Data-Driven Production Scheduling Models in Smart Factories: A Bibliometric and Thematic Analysis

Ogagavwodia Ejovi Okuma¹, Briggs Otekenari Tonye²

¹ Ph.D. Research Scholar, Department of Mechanical Engineering, Niger Delta University, Yenagoa, Bayelsa State, Nigeria.

² Technologist, Department of Mechanical Engineering, Rivers State University, Port Harcourt, Rivers State, Nigeria.    

Abstract

The incorporation of data-driven methods and the technologies of Industry 4.0 has revolutionized the way production scheduling is carried out, from traditional rule-of-thumb methods to intelligent and adaptive systems. This bibliometric and thematic analysis brings together the latest research (2014-2024) on the data-driven approach to production scheduling in smart manufacturing environments. We conduct a systematic review of 37 peer-reviewed journal articles and conference proceedings, and find that there are three major research themes, namely, (1) machine-learning-based scheduling algorithms, such as deep reinforcement learning and evolutionary metaheuristics, (2) cyber-physical systems integration, with real-time monitoring and disturbance management, and (3) digital twin technologies to facilitate closed-loop optimization. Key findings indicate that a dramatic change from a static scheduling paradigm to a more dynamic, adaptive scheduling paradigm is taking place and is benefiting from the use of production data, sensor networks, and computational intelligence. The analysis shows that the hybrid algorithms hybridizing genetic algorithms, particle swarm optimization, and neural networks, are superior in dealing with make span minimization and multi-objective optimization. The new trends focus on the integration of data-driven approaches, digital twins, and edge-cloud architectures in the context of energy efficiency and sustainability in manufacturing. These developments directly contribute to the achievement of multiple Sustainable Development Goals (SDGs), particularly SDG 9 (Industry, Innovation and Infrastructure), SDG 12 (Responsible Consumption and Production), and SDG 13 (Climate Action), by enabling resource-efficient and low-carbon production systems. There are still some gaps in complex operational constraints management, scalability for large-scale systems, model interpretability, and generalization over heterogeneous manufacturing environments. This review offers practical suggestions for practitioners who are using data-driven scheduling systems and suggests further research avenues for Industry 4.0 and Industry 5.0 manufacturing paradigms.

Keywords: Data-driven scheduling, Industry 4.0, Machine learning, Deep reinforcement learning, Digital twin, Smart factories, Cyber-physical systems, Production optimization, SDGs, Metaheuristic algorithms, Bibliometric analysis

References

1. Abdel-Rehim, W. (2023) ‘Implementation of a binary kidney-inspired algorithm based on a parallel method for solving the job shop scheduling problem’, Frontiers in Scientific Research and Technology, 3(2), pp. 1-15. https://doi.org/10.21608/fsrt.2023.234065.1106
2. Abidi, M. H., Alkhalefah, H., Mohammed, M. K., Umer, U. and Qudeiri, J. E. A. (2020) ‘Optimal scheduling of flexible manufacturing system using improved lion-based hybrid machine learning approach’, IEEE Access, 8, pp. 96088-96114. https://doi.org/10.1109/ACCESS.2020.2997663
3. Chen, C., Tiong, R. L. K. and Wu, K. (2023) ‘Identifying the promising production planning and scheduling method for manufacturing in Industry 4.0: A literature review’, Production & Manufacturing Research, 11(1), 2279329. https://doi.org/10.1080/21693277.2023.2279329
4. Converso, G., Gallo, M., Murino, T. and Vespoli, S. (2023) ‘Predicting failure probability in Industry 4.0 production systems: A workload-based prognostic model for maintenance planning’, Applied Sciences, 13(3), 1938. https://doi.org/10.3390/app13031938
5. Dehghanimohammadabadi, M., Keyser, R. and Sayyadi, H. (2021) ‘Simulation-optimization of digital twin’. Online World Conference on Soft Computing in Industrial Applications, pp. 234-245.
6. Deswal, S. and Deswal, P. (2025) ‘The Sustainable Development Goals (SDGs): A comprehensive review of progress, implementation, and the path forward’, International Journal of Technology, Health and Sustainability, 1(2), pp. 133-141. https://ijths.com/wp-content/uploads/IJTHS-010237.pdf
7. Essien, A. and Giannetti, C. (2020) ‘A deep learning model for smart manufacturing using convolutional LSTM neural network autoencoders’, IEEE Transactions on Industrial Informatics, 16(8), pp. 5276-5285.
8. Ghaleb, M., Taghipour, S. and Zolfagharinia, H. (2020) ‘Real-time optimization of maintenance and production scheduling for an Industry 4.0-based manufacturing system’. 2020 Annual Reliability and Maintainability Symposium (RAMS), pp. 1-8. https://doi.org/10.1109/RAMS48030.2020.9153721
9. Huang, X. (2018) ‘Solving the problem of multi-objective flexible job shop based on hybrid genetic algorithm and particle swarm optimization’, Operations Research and Fuzziology, 8(2), pp. 77-89.
10. Huang, J., Wang, A. and Ding, T. (2022) ‘Progressive order insertion dynamic scheduling method considering production capacity’. 2022 3rd International Conference on Computer Science and Management Technology (ICCSMT).
11. Khadivi, M., Charter, T., Yaghoubi, M., et al. (2023) ‘Deep reinforcement learning for machine scheduling: Methodology, the state-of-the-art, and future directions’, arXiv, abs/2310.03195. https://arxiv.org/abs/2310.03195
12. Kong, M., Wang, W., Deveci, M., et al. (2024) ‘A novel carbon reduction engineering method-based deep Q-learning algorithm for energy-efficient scheduling on a single batch-processing machine in semiconductor manufacturing’, International Journal of Production Research, 62(18), pp. 6449-6472. https://doi.org/10.1080/00207543.2023.2252932
13. Li, H., Cao, Y., Lei, Y., et al. (2024) ‘Energy-aware dynamic rescheduling of flexible manufacturing system using edge-cloud collaborative decision-making method’, International Journal of Computer Integrated Manufacturing.
14. Liu, J., Yu, D. and Wang, Y. (2021) ‘Digital twin-driven multi-objective optimization production scheduling with restraint tool resources’. 2021 7^th International Conference on Computer and Communications (ICCC), pp. 1205-1210. https://doi.org/10.1109/iccc54389.2021.9674414
15. Liu, A., Yue, D., Chen, J. L., et al. (2024) ‘Deep learning for intelligent production scheduling optimization’, International Journal of Simulation Modelling, 23(1), pp. 172-183.
16. Luo, D., Guan, Z., He, C., et al. (2021) ‘Data-driven cloud simulation architecture for automated flexible production lines: Application in real smart factories’, International Journal of Production Research, 60(12). https://doi.org/10.1080/00207543.2021.1931977
17. Ma, Y., Li, S., Qiao, F., et al. (2022) ‘A data-driven scheduling knowledge management method for smart shop floor’, International Journal of Computer Integrated Manufacturing, 35(7), pp. 780-793. https://doi.org/10.1080/0951192X.2022.2025622
18. Morsy, N. H., El-Hefnawy, N. A., Ahmed, H., et al. (2023) ‘Digital twin-based job shop scheduling algorithm for poultry feed industrial factory’, IJCI. International Journal of Computers and Information, 10(3), pp. 9-15.
19. Musaeva, K., Shaimerdenov, R. and Azhgaliyeva, M. (2024) ‘Smart factories and their impact on modern manufacturing enterprises: Prospects and challenges in the era of the digital economy’, E3S Web of Conferences, 468, 01009.
20. Negri, E., Fumagalli, L. and Macchi, M. (2020) ‘Field-synchronized digital twin framework for production scheduling with uncertainty’, Journal of Intelligent Manufacturing, 31(4), pp. 959-972.
21. Nouiri, M., Bekrar, A., Trentesaux, D., et al. (2019) ‘Towards energy efficient scheduling of manufacturing systems through collaboration between cyber physical production and energy systems’, Energies, 12(3), 421.
22. Penchev, P., Vitliemov, P. and Georgiev, I. (2023) ‘Optimization model for production scheduling taking into account preventive maintenance in an uncertainty-based production system’, Heliyon, 9(7), e17485. https://doi.org/10.1016/j.heliyon.2023.e17485
23. Kumar, A.K.R. and Dhas, E.R. (2020) ‘Performance analysis of opposition based particle swarm optimization with cauchy distribution in minimizing makespan time in job shop scheduling’, International Journal of Recent Technology and Engineering, 8(6), pp. 360-366. https://www.ijrte.org/wp-content/uploads/papers/v8i6/D8524118419.pdf
24. Qiao, F., Liu, J. and Ma, Y. (2020) ‘Industrial big-data-driven and CPS-based adaptive production scheduling for smart manufacturing’, International Journal of Production Research, 59(23), pp. 7139-7159. https://doi.org/10.1080/00207543.2020.1836417
25. Ren, F. and Liu, H. (2024) ‘Dynamic scheduling for flexible job shop based on MachineRank algorithm and reinforcement learning’, Scientific Reports, 14, 29741. https://doi.org/10.1038/s41598-024-79593-8
26. Rossit, D.A., Tohmé, F. and Frutos, M. (2019) ‘A data-driven scheduling approach to smart manufacturing’, Journal of Industrial Information Integration, 15, pp. 69-79. https://doi.org/10.1016/j.jii.2019.04.003
27. Sang, Y., Tan, J. and Liu, W. (2021) ‘A new many-objective green dynamic scheduling disruption management approach for machining workshop based on green manufacturing’, Journal of Cleaner Production, 297, 126489. https://doi.org/10.1016/j.jclepro.2021.126489
28. Schweitzer, F., Bitsch, G. and Louw, L. (2023) ‘Choosing solution strategies for scheduling automated guided vehicles in production using machine learning’, Applied Sciences, 13(2), 806. https://doi.org/10.3390/app13020806
29. Siatras, V., Bakopoulos, E., Mavrothalassitis, P., et al. (2024) ‘Production scheduling based on a multi-agent system and digital twin: A bicycle industry case’, Information, 15(6), 337. https://doi.org/10.3390/info15060337
30. Sun, D. and Zang, H. (2024) ‘Research on the application of evolutionary algorithms enhanced by deep learning in intelligent manufacturing scheduling’. 2024 5^th International Conference on Machine Learning and Computer Application (ICMLCA), pp. 518-525.
31. Sun, M. and Zhang, T. (2023) ‘A real-time production scheduling method for RFID-enabled semiconductor back-end shopfloor environment in industry 4.0’, IIMBG Journal of Sustainable Business and Innovation, 1(1), pp. 39-57. https://doi.org/10.1108/IJSBI-05-2023-0027
32. Tremblet, D., Thevenin, S. and Dolgui, A. (2023) ‘Makespan estimation in a flexible job-shop scheduling environment using machine learning’, International Journal of Production Research, 62(18). https://doi.org/10.1080/00207543.2023.2245918
33. Ullah, A. and Younas, M. (2024) ‘Development and application of digital twin control in flexible manufacturing systems’, Journal of Manufacturing and Materials Processing, 8(5), 214. https://doi.org/10.3390/jmmp8050214
34. Xiong, X., Xu, W., Liu, J. and Hu, Y. (2022) ‘Collaborative scheduling of production and transportation in the shop-floor based on digital twin’. 2022 IEEE 17^th Conference on Industrial Electronics and Applications (ICIEA), pp. 1821-1828.
35. Yan, J., Zhao, T., Zhang, T., Chu, H., Yang, C. and Zhang, Y. (2024) ‘A dynamic scheduling method combining iterative optimization and deep reinforcement learning to solve sudden disturbance events in a flexible manufacturing process’, Mathematics, 13(1), 4. https://doi.org/10.3390/math13010004
36. Zhang, Y., Zhu, H. and Tang, D. (2019) ‘An improved hybrid particle swarm optimization for multi-objective flexible job-shop scheduling problem’, Kybernetes, 49(12), pp. 2873-2892. https://doi.org/10.1108/K-06-2019-0430
37. Zhang, H., Buchmeister, B., Li, X., et al. (2023) ‘An efficient metaheuristic algorithm for job shop scheduling in a dynamic environment’, Mathematics, 11(10), 2336. https://doi.org/10.3390/math11102336