Optimization of Underground Logistics System Node Location Based on Adaptive and Dynamic Grey Wolf Optimization Algorithm

Abstract

With the increasing scarcity of urban land resources and the continuous growth of logistics demand, the Underground Logistics System (ULS) has emerged as a promising solution for alleviating urban traffic congestion and enhancing logistics efficiency. This study proposes an optimization method for underground logistics node location based on the Adaptive and Dynamic Grey Wolf Optimization (ADGWO) algorithm, aiming to address the challenges of multi-tiered node optimization in complex urban environments. A four-tier underground logistics node network is constructed in this study, consisting of logistics demand nodes, distribution nodes, transfer nodes, and urban logistics center nodes, forming a tree-like topology. In terms of optimization, the ADGWO algorithm incorporates a dynamically nonlinear convergence factor adjustment and an adaptive inertia weight, which enhances global search capability and mitigates premature convergence. Experimental results demonstrate that compared to traditional Grey Wolf Optimization (GWO), Particle Swarm Optimization (PSO), and Genetic Algorithm (GA), ADGWO exhibits significant improvements in convergence speed and optimization accuracy. The findings of this study provide theoretical support for the future planning and optimization of underground logistics systems