Application of LightGBM Algorithm in Production Scheduling Optimization on Non-Identical Parallel Machines
Received: 20 August 2024 | Revised: 15 September 2024 | Accepted: 19 September 2024 | Online: 11 October 2024
Corresponding author: Khalid Ait Ben Hamou
Abstract
Production scheduling plays a decisive role in supply chain management, directly influencing the operational efficiency and competitiveness of companies. This study explores the effectiveness of the LightGBM algorithm for production scheduling on non-identical parallel machines, comparing it to algorithms such as logistic regression, KNN, decision tree, and XGBoost. LightGBM was chosen for its speed of execution and its ability to handle large amounts of data. The results show that LightGBM outperforms the other models in terms of RMSE, MAE, explained variance score, and R² score for regression tasks, as well as in classification accuracy for certain features. Its superiority is attributed to its ability to efficiently handle data complexity while reducing computational complexity through its leaf tree growth technique. This study highlights LightGBM's potential for improving the efficiency of supply chain management systems and the challenges associated with computational scalability for large datasets. The results suggest that LightGBM is a robust and effective solution to optimize production scheduling, paving the way for future research in this field.
Keywords:
production scheduling, parallel machines, machine learning, LightGBM, optimizationDownloads
References
K. C. Ying, P. Pourhejazy, and X. Y. Huang, "Revisiting the development trajectory of parallel machine scheduling," Computers & Operations Research, vol. 168, Aug. 2024, Art. no. 106709.
M. Alanazi, R. S. Aldahr, and M. Ilyas, "Human Activity Recognition through Smartphone Inertial Sensors with ML Approach," Engineering, Technology & Applied Science Research, vol. 14, no. 1, pp. 12780–12787, Feb. 2024.
L. Li, Z. Liu, J. Shen, F. Wang, W. Qi, and S. Jeon, "A LightGBM-based strategy to predict tunnel rockmass class from TBM construction data for building control," Advanced Engineering Informatics, vol. 58, Oct. 2023, Art. no. 102130.
M. Rohaninejad, R. Tavakkoli-Moghaddam, B. Vahedi-Nouri, Z. Hanzálek, and S. Shirazian, "A hybrid learning-based meta-heuristic algorithm for scheduling of an additive manufacturing system consisting of parallel SLM machines," International Journal of Production Research, vol. 60, no. 20, pp. 6205–6225, Oct. 2022.
H. Togo, K. Asanuma, T. Nishi, and Z. Liu, "Machine Learning and Inverse Optimization for Estimation of Weighting Factors in Multi-Objective Production Scheduling Problems," Applied Sciences, vol. 12, no. 19, Jan. 2022, Art. no. 9472.
F. Li, S. Lang, B. Hong, and T. Reggelin, "A two-stage RNN-based deep reinforcement learning approach for solving the parallel machine scheduling problem with due dates and family setups," Journal of Intelligent Manufacturing, vol. 35, no. 3, pp. 1107–1140, Mar. 2024.
A. Uzunoglu, C. Gahm, S. Wahl, and A. Tuma, "Learning-augmented heuristics for scheduling parallel serial-batch processing machines," Computers & Operations Research, vol. 151, Mar. 2023, Art. no. 106122.
A. Uzunoglu, C. Gahm, and A. Tuma, "A machine learning enhanced multi-start heuristic to efficiently solve a serial-batch scheduling problem," Annals of Operations Research, vol. 338, no. 1, pp. 407–428, Jul. 2024.
C. L. Liu, C. J. Tseng, T. H. Huang, and J. W. Wang, "Dynamic Parallel Machine Scheduling With Deep Q-Network," IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 53, no. 11, pp. 6792–6804, Aug. 2023.
H. Yamashiro and H. Nonaka, "Estimation of processing time using machine learning and real factory data for optimization of parallel machine scheduling problem," Operations Research Perspectives, vol. 8, Jan. 2021, Art. no. 100196.
K. A. B. Hamou, Z. Jarir, and S. Elfirdoussi, "Design of a Machine Learning-based Decision Support System for Product Scheduling on Non Identical Parallel Machines," Engineering, Technology & Applied Science Research, vol. 14, no. 5, pp. 16317–16325, Oct. 2024.
Y. Li et al., "A K-means-Teaching Learning based optimization algorithm for parallel machine scheduling problem," Applied Soft Computing, vol. 161, Aug. 2024, Art. no. 111746.
G. Ke et al., "LightGBM: a highly efficient gradient boosting decision tree," in Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA, Sep. 2017, pp. 3149–3157.
D. Wang, L. Li, and D. Zhao, "Corporate finance risk prediction based on LightGBM," Information Sciences, vol. 602, pp. 259–268, Jul. 2022.
T. O. Hodson, "Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not," Geoscientific Model Development, vol. 15, no. 14, pp. 5481–5487, Jul. 2022.
D. Chicco, M. J. Warrens, and G. Jurman, "The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation," PeerJ Computer Science, vol. 7, Jul. 2021, Art. no. e623.
Ž. Ð. Vujovic, "Classification Model Evaluation Metrics," International Journal of Advanced Computer Science and Applications, vol. 12, no. 6, 2021.
S. Nuanmeesri, "A Hybrid Deep Learning and Optimized Machine Learning Approach for Rose Leaf Disease Classification," Engineering, Technology & Applied Science Research, vol. 11, no. 5, pp. 7678–7683, Oct. 2021.
Downloads
How to Cite
License
Copyright (c) 2024 Khalid Ait Ben Hamou, Zahi Jarir, Selwa Elfirdoussi
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
