The week's pick
Random Articles
Reseach Article
Adaptive SKU Allocation in Mattress Manufacturing via Multi-Agent Reinforcement Learning under Dynamic Loading Conditions
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 187 - Number 110 |
| Year of Publication: 2026 |
| Authors: Duc Hoang Nguyen |
10.5120/ijcafd4b2cbcdd0d
|
Duc Hoang Nguyen . Adaptive SKU Allocation in Mattress Manufacturing via Multi-Agent Reinforcement Learning under Dynamic Loading Conditions. International Journal of Computer Applications. 187, 110 ( May 2026), 26-33. DOI=10.5120/ijcafd4b2cbcdd0d
Abstract
Dynamic SKU allocation at loading stations plays a critical role in throughput, line balance, and Overall Equipment Effectiveness (OEE) in mattress assembly lines. Conventional static dispatching rules and equilibrium-based approaches perform adequately under stable conditions but deteriorate when key parameters, such as SKU loading time, vary. This study proposes a decentralized multi-agent reinforcement learning (MARL) approach for adaptive SKU allocation, formulated as a cooperative Dec-POMDP. Each station acts as an agent, making bidding decisions based on local observations, including buffer levels, in-transit items, and station OEE. A softmax-based allocation mechanism and a combined local–global reward are used to encourage both high throughput and balanced operations. A co-simulation framework integrates a Tecnomatix Plant Simulation model with a Python-based MARL system trained using MAPPO. Under nominal conditions, the MARL policy achieves performance comparable to a baseline equilibrium rule in terms of mean OEE and throughput, while maintaining low variability across stations. However, under moderate (30s→45s) and severe (30s→60s) loading-time disruptions, static methods show clear degradation, including reduced OEE, higher variance, and pronounced line imbalance. In contrast, the MARL approach maintains higher OEE and throughput, while improving system balance. These results highlight the effectiveness of decentralized MARL in improving robustness of cyber-physical production systems under dynamic disturbances.
References
- Ng Corrales, L.D., Lambán, M.P., Hernandez Korner, M.E., & Royo, J. (2020). Overall Equipment Effectiveness: Systematic Literature Review and Overview of Different Approaches. Applied Sciences.
- Sathler, K. P. B., Salonitis, K., & Kolios, A. (2023). Overall equipment effectiveness as a metric for assessing operational losses in wind farms: a critical review of literature. International Journal of Sustainable Energy, 42(1), 374–396. https://doi.org/10.1080/14786451.2023.2189490
- Nguyen, D. H. (2022). Simulation and evaluation of the mattress manufacturing process design model. International Journal of Computer Applications, 184(36), 16-21. https://doi.org/10.5120/ijca2022922454
- Zubair, M., Maqsood, S., Habib, T., Usman Jan, Q. M., Nadir, U., Waseem, M., & Yaseen, Q. M. (2021). Manufacturing productivity analysis by applying overall equipment effectiveness metric in a pharmaceutical industry. Cogent Engineering, 8(1). https://doi.org/10.1080/23311916.2021.1953681
- Zhang, L., Hu, Y., Tang, Q., Li, J., & Li, Z. (2021). Data-Driven Dispatching Rules Mining and Real-Time Decision-Making Methodology in Intelligent Manufacturing Shop Floor with Uncertainty. Sensors (Basel, Switzerland), 21(14), 4836. https://doi.org/10.3390/s21144836
- Stöckermann, P., Feudel, S., Immordino, A., Hayen, N., Altenmüller, T., Gebser, M., … Higgins, F. (2025). Reinforcement learning based dispatching solutions in semiconductor manufacturing: a literature review on validation and deployment. Production & Manufacturing Research, 13(1). https://doi.org/10.1080/21693277.2025.2582472
- Suvarna, M., Yap, K. S., Yang, W., Li, J., Ng, Y. T., & Wang, X. (2021). Cyber–Physical Production Systems for Data-Driven, Decentralized, and Secure Manufacturing—A Perspective. Engineering, 7(9), 1212-1223. https://doi.org/10.1016/j.eng.2021.04.021
- Bahrpeyma, F., & Reichelt, D. (2022). A review of the applications of multi-agent reinforcement learning in smart factories. Frontiers in Robotics and AI, 9, 1027340. https://doi.org/10.3389/frobt.2022.1027340
- Di, Y., Deng, L., & Zhang, L. (2024). A collaborative-learning multi-agent reinforcement learning method for distributed hybrid flow shop scheduling problem. Swarm and Evolutionary Computation, 91, 101764. https://doi.org/10.1016/j.swevo.2024.101764
- Xu, W., Gu, J., Zhang, W., Gen, M., & Ohwada, H. (2025). Multi-agent reinforcement learning for flexible shop scheduling problem: A survey. Frontiers in Industrial Engineering, 3, 1611512. https://doi.org/10.3389/fieng.2025.1611512
- Zhang, C., Juraschek, M., & Herrmann, C. (2024). Deep reinforcement learning-based dynamic scheduling for resilient and sustainable manufacturing: A systematic review. Journal of Manufacturing Systems, 77, 962-989. https://doi.org/10.1016/j.jmsy.2024.10.026
- Li, C., Chang, Q., & Fan, H. (2024). Multi-agent reinforcement learning for integrated manufacturing system-process control. Journal of Manufacturing Systems, 76, 585-598. https://doi.org/10.1016/j.jmsy.2024.08.021
- Al-zqebah, R., Guertler, M. & Clemon, L. (2025). Powder bed fusion factory productivity increases using discrete event simulation and genetic algorithm. Prod. Eng. Res. Devel. 19, 29–45. https://doi.org/10.1007/s11740-024-01286-y
- Marques, N., Figueira, G., & Guimarães, L. (2025). Dynamic dispatching rule selection for the job shop scheduling problem. Computers & Industrial Engineering, 210, 111471. https://doi.org/10.1016/j.cie.2025.111471
- Lee, D., Kang, Y. S., & Noh, S. D. (2026). Digital twin-driven deep reinforcement learning for real-time optimisation in dynamic AGV systems. International Journal of Production Research, 64(1), 106–124. https://doi.org/10.1080/00207543.2025.2543491.
- Liu, R., Piplani, R., & Toro, C. (2023). A deep multi-agent reinforcement learning approach to solve dynamic job shop scheduling problem. Computers & Operations Research, 159, 106294. https://doi.org/10.1016/j.cor.2023.106294
Index Terms
Keywords