Deep Reinforcement Learning for Selection of Dispatch Rules for Scheduling of Production Systems
Production scheduling is a critical task in the management of manufacturing systems. It is difficult to derive an optimal schedule due to the problem complexity. Computationally expensive and time-consuming solutions have created major issues for companies trying to respect their customers’ demands....
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/1/232 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549402507837440 |
|---|---|
| author | Kosmas Alexopoulos Panagiotis Mavrothalassitis Emmanouil Bakopoulos Nikolaos Nikolakis Dimitris Mourtzis |
| author_facet | Kosmas Alexopoulos Panagiotis Mavrothalassitis Emmanouil Bakopoulos Nikolaos Nikolakis Dimitris Mourtzis |
| author_sort | Kosmas Alexopoulos |
| collection | DOAJ |
| description | Production scheduling is a critical task in the management of manufacturing systems. It is difficult to derive an optimal schedule due to the problem complexity. Computationally expensive and time-consuming solutions have created major issues for companies trying to respect their customers’ demands. Simple dispatching rules have typically been applied in manufacturing practice and serve as a good scheduling option, especially for small and midsize enterprises (SMEs). However, in recent years, the progress in smart systems enabled by artificial intelligence (AI) and machine learning (ML) solutions has revolutionized the scheduling approach. Under different production circumstances, one dispatch rule may perform better than others, and expert knowledge is required to determine which rule to choose. The objective of this work is to design and implement a framework for the modeling and deployment of a deep reinforcement learning (DRL) agent to support short-term production scheduling. The DRL agent selects a dispatching rule to assign jobs to manufacturing resources. The model is trained, tested and evaluated using a discrete event simulation (DES) model that simulates a pilot case from the bicycle production industry. The DRL agent can learn the best dispatching policy, resulting in schedules with the best possible production makespan. |
| format | Article |
| id | doaj-art-42e3955a190049ccb5565e98b4aeaae4 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-42e3955a190049ccb5565e98b4aeaae42025-01-10T13:14:53ZengMDPI AGApplied Sciences2076-34172024-12-0115123210.3390/app15010232Deep Reinforcement Learning for Selection of Dispatch Rules for Scheduling of Production SystemsKosmas Alexopoulos0Panagiotis Mavrothalassitis1Emmanouil Bakopoulos2Nikolaos Nikolakis3Dimitris Mourtzis4Laboratory for Manufacturing Systems & Automation (LMS), Department of Mechanical Engineering & Aeronautics, University of Patras, Rio, 26504 Patras, GreeceLaboratory for Manufacturing Systems & Automation (LMS), Department of Mechanical Engineering & Aeronautics, University of Patras, Rio, 26504 Patras, GreeceLaboratory for Manufacturing Systems & Automation (LMS), Department of Mechanical Engineering & Aeronautics, University of Patras, Rio, 26504 Patras, GreeceLaboratory for Manufacturing Systems & Automation (LMS), Department of Mechanical Engineering & Aeronautics, University of Patras, Rio, 26504 Patras, GreeceLaboratory for Manufacturing Systems & Automation (LMS), Department of Mechanical Engineering & Aeronautics, University of Patras, Rio, 26504 Patras, GreeceProduction scheduling is a critical task in the management of manufacturing systems. It is difficult to derive an optimal schedule due to the problem complexity. Computationally expensive and time-consuming solutions have created major issues for companies trying to respect their customers’ demands. Simple dispatching rules have typically been applied in manufacturing practice and serve as a good scheduling option, especially for small and midsize enterprises (SMEs). However, in recent years, the progress in smart systems enabled by artificial intelligence (AI) and machine learning (ML) solutions has revolutionized the scheduling approach. Under different production circumstances, one dispatch rule may perform better than others, and expert knowledge is required to determine which rule to choose. The objective of this work is to design and implement a framework for the modeling and deployment of a deep reinforcement learning (DRL) agent to support short-term production scheduling. The DRL agent selects a dispatching rule to assign jobs to manufacturing resources. The model is trained, tested and evaluated using a discrete event simulation (DES) model that simulates a pilot case from the bicycle production industry. The DRL agent can learn the best dispatching policy, resulting in schedules with the best possible production makespan.https://www.mdpi.com/2076-3417/15/1/232artificial intelligencedeep reinforcement learningproduction schedulingdeep Q-learningdiscrete event simulation |
| spellingShingle | Kosmas Alexopoulos Panagiotis Mavrothalassitis Emmanouil Bakopoulos Nikolaos Nikolakis Dimitris Mourtzis Deep Reinforcement Learning for Selection of Dispatch Rules for Scheduling of Production Systems Applied Sciences artificial intelligence deep reinforcement learning production scheduling deep Q-learning discrete event simulation |
| title | Deep Reinforcement Learning for Selection of Dispatch Rules for Scheduling of Production Systems |
| title_full | Deep Reinforcement Learning for Selection of Dispatch Rules for Scheduling of Production Systems |
| title_fullStr | Deep Reinforcement Learning for Selection of Dispatch Rules for Scheduling of Production Systems |
| title_full_unstemmed | Deep Reinforcement Learning for Selection of Dispatch Rules for Scheduling of Production Systems |
| title_short | Deep Reinforcement Learning for Selection of Dispatch Rules for Scheduling of Production Systems |
| title_sort | deep reinforcement learning for selection of dispatch rules for scheduling of production systems |
| topic | artificial intelligence deep reinforcement learning production scheduling deep Q-learning discrete event simulation |
| url | https://www.mdpi.com/2076-3417/15/1/232 |
| work_keys_str_mv | AT kosmasalexopoulos deepreinforcementlearningforselectionofdispatchrulesforschedulingofproductionsystems AT panagiotismavrothalassitis deepreinforcementlearningforselectionofdispatchrulesforschedulingofproductionsystems AT emmanouilbakopoulos deepreinforcementlearningforselectionofdispatchrulesforschedulingofproductionsystems AT nikolaosnikolakis deepreinforcementlearningforselectionofdispatchrulesforschedulingofproductionsystems AT dimitrismourtzis deepreinforcementlearningforselectionofdispatchrulesforschedulingofproductionsystems |