Applying reinforcement learning method to optimize an Energy Hub operation in the smart grid

New days, the concepts of “Smart Grid” and “Energy Hub” have been introduced to improve the operation of the energy systems. This paper introduces a new conception entitling Smart Energy Hub (S. E. Hub), as a multi-carrier energy system in a smart grid environment. To show the application of this novel idea, we present a residential S. E. Hub which employs Reinforcement Learning (RL) method for finding a near optimal solution. The simulation results show that by applying the S. E. Hub model and then using the proposed method for a residential customer, running cost is reduced substantially. While, comparing with the classical ones, the RL method does not require any data about the environment and either equipment´s parameters.