Development of artificial Intelligence-Based adaptive vehicle to grid and grid to vehicle controller for electric vehicle charging station

Abstract

Electric vehicle charging stations (EVCS) that are based on DC microgrids are presented in this research. The system comprises a solar photovoltaic system (SPVS), storage battery (SB), electric vehicle (EV) and grid. The adaptive interaction artificial neural network (AI-ANN)-based vehicle to grid (V2G) and grid to vehicle (G2V) power management controller (PMC) is suggested for DC microgrid based EVCS. This EVCS is suitable for the residential building and offices where EV may be parked. This EVCS provides the facility to manage the power of the building in addition to charge the EVIt has two different modes of operation. The first mode uses the EV as a power source. In the second mode, the EV functions as a load. This controller is developed to acquire electrical power from the solar photovoltaic system (SPVS), storage battery, EV and grid respectively. If the solar photovoltaic system (SPVS) and storage battery power are insufficient to meet the demand, power is extracted from electric vehicle (V2G). If the solar photovoltaic system (SPVS), storage battery and EV are not sufficient to meet up demand, then deficit power is obtained from the grid (G2V). ANN based power management controller (PMC) Also provides a consistent DC bus voltage and reduces overshoot from 9.6 % to 0 %., settling time from 1.18 sec. to 0.52 sec. and rise time from 0.27 sec. to 0.25 sec. of DC bus voltage compared to conventional controller. The suggested power management controller tested for two different modes i.e., V2G and G2V using MATLAB Simulink software.

Keywords

• Neural network
• Bidirectional converter
• Power management
• Electric vehicle (EV)
• Electric vehicle charging station
• Storage battery.