Electric vehicle with smart grid integration using a hybrid honey badger algorithm and artificial neural network

Electric vehicles (EVs) are a specific class of vehicles that use one or more electric motors to create propulsion. Numerous recent research studies have focused on energy storage systems (ESS) as a major research area. However, as EV usage grows, there are several challenges related to the electricity required for charging that result in peak demand of smart grids with EV stations. The probable impacts of integrating EVs and photovoltaic (PV) into the grid, on certain individuals, are the subjects of numerous researches. The main motivation for PV's incorporation in grid-to-vehicle (G2V) and vehicle-to-grid (V2G) services is to provide supplementary power services to preserve the grid stability. PV arrays have to meet one more need before they choose to offer V2G services. Controlling the power between different load and source conditions requires a number of analyses. Therefore, a hybrid intuitive model was developed that implements a honey badger algorithm and artificial neural network (HBA-ANN) controller to balance grids and frequency. With the inclusion of PV generation, the proposed HBA-ANN optimizes the G2V or V2G outline of the EVs using dynamic programming. The result analysis clearly shows that the proposed HBA-ANN controller's overall efficacy surpasses that of existing controllers based on artificial neural network-based particle swarm optimization (ANN-PSO) and resettable integrator (RI). The evaluation, conducted in terms of overall harmonic distortion, power loss, and efficiency, demonstrates that the proposed HBA-ANN controller achieves 3.26%, 0.186 kW, and 97.14%, respectively.