Electric vehicles and drones promise to transform transportation systems and supply chains. However, long recharge times and battery degradation inhibit adoption. To overcome these barriers, swap stations enable quick battery exchange. We introduce a stochastic scheduling, allocation, and inventory replenishment problem which determines the charging, discharging, and replacement decisions at a swap station over time. The decisions are complex because recharging is necessary for short-term operation but causes degradation and the need for future replacement. We model the problem as a Markov Decision Process, solve it using backward induction, and show that the problem suffers from the curses of dimensionality. Hence, we propose two approximate methods, a heuristic benchmark policy and a reinforcement learning method, which provide high-quality solutions. Using a designed experiment, we deduce effective operational insights.

电动汽车和无人机有望改变运输系统和供应链。但是，较长的充电时间和电池退化会阻碍采用。为了克服这些障碍，交换站可以快速更换电池。我们介绍了随机调度，分配和库存补给问题，该问题确定了随时间推移交换站的充电，放电和更换决定。决策很复杂，因为短期操作需要充电，但会导致性能下降以及将来需要更换。我们将问题建模为马尔可夫决策过程，使用后向归纳法对其进行求解，并证明该问题遭受了维数的诅咒。因此，我们提出了两种近似方法，一种启发式基准策略和一种强化学习方法，提供高质量的解决方案。通过设计实验，我们可以得出有效的运营见解。