摘要
随着消费者对生鲜产品需求的增长,冷链物流行业迅速发展,同时面临提升配送效率和减少环境污染的双重挑战。为此提出一个多目标路径规划模型,旨在使运输成本和碳排放最小化,客户满意度最大化。该模型基于一系列关键假设,考虑固定成本、运输成本、货物损坏成本、顾客满意度等因素。提出一种结合人工蜂群算法和Q-learning技术的QABC算法,以提高路径规划的效率和准确性。通过与多目标粒子群优化(MOPSO)算法的对比,QABC算法在节约成本、减少碳排放和提升客户满意度方面展示了显著优势。实验结果表明,所提模型为冷链物流配送提供了新的决策支持工具,推动了行业的绿色可持续发展。
With the growing demand for fresh food products,the cold chain logistics industry has rapidly developed,and it leads to the dual challenges of improving delivery efficiency and reducing environmental pollution.This paper proposes a multi-objective path planning model that aims to minimize transportation costs and carbon emissions while maximizing customer satisfaction.The model is based on a series of key assumptions,considering fixed costs,transportation costs,product damage costs,and customer satisfaction factors.An improved artificial bee colony algorithm combined with Q-learning technology,known as the QABC algorithm,is proposed to enhance the efficiency and accuracy of path planning.Compared with the multi-objective particle swarm optimization(MOPSO)algorithm,the QABC algorithm shows significant advantages in terms of cost savings,reduces carbon emissions,and improves customer satisfaction.The experimental results show that the proposed model provides a new decision support tool for cold chain logistics distribution and promote the green and sustainable development of the industry.
作者
钱宇
QIAN Yu(Department of Economic Management,Shanghai Communications Polytechnic,Shanghai 201314,China)
出处
《微型电脑应用》
2024年第11期120-123,共4页
Microcomputer Applications
基金
2024年上海交通职业技术学院校级科研创新团队项目(2024T04)。
关键词
冷链物流
交通运输
路径规划
多目标优化
人工蜂群算法
cold chain logistic
transportation
path planning
multi-objective optimization
artificial bee colony algorithm
