Microgrid Frequency Disturbance Mitigation by Reinforcement Learning Controlled V2G

I want to simulate V2G to mitigate the frequency disturbance of the microgrid. The microgrid consists of several plants (EV, PV, Wind etc). The math model of plants is attached. The disturbance is applied to the microgrid. V2G controlled by Reinforcement Learning (RL) mitigate this frequency disturbance. A similar paper is attached as a reference.