에이전트 기반 시뮬레이션을 통한 디스패칭 시스템의 강화학습 모델
A Reinforcement Learning Model for Dispatching System through Agent-based Simulation
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
In the manufacturing industry, dispatching systems play a crucial role in enhancing production efficiency and optimizing pro- duction volume. However, in dynamic production environments, conventional static dispatching methods struggle to adapt to various environmental conditions and constraints, leading to problems such as reduced production volume, delays, and resource wastage. Therefore, there is a need for dynamic dispatching methods that can quickly adapt to changes in the environment. In this study, we aim to develop an agent-based model that considers dynamic situations through interaction between agents. Additionally, we intend to utilize the Q-learning algorithm, which possesses the characteristics of temporal difference (TD) learning, to automati- cally update and adapt to dynamic situations. This means that Q-learning can effectively consider dynamic environments by sensi- tively responding to changes in the state space and selecting optimal dispatching rules accordingly. The state space includes information such as inventory and work-in-process levels, order fulfilment status, and machine status, which are used to select the optimal dispatching rules. Furthermore, we aim to minimize total tardiness and the number of setup changes using reinforcement learning. Finally, we will develop a dynamic dispatching system using Q-learning and compare its performance with conventional static dispatching methods.
Abstract
In the manufacturing industry, dispatching systems play a crucial role in enhancing production efficiency and optimizing pro- duction volume. However, in dynamic production environments, conventional static dispatching methods struggle to adapt to various environmental conditions and constraints, leading to problems such as reduced production volume, delays, and resource wastage. Therefore, there is a need for dynamic dispatching methods that can quickly adapt to changes in the environment. In this study, we aim to develop an agent-based model that considers dynamic situations through interaction between agents. Additionally, we intend to utilize the Q-learning algorithm, which possesses the characteristics of temporal difference (TD) learning, to automati- cally update and adapt to dynamic situations. This means that Q-learning can effectively consider dynamic environments by sensi- tively responding to changes in the state space and selecting optimal dispatching rules accordingly. The state space includes information such as inventory and work-in-process levels, order fulfilment status, and machine status, which are used to select the optimal dispatching rules. Furthermore, we aim to minimize total tardiness and the number of setup changes using reinforcement learning. Finally, we will develop a dynamic dispatching system using Q-learning and compare its performance with conventional static dispatching methods.
참고문헌 (14)
- Cho, Y. I., "Development of the Reinforcement Learning-based Adaptive Scheduling Algorithm for Panel Block Shop", Korean Journal of Computational Design and Engineering, 26(2), pp.81~92 (2021)
- Cho, Y. I., "Development of Quay Scheduling Algorithm Based on Reinforcement Learning", Korean Journal of Computational Design and Engineering, 27(2), pp.98~114 (2022)
- Choi, H. W., "Analysis of Workforce Scheduling Using Adjusted Man-machine Chart and Simulation", Journal of Korean Society of Industrial and Systems Engineering, 47(1), pp.20~27 (2024)
- "Hanbat National University"[URL]
- Kang, B. W., "A Dynamic OHT Routing Algorithm in Automated Material Handling Systems", Journal of Korean Society of Industrial and Systems Engineering, 45(3), pp.40~48 (2022)
- Kim, S. J., "Real-time scheduling using CNN on a parallel machine with setup cost", Proceedings of the 2018 Korean Institute of Industrial Engineers Fall Conference, pp.1385~1401 (2018)
- Kim, H. H., "Reinforcement Learning-based Dynamic Weapon Assignment to Multi-Caliber Long-Range Artillery Attacks", Journal of Korean Society of Industrial and Systems Engineering, 45(4), pp.42~52 (2022)
- Nam, S. H., "Reinforcement Learning for Minimizing Tardiness and Set-Up Change in Parallel Machine Scheduling Problems for Profile Shops in Shipyard", Journal of the Society of Naval Architects of Korea, 60(3), pp.202~211 (2023)
- Priore, P., "Dynamic scheduling of manufacturing systems using machine learning: An updated review", Artificial Intelligence for Engineering Design, Analysis and Manufacturing, 28(1), pp.83~97 (2014)
- "The AnyLogic Company"[URL]
- Waschneck, B., "Deep reinforcement learning for semiconductor production scheduling", Proceedings of the 29th Annual SEMI Advanced Semiconductor Manufacturing Conference (ASMC), pp.301~306 (2018)
- Yoo, W. S., "Real-Time Scheduling Scheme based on Reinforcement Learning Considering Minimizing Setup Cost", The Journal of Society for e-Business Studies, 25(2), pp.15~27 (2020)
- Zhang, Z., "Flow Shop Scheduling with Reinforcement Learning", Asia-Pacific Journal of Operational Research (2013)