Dynamic Routing and Scheduling of Mobile Charging Stations for Electric Vehicles Using Deep Reinforcement Learning
Document Type
Conference Proceeding
Publication Date
1-1-2024
Abstract
This paper presents an innovative solution for charging electric vehicles (EVs) on the go. Unlike traditional charging stations, our proposed system schedules and routes mobile charging stations (MCSs) to provide charging services to EVs at their preferred location and time. However, the dynamic and evolving nature of EV charging requests requires a real-time approach to optimize the scheduling and routing of MCSs. To address this challenge, we propose a distributed model-free deep reinforcement learning approach for the dynamic routing of MCSs. The MCSs learn the optimal policy by interacting with the environment in a distributed manner without explicitly needing to model the system. Numerical results demonstrate that our approach provides optimal charging solutions to meet the growing demand for EV charging.
Identifier
85207470960 (Scopus)
ISBN
[9798350381832]
Publication Title
IEEE Power and Energy Society General Meeting
External Full Text Location
https://doi.org/10.1109/PESGM51994.2024.10688695
e-ISSN
19449933
ISSN
19449925
Recommended Citation
Qureshi, Ubaid; Ghosh, Arnob; and Panigrahi, B. K., "Dynamic Routing and Scheduling of Mobile Charging Stations for Electric Vehicles Using Deep Reinforcement Learning" (2024). Faculty Publications. 838.
https://digitalcommons.njit.edu/fac_pubs/838