系统仿真学报 ›› 2024, Vol. 36 ›› Issue (11): 2592-2603.doi: 10.16182/j.issn1004731x.joss.23-0912

• 研究论文 • 上一篇    

基于改进DQN算法的自动化码头AGV调度问题研究

梁承姬1, 张石东1, 王钰1, 鲁斌2   

  1. 1.上海海事大学,物流科学与工程研究院,上海 201306
    2.上海市政工程设计研究总院有限公司,上海 200092
  • 收稿日期:2023-07-18 修回日期:2023-10-03 出版日期:2024-11-13 发布日期:2024-11-19
  • 通讯作者: 王钰
  • 第一作者简介:梁承姬(1970-),女,朝鲜族,教授,博士,研究方向为港口物流、地下物流、调度优化等。
  • 基金资助:
    国家自然科学基金(71972128);上海市青年科技英才扬帆计划(21YF1416400);上海市青年科技启明星计划(21QB1404800)

AGV Scheduling Problem at Automated Terminals Based on Improved DQN Algorithm

Liang Chengji1, Zhang Shidong1, Wang Yu1, Lu Bin2   

  1. 1.Institute of Logistics Science and Engineering, Shanghai Maritime University, Shanghai 201306, China
    2.Shanghai Municipal Engineering Design Institute Co. , Ltd. , Shanghai 200092, China
  • Received:2023-07-18 Revised:2023-10-03 Online:2024-11-13 Published:2024-11-19
  • Contact: Wang Yu

摘要:

针对自动化码头AGV(automated guided vehicle)调度问题,提出了一种考虑未来任务的深度Q网络(future tasks considering deep Q-network,F-DQN)算法指导AGV进行实时调度。对系统状态进行了改进,结合实时调度和静态调度的优点在做出实时决策时考虑了静态的未来任务信息,以获得更优的调度方案。以洋山四期自动化码头的真实布局和设备情况为参考,使用仿真软件Plant Simulation进行了一系列仿真实验。实验结果表明:F-DQN算法可以有效解决自动化码头AGV实时调度问题,且F-DQN算法相比于传统DQN算法,能够显著缩短岸桥的等待时间。

关键词: 自动化码头, AGV调度, DQN, MDP, 仿真模型

Abstract:

A future tasks considering deep Q-network (F-DQN) algorithm was proposed to output real-time scheduling results of automated guided vehicles (AGVs) at automated terminals. This algorithm combined the advantages of real-time scheduling and static scheduling, improving the system status by considering static future task information when making real-time decisions, so as to obtain a better scheduling solution. In this study, the actual layout and equipment conditions of the Yangshan phase IV automated terminal were considered, and a series of simulation experiments were conducted using the Plant Simulation software. The experimental results show that the F-DQN algorithm can effectively solve the real-time scheduling problem of AGVs at automated terminals. Furthermore, the F-DQN algorithm significantly reduces the waiting time of quay cranes compared to the traditional DQN algorithm.

Key words: automated terminal, AGV scheduling, DQN, MDP, simulation model

中图分类号: