Date of Graduation


Document Type


Degree Name

Doctor of Philosophy in Engineering (PhD)

Degree Level



Industrial Engineering


Sarah Nurre Pinkley

Committee Member

Kelly Sullivan

Second Committee Member

Mohammad Marufuzzaman

Third Committee Member

Shengfan Zhang


Approximate Dynamic Programming, Battery Swap Stations, Electric Vehicles and Drones, Markov Decision Processes, Optimization, Reinforcement Learning


In this dissertation, motivated by electric vehicle (EV) and drone application growth, we propose novel optimization problems and solution techniques for managing the operations at EV and drone battery swap stations. In Chapter 2, we introduce a novel class of stochastic scheduling allocation and inventory replenishment problems (SAIRP), which determines the recharging, discharging, and replacement decisions at a swap station over time to maximize the expected total profit. We use Markov Decision Process (MDP) to model SAIRPs facing uncertain demands, varying costs, and battery degradation. Considering battery degradation is crucial as it relaxes the assumption that charging/discharging batteries do not deteriorate their quality (capacity). Besides, it ensures customers receive high-quality batteries as we prevent recharging/discharging and swapping when the average capacity of batteries is lower than a predefined threshold. Our MDP has high complexity and dimensions regarding the state space, action space, and transition probabilities; therefore, we can not provide the optimal decision rules (exact solutions) for SAIRPs of increasing size. Thus, we propose high-quality approximate solutions, heuristic and reinforcement learning (RL) methods, for stochastic SAIRPs that provide near-optimal policies for the stations.

In Chapter 3, we explore the structure and theoretical findings related to the optimal solution of SAIRP. Notably, we prove the monotonicity properties to develop fast and intelligent algorithms to provide approximate solutions and overcome the curses of dimensionality. We show the existence of monotone optimal decision rules when there is an upper bound on the number of batteries replaced in each period. We demonstrate the monotone structure for the MDP value function when considering the first, second, and both dimensions of the state. We utilize data analytics and regression techniques to provide an intelligent initialization for our monotone approximate dynamic programming (ADP) algorithm. Finally, we provide insights from solving realistic-sized SAIRPs.

In Chapter 4, we consider the problem of optimizing the distribution operations of a hub using drones to deliver medical supplies to different geographic regions. Drones are an innovative method with many benefits including low-contact delivery thereby reducing the spread of pandemic and vaccine-preventable diseases. While we focus on medical supply delivery for this work, it is applicable to drone delivery for many other applications, including food, postal items, and e-commerce delivery. In this chapter, our goal is to address drone delivery challenges by optimizing the distribution operations at a drone hub that dispatch drones to different geographic locations generating stochastic demands for medical supplies. By considering different geographic locations, we consider different classes of demand that require different flight ranges, which is directly related to the amount of charge held in a drone battery. We classify the stochastic demands based on their distance from the drone hub, use a Markov decision process to model the problem, and perform computational tests using realistic data representing a prominent drone delivery company. We solve the problem using a reinforcement learning method and show its high performance compared with the exact solution found using dynamic programming. Finally, we analyze the results and provide insights for managing the drone hub operations.