Optimal sizing and smart charging abilities of electric vehicle charging station by considering quality of service using hybrid technique

• Published in: Energy sources. Part A, Recovery, utilization, and environmental effects Recovery, utilization, and environmental effects, 2022-02, Vol.ahead-of-print (ahead-of-print), p.1-17
• Main Authors: Palani, Velmurugan, Gomathi, Subbiah, Aruna, Ponnupandian, Veeramani, Vasan Prabhu, Manathunainathan, Veeramani
• Format: Article
• Language: English
• Subjects: Charging station; electric vehicle; golden eagle optimizer; probability distributions; quality of service; radial basis function neural network
• ISSN: 1556-7036; 1556-7230
• DOI: 10.1080/15567036.2022.2032879

In this article, an optimal size and smart charging abilities of an electric vehicle charging station (EVCS) assuming the quality of service (QoS) using a hybrid technique are proposed. The proposed method is the combination of the Golden Eagle Optimizer (GEO) and the Radial Basis Function Neural Network (RBFNN), and therefore, it is known as the GEO-RBFNN method. The major aim of this work is "to solve the dimensional problem of charging stations (CSs) using an optimization framework that lessens the investment costs of charging station operators, and also, quality of service (QoS) is achieved by its electric vehicle owners." The effect of smart scheduling is analyzed through the loading capacities of the scheduling charging station. The parameters of the incoming charging tasks are approximated using analytical probability distributions and handle the size of the issue depending on the optimization technique. By using the proposed strategy, the electric vehicle begins to charge at regular intervals. The electric vehicle starts charging, but once it starts the charging, it can be no longer interrupted. The scalability of the optimal sizing approach is better with the aid of the proposed GEO-RBFNN strategy. The proposed approach is carried out on the MATLAB site, and its efficiency is analyzed using other existing approaches. In the GEO-RBFNN technique, the simulation time achieves 14.8 seconds at 100 counts of iteration. At 250 counts of iteration, the simulation time achieves 29.2 seconds. At 500 counts of iteration, the simulation time achieves 69.9 seconds. At 1000 counts of iteration, the simulation time achieves 77.1 seconds.