Intelligent Logistics Resource Scheduling Based on Hybrid Parameter Ant Colony Algorithm and Reinforcement Learning

Abstract

To solve the problem of low efficiency in logistics resource scheduling, research proposes an intelligent scheduling technology. A logistics resource task scheduling model is constructed by analyzing logistics tasks. To solve the scheduling model, a mixed-parameter improved ant colony algorithm is introduced to solve the problem. The ant colony traversal is used to search for the objective function, and the information is used to modify the parameter adjustment algorithm. In addition, the study introduced reinforcement learning to optimize the pheromone problem of the ant colony algorithm and improved the performance of the algorithm. In the experimental analysis, task execution time, execution efficiency and task cost were introduced as indicators. In the task operation time comparison, the improved hybrid parameter ant colony model could converge in the shortest time. The shortest packing operation time was 16052 s, which was shorter than other models. In the cost comparison of logistics resource scheduling task, the cost of the improved hybrid parameter ant colony optimization model in the purchasing task was 29865 yuan, which was lower than other models. In the comparison of the resource execution rate of the order taking task, when the number of resources was 5000, the resource execution rate of the improved hybrid parameter ant colony model was 95.65%, which was significantly better than the other models. In addition, comparing the cost reduction rate of different models in scheduling arrangement, the cost reduction rate of genetic algorithm and particle swarm algorithm was 3.54% and 6.45% respectively. While the improved hybrid parameter ant colony model was 9.54%, the research model had significantly better cost control. This indicates that the research model has better application in logistics scheduling. The research content will provide technical reference for the transformation of information technology in logistics industry and optimization of logistics resource scheduling.