of the solver into a “grid2op” action

If you still can’t find what you’re looking for, try in one of the following pages:

Still trouble finding the information ? Do not hesitate to send a github issue about the documentation at this link: Documentation issue template