A new reinforcement learning approach for improving energy trading management for smart microgrids in the internet of things

To face the challenge of climate changes, it is necessary to change the usage of natural energy resources like oil, natural gas and coal to the use of renewable resources like the wind and sun energy providing a tool for efficient network management with using various distributed generation and storage services is a critical issue for smart microgrids. Due to the nature of this type of power grid, reinforcement learning is an online-wide framework for solving scattering problems. Therefore, while considering economic dispatch as a reference method of distributed power grid, its management is modelled locally. Here a distributed algorithm is defined for generalised consumption balancing. The simulation shows that this algorithm has the potential to maintain the stability of the safe and efficient operation of the entire network, taking in to account the local stability. Also, the cost of energy usage is reduced in transmission and distribution system.