Prototyping Design and Optimization of Smart Electric Vehicles/Stations System using ANN

Authors

  • Mohamed Elkasrawy Renewable Energy Programme, Faculty of Engineering, and FabLab in the Center for Emerging Learning Technology (CELT), The British University in Egypt (BUE), 11387, Cairo, Egypt
  • Ahmed Hassan Electrical Engineering Department, Faculty of Engineering, and FabLab in the Center for Emerging Learning Technology (CELT), The British University in Egypt (BUE), 11387, Cairo, Egypt
  • Sameh Abdellatif Electrical Engineering Department, Faculty of Engineering, and FabLab in the Center for Emerging Learning Technology (CELT), The British University in Egypt (BUE), 11387, Cairo, Egypt
  • Gamal Ebrahim Computer Engineering Department, Faculty of Engineering, Ain Shams University, Cairo, Egypt
  • Hani Ghali Electrical Engineering Department, Faculty of Engineering, and FabLab in the Center for Emerging Learning Technology (CELT), The British University in Egypt (BUE), 11387, Cairo, Egypt

DOI:

https://doi.org/10.32985/ijeces.13.6.8

Keywords:

Real-time algorithms, Physical realization, Electric vehicles stations, Queuing delay optimization, Artificial neural network (ANN) algorithm

Abstract

This paper demonstrates an experimental attempt to prototype electric vehicle charging station’s (EVCS) decision-making unit, using artificial neural network (ANN) algorithm. The algorithm acts to minimize the queuing delay in the station, with respect to the vehicle state of charge (SOC), and the expected arrival time. A simplified circuit model has been used to prototype the proposed algorithm, to minimize the overall queuing delay. Herein, the worst-case scenario is considered by having number of electric vehicles arriving to the station at the same time greater than the charging points available in the station side. Accordingly, the optimization technique was applied to reduce the mean charging time of the vehicles and minimize queuing delay. Results showed that this model can help in reducing the queuing delay by around 20% of the mean charging time of the station, while referring to a bare model without ANN algorithm as a reference.

Downloads

Published

2022-09-01

Issue

Vol. 13 No. 6 (2022)

Section

Original Scientific Papers