Distributed Edge Intelligence Empowered Hybrid Charging Scheduling in Internet of Electric Vehicles

As distributed edge intelligence (DEI) advances within the Internet of Electric Vehicles (IoEV), the deployment of mobile charging stations (MCSs) offers a solution to the uneven distribution of fixed charging stations (FCSs), enhancing energy access in remote areas. However, MCS faces the problem of passive scheduling, limiting effective resource utilization and prolonging charging waiting time. This article proposes a hybrid charging model algorithm (HCMA) to address the above challenge, particularly in regions with limited available FCS. We first formulate a multiobjective optimization problem to optimize electric vehicle (EV) charging modes, volumes, and MCS scheduling arrangements. Then, we decompose the original problem into two subproblems. By determining EV charging locations and EV charging mode, the two subproblems are solved, respectively. Finally, simulations based on real-world data demonstrate that HCMA performs better compared to several representative methods, including random working, ARMM, and RBA, in terms of average charging waiting time, extra traveling distance, average unit price of energy, and number of MCS schedules.