Electric vehicle charge scheduling using an artificial neural network

With the integration of EVs into the power grid, smart metering using machine-to-machine (M2M) communication is likely to play an important role in real-time energy management and control. Smart devices embedded with advanced metering infrastructure (AMI) can forecast the energy demand as well as perform energy pricing in real time. In this paper, an artificial neural network (ANN) based intelligent decision-making system is presented that utilises data logged by an M2M AMI for EV charge scheduling and load management. The ANN was trained using household power consumption and EV energy demand data, and was used to decide when a vehicle should charge (G2V), or could discharge (V2G).