Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.13091/5142
Title: | Cost Analysis of Electric Vehicle Charging Stations and Estimation of Payback Periods with Artificial Neural Networks | Authors: | Olcay K. Cetinkaya N. |
Keywords: | artificial neural networks deep learning. electric vehicle charging stations costs energy consumption Automotive industry Charging (batteries) Cost benefit analysis Deep learning Electric vehicles Energy utilization Investments 'current Charging station Cost analysis Cost calculation Deep learning. Electric vehicle charging Electric vehicle charging station cost Energy-consumption High growth Payback periods Neural networks |
Publisher: | Institute of Electrical and Electronics Engineers Inc. | Abstract: | In this study, the current number of electric vehicles charging stations (EVCS) and the projected increase in their numbers for two different scenarios, as outlined in the literature, have been analyzed, taking into consideration all kinds of charging station costs, to determine their payback periods. Cost calculations and revenue projections have been conducted based on the high growth scenario for charging stations to establish their respective payback periods. Artificial neural networks (ANN) were developed using these data, and payback periods were predicted according to the medium growth scenario. An equation was formulated using the current numbers of electric vehicles and the growth rates specified in the literature to determine the number of electric vehicles in the near future. Moreover, the energy consumption of electric vehicles currently utilized in the automotive industry was identified using the data obtained. All of these data were employed in the training of artificial neural networks. The source of income covering the charging station costs is derived from electricity sales made at the stations. The calculated payback periods based on the number of charging stations per vehicle provided in the study and the forecasts made using artificial neural networks indicate that the charging station payback periods will significantly decrease in the future, warranting careful consideration of the initial costs. © 2023 IEEE. | Description: | FAAC Bulgaria EAD 2023 IEEE International Conference on Communications, Information, Electronic and Energy Systems, CIEES 2023 -- 23 November 2023 through 25 November 2023 -- 196150 |
URI: | https://doi.org/10.1109/CIEES58940.2023.10378772 https://hdl.handle.net/20.500.13091/5142 |
ISBN: | 9798350336917 |
Appears in Collections: | Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collections |
Show full item record
CORE Recommender
Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.