Abstract

In this paper, a new method for identifying the best charging hours, proportional to providing discounts on energy sales prices, is suggested by using reinforcement learning techniques at fast charging stations for electric vehicles. Given the ever-increasing power of electric vehicles as an important consumer of smart grids for electric power distribution, charging of these vehicles in smart grids is very important. The waiting time in the queue as well as the owners' profits are two important parameters in design fast charging stations. In previous studies, when the vehicles arrival rate increases to busy hours, the waiting time in the vehicles queue is higher than the driver's satisfaction, causing a number of vehicles to leave the station and reduced the rental profits, but can be Providing discounts on energy sales prices during stand-by hours encourages drivers to charge at these hours. In the proposed method, three important parameters, waiting time in the queue, the amount of energy costs paid by the owners of the vehicles, as well as the profits of the owners of the station, were examined to determine the best hours of charge for vehicles, in proportion to the discounts provided by the owners of the stations. The simulation results show that with the proposed method, the owners of the stations increased by 4 %, and also the drivers would save from 10% to 40% at their own expense, according to the selected ones for charging, and less time in queue stand.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.