This experiment creatively uses Quantum Reinforcement Learning （QRL） to solve the energy scheduling problem of EMS and proposes the Q-EMS framework. As a comparison, the current cutting-edge DQN strategy is used as baseline1 and Fixed scheme as baseline2.
The code file contains the following sections:
- result
This folder holds the data related to the experiment and saves the experimental data as .npy for easy graphing and reproduction.
- resultfig
This folder holds the figures related to the experiment, and each of its sub_folders is the code that generates each images.
- utils
This folder holds experimentally relevant datasets.
- requirement.txt
This folder holds the packages for the adaptations needed to equip the QRL.
- other .py file
The relevant python code for each strategy ( Q-EMS , DQN , Fixed ).