Efficient distribution network based on photovoltaic fed electric vehicle charging station using WSO-RBFNN approach

An integral and prevalent aspect of modern life is the electric vehicle (EV).EV charging networks struggle with power losses and high energy costs, particularly as demand rises leading to inefficiencies and potential system overloads. A hybrid WSO-RBFNN approach is proposed for the distribution network's photovoltaic (PV) fed electric vehicle charging stations. The performance of the proposed hybrid strategy is a combination of war strategy optimization (WSO) and Radial basis function neural network (RBFNN). It is hence referred to as the WSO-RBFNN technique. WSO optimizes the distribution network by minimizing power loss, improving voltage sensitivity, and reducing costs. Meanwhile, the RBFNN predicts the load demand. This innovative technique WSO-RBFNN identifies the nearest charging spots that minimize power loss and RBFNN optimizes power flow predicts charging demands and addresses both environmental and electrical grid stability concerns. The proposed technique is implemented in MATLAB. MATLAB is powerful computational software widely used in different fields like numerical computation, visualization, and algorithm development. MATLAB provides powerful tools for data visualization and plotting. The results are compared to various existing Heap-based optimizer (HBO), Wild horse optimizer (WHO), and Salp Swarm Algorithm (SSA) techniques. The proposed approach contributes only 0.59 % of a power loss it is less and the cost of energy is 0.18$ which is lesser and the voltage deviation is 6.6 pu which is less than the existing techniques.