Simultaneous allocation of EV charging stations and renewable energy sources: An Elite RERNN‐m2MPA approach

Abstract

This article proposes a hybrid optimization technique for optimal location and sizing of electric vehicle fast charging stations (EVFCSs) and renewable energy sources (RESs). The proposed hybrid optimization technique is the consolidation of recalling-enhanced recurrent neural network (RERNN) and Marine Predators Algorithm (MPA), hence it is called RERNN-m2MPA technique. Here, an enhanced MPA (m2MPA) is proposed. The major objective of this article is to energy loss reduction, voltage deviation of the power system network and minimization of the land cost with maximum weightage to serve maximum EV with minimum installation cost. The lessening of voltage deviation is considered as objective function to maintain a stable voltage profile in every nodes. The land cost is diminished with weightage maximization to serve maximal electric vehicle with minimal installation cost of electric vehicle charging station (EVCS). In this proposal, optimal location with capacity of fast charging stations and RESs are determined concurrently, while determined the deviation paths and uncertainties of RESs. To this intention, RERNN is proposed to cover the charging demand for EVs on the transportation network. Moreover, an m2MPA is proposed to optimal allocation of RESs and fast charging stations with respect to the distribution and transportation networks. Likewise, the proposed technique minimizes the adverse effects of fast charging demand on the grid, particularly during peak periods reducing the need for larger capabilities of energy storage units to absorb fast charging fluctuations and reduces the need for separate FCS installation. By then, the proposed technique is carried out in MATLAB/Simulink platform, its performance is compared with various existing techniques.