I am working on a smart grid system which can be modeled with multiple agents interacting with each other. The agents are physically coupled with non-linearities, the action of one agent has a direct effect on the other agent.
I am trying to figure out which approach to use to control the system while maintaining autonomy. However it seems very hard to decide on one control strategy, as there are so many. Multi-Agent Reinforcement Learning can be considered, as well as Distributed Control strategies (like Distributed MPC) or other algorithms from the field of game theory.
Right now I am super confused which approach would be the best for my problem. I would be very glad to see any recommendations or papers or books where I can get a good overview.
Thanks a lot!