A hybrid approach based economic assessment EV charging station powered by integrating solar PV and biomass

Abstract

In today's world, electric vehicles (EVs) are becoming increasingly popular. A significant power outage occurs in the system when EVs are charged from grid-connected charging stations. This manuscript proposes a hybrid approach for charging station electricity generation by integrating solar PV and biomass. The proposed hybrid technique is a combination of both the Dandelion Optimizer (DO) and Deep Attention Dilated Residual Convolutional Neural Network (DADRCNN). It is hence called DO-DADRCNN. The proposed approach DO is used to optimize the control parameter of the converter. And DADRCNN model used to predict the control parameter of the converter. This paper's main goal is the minimization of levelized cost of energy (LCOE), initial cost and net present cost (NPC). The most ecologically friendly system is the Photo Voltaic (PV)/battery hybrid since it emits no pollutants. The new uses for hybrid renewable energy power systems that combine solar photovoltaics and biogas, as well as an examination of the system's economic and environmental performance. The DAO-DADRCNN approach and the environmental economic evaluation of hybrid sustainable energy systems are intended to be investigated. Biogas and solar PV-based EV charging solutions provide techno economic and environmental feasibility. The proposed strategy is implemented in the MATLAB platform and the emission of carbon-di-oxide (CO2) emission is compared with various existing techniques like Wild horse optimizer, Salp Swarm Algorithm, and Particle Swarm Optimization. The proposed approach DO-DADRCNN obtains lower carbon dioxide (CO2) emission than the existing techniques. The CO2 emissions of the proposed technique is 5 kg/h which is lower and the cost for energy is 0.8$ which is lower than the existing methods.