Charging infrastructure facilitate a large-scale Introduction of electric vehicle in urban areas using hybrid technique: A RBFNN-SPOA approach

Abstract

A hybrid technique is proposed for the effects of different roll-out techniques for charging the infrastructure that enables large-scale introduction of electric vehicles (EVs). The proposed hybrid technique is the combined execution of both Radial Basis Function Neural Network (RBFNN) and Student psychology optimization algorithm (SPOA), together called as RBFNN-SPOA strategy. The proposed method contains 3 kinds of agents operate in the environment from which charging stations is located. The communication among these agents are simulated in 3 ways. They are (1) charging process from which the EV driver cooperates with available charging stations and other electric vehicle drivers, (2) the process of purchasing a vehicle of non-electric vehicle car owners from which they take current charging infrastructure utilization into account, (3) the installment process of new charging stations through charging point operator (CPO) is based on placement tactic depends on charging station (CS) utilization. Firstly, a larger dataset on real charging patterns are utilized to design the charging behaviour of agents by RBFNN. Secondly, the proposed approach contains significantly more communication among electric vehicle drivers compared to existing approaches and also more precisely specifies the difficult system of on-street electric vehicle charging at an urban context. Thirdly, the relation among charging infrastructure and electric vehicle adoption based on experimental choice, while the existing methods provides assumptions by using SPOA. Finally, the proposed approach is implemented in MATLAB or Simulink platform and its performance is compared with existing approaches.