基于多智能体的生鲜农产品多级库存成本控制模型  

Multi-level inventory cost control model of fresh agricultural products based on multi-agent

作　　者：李姣姣 何利力[1] 郑军红[1] Li Jiaojiao;He Lili;Zheng Junhong(College of Computer Science and Technology,Zhejiang Sci-Tech University,Hangzhou,Zhejiang 310018,China)

机构地区：[1]浙江理工大学计算机科学与技术学院,浙江杭州310018

出　　处：《计算机时代》2023年第9期81-86,共6页Computer Era

基　　金：浙江省重点研发“尖兵”攻关计划项目(2023C01119)。

摘　　要：针对生鲜农产品多级库存成本控制问题,运用多智能强化学习思想,从供应链视角抽象出批发商与零售商智能体,引入三参数Weibull函数描述生鲜农产品的损腐特征,使用深度双Q网络算法构建基于多智能体的生鲜农产品多级库存成本控制模型。该模型基于智能体间相互合作,优化订货并控制多级库存成本。实验结果表明,基于多智能体的库存成本控制模型能够在一定程度上减轻供应链多级库存中的牛鞭效应,有效降低各级库存成本,减少生鲜损腐。the agents of wholesaler and retailer from the perspective of supply chain.The threeparameter Weibull function is introduced to describe the spoilage characteristics of fresh agricultural products,and the Double Deep Q Network algorithm is applied to construct a multi-agent-based multi-level inventory cost control model of fresh agricultural products.The model is based on mutual cooperation among agents to optimize ordering and control multi-level inventory cost.The experimental results show that the proposed model can mitigate the bullwhip effect of multi-level inventory in the supply chain to a certain extent,effectively reduce inventory costs at all levels,and minimize spoilage losses.

关 键 词：生鲜农产品 多智能体 强化学习 多级库存成本控制 供应链 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] F253[自动化与计算机技术—控制科学与工程]