Dynamic hub capacity planning in hyperconnected relay transportation networks under uncertainty

Abstract

In this article, we consider a truck carrier aiming to set contracts with multiple hub providers to reserve hub capacities in a hyperconnected relay transportation network. This network enables long-haul freight shipments to be transported by multiple short-haul drivers commuting between fixed-base hubs, promoting a driver-friendly approach. We introduce the dynamic stochastic hub capacity-routing problem (DS-HCRP), which is a two-stage stochastic program to determine hub contracted capacities for each planning period that minimizes hub and subsequent transportation costs given demand and travel time uncertainty. To overcome the difficulty in solving this NP-hard problem, we propose a combinatorial Benders decomposition (CBD) algorithm based on a tailored implementation of branch-and-Benders-cut. In addition, we design a heuristic initial cut pool generation method to restrict the search space within the CBD algorithm. Experimental results from a case study in the automotive delivery sector demonstrate that our algorithm outperforms other commonly used approaches in terms of solution quality and convergence speed. Furthermore, the results show that the proposed model offers potential savings of up to 22.96% in hub costs and 8.47% in total costs compared to its static deterministic counterpart by effectively mitigating the impact of demand fluctuations and network disruptions, thus highlighting the advantages of dynamic and stochastic integration in capacity planning.