Charging Scheduling Strategies of Cooperated Car-hailing Operating Business for Electric Taxis

With the popularity of electric vehicles (EVs), the replacement on the traditional fuel taxis to the electric taxis (e-taxis) has been gradually emerged in a creasing number of cities. Compared with the ordinary EVs, e-taxis require frequent charging due to their long daily mileage and high total power consumption. Additionally, the disorderly charging behaviors of EVs have caused congestion in charging stations (CSs) and have seriously affected the normal business of e-taxi drivers. This paper proposes a management architecture that combines the charging network and the car-hailing operating network of e-taxis. With the goal of minimizing the charging cost of e-taxis, a set of scheduling strategy which combines car-hailing operating business and charging plan is designed based on reinforcement learning (RL). The result shows that this strategy can effectively lower the charging cost of e-taxis by reducing the charging queue time in the CSs.