Integrated design of unmanned aerial mobility network: A data-driven risk-averse approach

In this paper, we propose an integrated design problem of Unmanned Aerial Mobility Network (UAMN), which includes airport location selection (strategic decision) and routes planning (operational decision) to minimize the total cost, while guaranteeing flow constraints, capacity constraints, and electricity constraints. To facility expensive long-term infrastructure planning facing demand uncertainty, we develop a data-driven risk-averse two-stage stochastic optimization model based on the Wasserstein distance. The analysis of the numerical examples proves that our DRO framework provides a relatively robust solution for UAMN. Also, we find that the optimal network configuration is affected by the "pooling effects", which is proved by the fact that the total infrastructure costs can be saved by pooling drone flows into a small number of high-capacity channels/transfer airports. Interestingly, a candidate node without historical demand records can be chosen to locate an airport, in case the demand surges up at this node. We demonstrate the application of our model for a real medical resources transportation problem with our industry partner, collecting donated blood to a blood bank in Hangzhou, China.