Optimizing solar photovoltaic and biomass integration for electric vehicle charging stations in metropolitan cities: A hybrid approach

Abstract

This paper proposes a hybrid strategy for designing and optimizing a hybrid solar photovoltaic (PV) and biomass‐based electric vehicle charging station (EVCS) in metropolitan cities. The proposed strategy is the joint execution of the dung beetle optimizer (DBO) and Finite Basis Physics‐Informed Neural Networks Technique. It is hence called the DBO‐FBPINNs approach. The proposed strategy aims are to minimize initial cost and operating cost, net present cost, and levelized cost of energy. The design phase involves the energy storage systems, integration of solar PV panels, and biomass generators to warranty a reliable and continuous power supply for the EV charging infrastructure. Feasibility analysis encompasses various technical, economic, and environmental aspects. The converter's control signal is optimized via the DBO method. The FBPINNs model is used to forecast the optimal control parameters of the converter. By then, the proposed DBO‐FBPINNs method is implemented in the MATLAB platform and evaluated their performance with various present strategy's like deep neural network (DNN), fuzzy neural network (FNN), and recurrent neural network (RNN). When compared to other current technologies, the proposed strategy exhibits a low cost of $1.2.