物流行业在市场经济中的比重越来越大，要长期稳定地发展现代物流行业，必须有效解决运输成本问题优化物流系统。车辆调度问题是优化物流系统的关键环节，动态车辆调度问题涉及很多不确定因素，求解更为复杂，近年来已逐渐成为研究的热点。应用目前热度高的云计算、物联网技术构建云物流信息平台，可节约大量物流资源，对物流发展具有重要意义。

本文针对物流系统中的车辆调度问题，在物流云平台基础上设计车辆调度系统，云平台采集并存储物流数据，车辆调度系统通过交互界面实现车辆信息、货物信息、客户信息的展示以及车辆调度功能。车辆调度功能根据采集的物流信息，对构建的调度模型进行求解，得到车辆的最优行车路径。实现过程为：针对物流配送车辆调度问题中的物流信息不确定性，以运输成本最小为优化目标，建立了带有配送时间约束和车辆载重约束的动态车辆调度数学模型；为了求解物流配送车辆的最优行车路径，以遗传算法为基础求解调度模型，设计量子遗传算法提高算法效率，对量子旋转角的大小采取了一种动态选取策略，加速了算法的收敛。

仿真实验对比结果表明，量子遗传算法求得比遗传算法运输成本低的行车路径，在算法效率方面，平均迭代次数减小，收敛速度提高。量子编码增加了种群的多样性提高全局收敛性，量子旋转加速了算法收敛，结果证明算法适用于动态车辆调度问题的求解。设计物流配送车辆调度系统实现物流车辆的调度功能，为实际物流系统提供了方案参考。

The proportion of the logistics industry in the market economy is increasing. To develop the modern logistics industry steadily for a long time, it is necessary to effectively solve the problem of transportation costs and optimize the logistics system. The vehicle scheduling problem is a key link in optimizing the logistics system. The dynamic vehicle scheduling problem involves many uncertain factors and is more complicated to solve, so it has gradually become a research hotspot in recent years. The application of the most popular cloud computing and Internet of Things technology to build a cloud logistics information platform can save a lot of logistics resources and is of great significance to the development of logistics.

Aiming at the vehicle scheduling problem in the logistics system, this paper designs a vehicle scheduling system based on the logistics cloud platform. The cloud platform collects and stores logistics data, the vehicle scheduling system implements the display of vehicle information, cargo information, customer information, and vehicle scheduling functions through an interactive interface. The vehicle scheduling function uses the constructed scheduling model in combination with the collected logistics information, and uses the solving algorithm to obtain the optimal driving path of the vehicle. In view of the logistics information uncertainty in the logistics distribution vehicle scheduling problem, with the minimum transportation cost as the optimization goal, a dynamic vehicle scheduling mathematical model with distribution time constraints and vehicle load constraints is established; In order to solve the optimal driving route of logistics distribution vehicles, the scheduling model is solved based on genetic algorithm. The quantum genetic algorithm is used to improve the efficiency of the algorithm. A dynamic selection strategy is adopted for the size of the quantum rotation angle to accelerate the convergence of the algorithm.

The comparison results of simulation experiments show that the quantum genetic algorithm finds the driving route with lower transportation cost than the genetic algorithm. In terms of algorithm efficiency, the average number of iterations decreases and the convergence speed increases. Quantum coding increases the diversity of the population and improves the global convergence. Quantum rotation accelerates the algorithm convergence. The results prove that the algorithm is suitable for solving dynamic vehicle scheduling problems. Designing a logistics distribution vehicle scheduling system to achieve logistics vehicle scheduling provides a program reference for the actual logistics system.