A Study on the Location Optimization of Smart Parcel Lockers Based on Bilevel Programming

To address the challenges of high costs and insufficient coverage in smart parcel locker site selection, this study develops a bilevel programming model. The upper level aims to maximize enterprise profit, while the lower level focuses on optimizing customer satisfaction. A case study is conducted, in which K-means clustering is employed to identify candidate locations. The effectiveness of the proposed bilevel model is validated, and a simulated annealing-enhanced genetic algorithm is introduced to solve the site selection problem efficiently. The results demonstrate that this integrated approach significantly improves both economic performance and service quality in parcel locker deployment.