Real‐Time Logistics Path Planning of IIoT Edge Computing Based on Improved Ant Colony Algorithm

ABSTRACT To address the challenges of real‐time logistics path planning in industrial IoT edge computing scenarios, this paper proposes an enhanced heuristic path planning method based on an improved ant colony algorithm. The proposed method integrates an iterative incentive factor with a Levy flying strategy in a dual‐ant colony mechanism, effectively enhancing global search capability and convergence speed. It further constructs a super‐heuristic framework incorporating dynamic pheromone updates and multi‐objective balancing strategies. Simulation results demonstrate that the proposed algorithm achieves optimal performance across seven benchmark instances, with superior hyper‐volume and inverse generation distance values. In large‐scale networks, the algorithm exhibits fast convergence and low computational latency. The conclusion indicates that this method significantly improves path planning quality, efficiency, and multi‐objective balance, providing effective technical support for intelligent logistics scheduling.