Dynamic load management for a residential customer; Reinforcement Learning approach

• Modelling a residential customer to be adaptable with Reinforcement Learning (RL) algorithm.
• Fully automated dynamic load management based on RL algorithm is introduced.
• We propose a cloud computing (CC) architecture to handle tremendous generation data.
• Proposed algorithm increases efficiency of energy system substantial.

United Nation aims to double the global rate of improvement in energy efficiency as one of the sustainable development goals. It means researchers should focus on energy systems to enhance their overall efficiency. One of the effective solution to move from suboptimal energy systems to optimal ones is analyzing energy system in Energy Hub (EH) framework. In EH framework, interactions between different energy carriers are considered in supplying the required loads. The couplings and selecting proper combinations of inputs energy carriers lead to more optimized and intelligent consumption. The appropriate combination is found by solving an optimization problem at each time step. Utilizing intelligent technologies such as Advanced Metering Infrastructures (AMIs) inevitably facilitate the decision making processes. This paper modifies the classic Energy Hub model to present an upgraded model in the smart environment entitling “Smart Energy Hub” and optimizes the operation of a residential customer equipped with combined heat and power (CHP), auxiliary boiler, electricity storage and heating storage in this framework. Supporting real time, two-way communication between utility companies and smart energy hubs, and allowing AMIs at both ends to manage power consumption necessitates large-scale real-time computing capabilities to handle the communication and the storage of huge transferable data. To address this concern and reduce the amount of calculations, Reinforcement Learning (RL) method is employed to find a near optimal solution, which does not need massive computations. Finally, communications to large numbers of endpoints in a secure, scalable, and highly-available environment, in this paper, we propose a cloud computing (CC) architecture. Simulation results show that by applying RL technique in smart energy hub framework for a residential customer, efficiency of the energy system is increased substantially and leads to decrease energy bills and electricity peak load.