In multi-objective dynamic job shop scheduling (MODJSS), achieving production efficiency while reducing energy consumption remains a major challenge in green manufacturing. Genetic programming (GP) has been widely adopted as an effective hyper-heuristic approach for automatically evolving dispatching rules (DRs). Surrogate models have also been widely used in GP frameworks to reduce computational cost. However, existing surrogate-assisted approaches mainly focus on a single DR and cannot capture the collective behavior of ensemble individuals, that is, the interactions and possible conflicts among multiple rules. To address this issue, this paper proposes an improved surrogate-assisted evaluation framework based on ensemble genetic programming (EGP) to capture the collective behavior of ensemble individuals and thereby reduce the computational cost of simulation-based fitness evaluation. Phenotype-based feature representations were developed for both individual and ensemble rules, where ensemble features incorporate behavioral information, diversity, and decision conflict. Surrogate models were trained to predict multiple objectives, and a hierarchical evaluation strategy was employed in which candidate solutions are first evaluated by surrogate predictions and ranked by non-dominated sorting, while only a subset of high-quality solutions is selected for actual simulation. The experimental results showed that (ⅰ) the proposed framework significantly reduces the number of expensive simulation evaluations and the evaluation cost of ensemble individuals, while remaining competitive in solution quality; (ⅱ) surrogate-assisted evaluation improves the computational efficiency of EGP and indicates that the method has application potential in larger and more complex dynamic scheduling scenarios.
Citation: Gang Wang, Adilanmu Sitahong, Yiping Yuan, Peiyin Mo, Areziguli Wubuli, Junyan Ma. Surrogate-assisted automatic design of dispatching rules using ensemble genetic programming for multi-objective dynamic job shop scheduling[J]. Journal of Industrial and Management Optimization, 2026, 22(10): 5466-5506. doi: 10.3934/jimo.2026187
In multi-objective dynamic job shop scheduling (MODJSS), achieving production efficiency while reducing energy consumption remains a major challenge in green manufacturing. Genetic programming (GP) has been widely adopted as an effective hyper-heuristic approach for automatically evolving dispatching rules (DRs). Surrogate models have also been widely used in GP frameworks to reduce computational cost. However, existing surrogate-assisted approaches mainly focus on a single DR and cannot capture the collective behavior of ensemble individuals, that is, the interactions and possible conflicts among multiple rules. To address this issue, this paper proposes an improved surrogate-assisted evaluation framework based on ensemble genetic programming (EGP) to capture the collective behavior of ensemble individuals and thereby reduce the computational cost of simulation-based fitness evaluation. Phenotype-based feature representations were developed for both individual and ensemble rules, where ensemble features incorporate behavioral information, diversity, and decision conflict. Surrogate models were trained to predict multiple objectives, and a hierarchical evaluation strategy was employed in which candidate solutions are first evaluated by surrogate predictions and ranked by non-dominated sorting, while only a subset of high-quality solutions is selected for actual simulation. The experimental results showed that (ⅰ) the proposed framework significantly reduces the number of expensive simulation evaluations and the evaluation cost of ensemble individuals, while remaining competitive in solution quality; (ⅱ) surrogate-assisted evaluation improves the computational efficiency of EGP and indicates that the method has application potential in larger and more complex dynamic scheduling scenarios.
| [1] |
Y. Feng, Q. Wang, Y. Gao, J. Cheng, J. Tan, Energy-efficient job-shop dynamic scheduling system based on the cyber-physical energy-monitoring system, IEEE Access, 6 (2018), 52238–52247. https://doi.org/10.1109/ACCESS.2018.2869048 doi: 10.1109/ACCESS.2018.2869048
|
| [2] |
L. Ge, C. Su, Q. Cheng, H. Zheng, Z. Liu, Y. Guo, et al., Impacts of global manufacturing transfer on energy intensity, consumption, and transition: an industry linkage perspective, Habitat Int., 161 (2025), 103410. https://doi.org/10.1016/j.habitatint.2025.103410 doi: 10.1016/j.habitatint.2025.103410
|
| [3] |
K. Lo, H. Li, M. Wang, Energy conservation in China's energy-intensive enterprises: an empirical study of the ten-thousand enterprises program, Energy Sustain. Dev., 27 (2015), 105–111. https://doi.org/10.1016/j.esd.2015.05.002 doi: 10.1016/j.esd.2015.05.002
|
| [4] |
A. Hasanbeigi, L. Price, A review of energy use and energy efficiency technologies for the textile industry, Renew. Sustain. Energy Rev., 16 (2012), 3648–3665. https://doi.org/10.1016/j.rser.2012.03.029 doi: 10.1016/j.rser.2012.03.029
|
| [5] |
L. He, R. Chiong, W. Li, S. Dhakal, Y. Cao, Y. Zhang, Multiobjective optimization of energy-efficient JOB-shop scheduling with dynamic reference point-based fuzzy relative entropy, IEEE Trans. Ind. Inform., 18 (2022), 600–610. https://doi.org/10.1109/TII.2021.3056425 doi: 10.1109/TII.2021.3056425
|
| [6] |
J. Duan, J. Wang, Energy-efficient scheduling for a flexible job shop with machine breakdowns considering machine idle time arrangement and machine speed level selection, Comput. Ind. Eng., 161 (2021), 107677. https://doi.org/10.1016/j.cie.2021.107677 doi: 10.1016/j.cie.2021.107677
|
| [7] |
R. Li, W. Gong, C. Lu, L. Wang, A learning-based memetic algorithm for energy-efficient flexible job-shop scheduling with type-2 fuzzy processing time, IEEE Trans. Evol. Comput., 27 (2023), 610–620. https://doi.org/10.1109/TEVC.2022.3175832 doi: 10.1109/TEVC.2022.3175832
|
| [8] |
K. Akram, M. U. Bhutta, S. I. Butt, S. I. Husain Jaffery, M. Khan, A. Zeb, et al., A Pareto-optimality based black widow spider algorithm for energy efficient flexible job shop scheduling problem considering new job insertion, Appl. Soft Comput., 164 (2024), 111937. https://doi.org/10.1016/j.asoc.2024.111937 doi: 10.1016/j.asoc.2024.111937
|
| [9] |
G. May, B. Stahl, M. Taisch, V. Prabhu, Multi-objective genetic algorithm for energy-efficient job shop scheduling, Int. J. Prod. Res., 53 (2015), 7071–7089. https://doi.org/10.1080/00207543.2015.1005248 doi: 10.1080/00207543.2015.1005248
|
| [10] |
T. Jiang, C. Zhang, H. Zhu, J. Gu, G. Deng, Energy-efficient scheduling for a job shop using an improved whale optimization algorithm, Mathematics, 6 (2018), 220. https://doi.org/10.3390/math6110220 doi: 10.3390/math6110220
|
| [11] |
M. Xu, Y. Mei, F. Zhang, M. Zhang, Learn to optimise for job shop scheduling: a survey with comparison between genetic programming and reinforcement learning, Artif. Intell. Rev., 58 (2025), 160. https://doi.org/10.1007/s10462-024-11059-9 doi: 10.1007/s10462-024-11059-9
|
| [12] |
Y. Zeiträg, J. R. Figueira, N. Horta, R. Neves, Surrogate-assisted automatic evolving of dispatching rules for multi-objective dynamic job shop scheduling using genetic programming, Expert Syst. Appl., 209 (2022), 118194. https://doi.org/10.1016/j.eswa.2022.118194 doi: 10.1016/j.eswa.2022.118194
|
| [13] |
S. Nguyen, M. Zhang, M. Johnston, K. C. Tan, Learning iterative dispatching rules for job shop scheduling with genetic programming, Int. J. Adv. Manuf. Technol., 67 (2013), 85–100. https://doi.org/10.1007/s00170-013-4756-9 doi: 10.1007/s00170-013-4756-9
|
| [14] |
S. Nguyen, M. Zhang, M. Johnston, K. C. Tan, Genetic programming for evolving due-date assignment models in job shop environments, Evol. Comput., 22 (2014), 105–138. https://doi.org/10.1162/EVCO_a_00105 doi: 10.1162/EVCO_a_00105
|
| [15] |
F. Zhang, Y. Mei, S. Nguyen, M. Zhang, Collaborative multifidelity-based surrogate models for genetic programming in dynamic flexible job shop scheduling, IEEE Trans. Cybern., 52 (2022), 8142–8156. https://doi.org/10.1109/TCYB.2021.3050141 doi: 10.1109/TCYB.2021.3050141
|
| [16] |
T. Soule, J. A. Foster, Effects of code growth and parsimony pressure on populations in genetic programming, Evol. Comput., 6 (1998), 293–309. https://doi.org/10.1162/evco.1998.6.4.293 doi: 10.1162/evco.1998.6.4.293
|
| [17] |
Z. Sheikh Khozani, M. J. S. Safari, A. Danandeh Mehr, W. H. Melini Wan Mohtar, An ensemble genetic programming approach to develop incipient sediment motion models in rectangular channels, J. Hydrol., 584 (2020), 124753. https://doi.org/10.1016/j.jhydrol.2020.124753 doi: 10.1016/j.jhydrol.2020.124753
|
| [18] |
M. Xu, Y. Mei, F. Zhang, M. Zhang, Genetic Programming for Dynamic Flexible Job Shop Scheduling: Evolution With Single Individuals and Ensembles, IEEE Trans. Evol. Comput., 28 (2024), 1761–1775. https://doi.org/10.1109/TEVC.2023.3334626 doi: 10.1109/TEVC.2023.3334626
|
| [19] |
A. L. V. Coelho, E. Fernandes, K. Faceli, Inducing multi-objective clustering ensembles with genetic programming, Neurocomputing, 74 (2010), 494–498. https://doi.org/10.1016/j.neucom.2010.09.014 doi: 10.1016/j.neucom.2010.09.014
|
| [20] |
Y. Jin, Surrogate-assisted evolutionary computation: recent advances and future challenges, Swarm Evol. Comput., 1 (2011), 61–70. https://doi.org/10.1016/j.swevo.2011.05.001 doi: 10.1016/j.swevo.2011.05.001
|
| [21] |
Y. Zhang, S. Bhattacharyya, Genetic programming in classifying large-scale data: an ensemble method, Inf. Sci., 163 (2004), 85–101. https://doi.org/10.1016/j.ins.2003.03.028 doi: 10.1016/j.ins.2003.03.028
|
| [22] |
M. Makhoabenyane, S. Guo, E. Leburu, Towards Sustainable Factories: A Systematic Review of Energy-Conscious Job-Shop Scheduling Models and Algorithms, Sustainability, 17 (2025), 11330. https://doi.org/10.3390/su172411330 doi: 10.3390/su172411330
|
| [23] |
S. Zhang, J. Zhong, H. Yang, Z. Li, G. Liu, A study on PGEP to evolve heuristic rules for FJSSP considering the total cost of energy consumption and weighted tardiness, Comput. Appl. Math., 38 (2019), 185. https://doi.org/10.1007/s40314-019-0934-1 doi: 10.1007/s40314-019-0934-1
|
| [24] |
S. Yang, L. Meng, S. Ullah, B. Zhang, H. Sang, P. Duan, MILP modeling and optimization of multi-objective three-stage flexible job shop scheduling problem with assembly and AGV transportation, IEEE Access, 13 (2025), 25369–25386. https://doi.org/10.1109/ACCESS.2025.3535825 doi: 10.1109/ACCESS.2025.3535825
|
| [25] |
R. Wang, Y. Jing, C. Gu, S. He, J. Chen, End-to-end multitarget flexible job shop scheduling with deep reinforcement learning, IEEE Internet Things J., 12 (2025), 4420–4434. https://doi.org/10.1109/JIOT.2024.3485748 doi: 10.1109/JIOT.2024.3485748
|
| [26] |
Y. Tian, Z. Gao, L. Zhang, Y. Chen, T. Wang, A multi-objective optimization method for flexible job shop scheduling considering cutting-tool degradation with energy-saving measures, Mathematics, 11 (2023), 324. https://doi.org/10.3390/math11020324 doi: 10.3390/math11020324
|
| [27] |
J. M. Kim, K. Han, B. S. Choi, S. H. Song, M. Park, M. H. Choi, Effect of coal-fired power plant flexible operating method on boiler header fatigue life, J. Mech. Sci. Technol., 38 (2024), 5113–5121. https://doi.org/10.1007/s12206-024-0844-z doi: 10.1007/s12206-024-0844-z
|
| [28] |
A. M. Sahlodin, P. I. Barton, Optimal Campaign Continuous Manufacturing, Ind. Eng. Chem. Res., 54 (2015), 11344–11359. https://doi.org/10.1021/acs.iecr.5b01376 doi: 10.1021/acs.iecr.5b01376
|
| [29] |
E. Xu, Y. Li, Y. Liu, J. Du, X. Gao, Energy saving scheduling strategy for job shop under TOU and tiered electricity price, Alex. Eng. J., 61 (2022), 459–467. https://doi.org/10.1016/j.aej.2021.06.008 doi: 10.1016/j.aej.2021.06.008
|
| [30] |
F. Dunke, S. Nickel, Approximate and exact approaches to energy-aware job shop scheduling with dynamic energy tariffs and power purchase agreements, Appl. Energy, 380 (2025), 125065. https://doi.org/10.1016/j.apenergy.2024.125065 doi: 10.1016/j.apenergy.2024.125065
|
| [31] |
H. Qu, X. Tong, M. Cai, Y. Shi, X. Lan, Energy-saving scheduling strategy for variable-speed flexible job-shop problem considering operation-dependent energy consumption, Expert Syst. Appl., 256 (2024), 124952. https://doi.org/10.1016/j.eswa.2024.124952 doi: 10.1016/j.eswa.2024.124952
|
| [32] |
W. Shao, Z. Shao, D. Pi, A multi-neighborhood-based multi-objective memetic algorithm for the energy-efficient distributed flexible flow shop scheduling problem, Neural Comput. Appl., 34 (2022), 22303–22330. https://doi.org/10.1007/s00521-022-07714-3 doi: 10.1007/s00521-022-07714-3
|
| [33] |
J. Duan, F. Liu, Q. Zhang, J. Qin, Y. Zhou, Genetic programming hyper-heuristic-based solution for dynamic energy-efficient scheduling of hybrid flow shop scheduling with machine breakdowns and random job arrivals, Expert Syst. Appl., 254 (2024), 124375. https://doi.org/10.1016/j.eswa.2024.124375 doi: 10.1016/j.eswa.2024.124375
|
| [34] |
Z. Hou, K. Wang, H. Zou, J. Guo, Y. Li, Energy-efficient flexible job-shop scheduling with multi-cavity imbalances and machine breakdowns using improved multi-objective genetic programming, Eng. Optim., 58 (2026), 2248–2275. https://doi.org/10.1080/0305215X.2025.2559840 doi: 10.1080/0305215X.2025.2559840
|
| [35] |
A. Sitahong, Y. Yuan, M. Li, J. Ma, Z. Ba, Y. Lu, Learning dispatching rules via novel genetic programming with feature selection in energy-aware dynamic job-shop scheduling, Sci. Rep., 13 (2023), 8558. https://doi.org/10.1038/s41598-023-34951-w doi: 10.1038/s41598-023-34951-w
|
| [36] |
I. D. Mienye, Y. Sun, A survey of ensemble learning: concepts, algorithms, applications, and prospects, IEEE Access, 10 (2022), 99129–99149. https://doi.org/10.1109/ACCESS.2022.3207287 doi: 10.1109/ACCESS.2022.3207287
|
| [37] |
A. Mohammed, R. Kora, A comprehensive review on ensemble deep learning: opportunities and challenges, J. King Saud Univ. Comput. Inf. Sci., 35 (2023), 757–774. https://doi.org/10.1016/j.jksuci.2023.01.014 doi: 10.1016/j.jksuci.2023.01.014
|
| [38] |
M. Ɖurasević, D. Jakobović, Creating dispatching rules by simple ensemble combination, J. Heuristics, 25 (2019), 959–1013. https://doi.org/10.1007/s10732-019-09416-x doi: 10.1007/s10732-019-09416-x
|
| [39] |
E. Hart, K. Sim, A hyper-heuristic ensemble method for static job-shop scheduling, Evol. Comput., 24 (2016), 609–635. https://doi.org/10.1162/EVCO_a_00183 doi: 10.1162/EVCO_a_00183
|
| [40] |
J. Park, Y. Mei, S. Nguyen, G. Chen, M. Zhang, An investigation of ensemble combination schemes for genetic programming based hyper-heuristic approaches to dynamic job shop scheduling, Appl. Soft Comput., 63 (2018), 72–86. https://doi.org/10.1016/j.asoc.2017.11.020 doi: 10.1016/j.asoc.2017.11.020
|
| [41] |
J. Park, S. Nguyen, M. Zhang, M. Johnston, Evolving ensembles of dispatching rules using genetic programming for job shop scheduling, Genet. Program., (2015), 92–104. https://doi.org/10.1007/978-3-319-16501-1_8 doi: 10.1007/978-3-319-16501-1_8
|
| [42] |
Z. Huang, Y. Mei, F. Zhang, M. Zhang, Multitask linear genetic programming with shared individuals and its application to dynamic job shop scheduling, IEEE Trans. Evol. Comput., 28 (2024), 1546–1560. https://doi.org/10.1109/TEVC.2023.3263871 doi: 10.1109/TEVC.2023.3263871
|
| [43] |
Y. Mei, S. Nguyen, B. Xue, M. Zhang, An efficient feature selection algorithm for evolving job shop scheduling rules with genetic programming, IEEE Trans. Emerg. Top. Comput. Intell., 1 (2017), 339–353. https://doi.org/10.1109/TETCI.2017.2743758 doi: 10.1109/TETCI.2017.2743758
|
| [44] |
Y. Zhou, J. Yang, Z. Huang, Automatic design of scheduling policies for dynamic flexible job shop scheduling via surrogate-assisted cooperative co-evolution genetic programming, Int. J. Prod. Res., 58 (2020), 2561–2580. https://doi.org/10.1080/00207543.2019.1620362 doi: 10.1080/00207543.2019.1620362
|
| [45] |
S. Nguyen, M. Zhang, K. C. Tan, Surrogate-assisted genetic programming with simplified models for automated design of dispatching rules, IEEE Trans. Cybern., 47 (2017), 2951–2965. https://doi.org/10.1109/TCYB.2016.2562674 doi: 10.1109/TCYB.2016.2562674
|
| [46] |
T. Hildebrandt, J. Branke, On using surrogates with genetic programming, Evol. Comput., 23 (2015), 343–367. https://doi.org/10.1162/EVCO_a_00133 doi: 10.1162/EVCO_a_00133
|
| [47] |
S. Nguyen, M. Zhang, D. Alahakoon, K. C. Tan, People-centric evolutionary system for dynamic production scheduling, IEEE Trans. Cybern., 51 (2021), 1403–1416. https://doi.org/10.1109/TCYB.2019.2936001 doi: 10.1109/TCYB.2019.2936001
|
| [48] |
F. Zhang, Y. Mei, S. Nguyen, K. C. Tan, M. Zhang, Instance-rotation-based surrogate in genetic programming with brood recombination for dynamic job-shop scheduling, IEEE Trans. Evol. Comput., 27 (2023), 1192–1206. https://doi.org/10.1109/TEVC.2022.3180693 doi: 10.1109/TEVC.2022.3180693
|
| [49] |
T. G. Dietterich, Ensemble Methods in Machine Learning, Mult. Classif. Syst., (2000), 1–15. https://doi.org/10.1007/3-540-45014-9_1 doi: 10.1007/3-540-45014-9_1
|
| [50] |
Z. Wang, J. Zhang, S. Yang, An improved particle swarm optimization algorithm for dynamic job shop scheduling problems with random job arrivals, Swarm Evol. Comput., 51 (2019), 100594. https://doi.org/10.1016/j.swevo.2019.100594 doi: 10.1016/j.swevo.2019.100594
|
| [51] |
G. Varoquaux, L. Buitinck, G. Louppe, O. Grisel, F. Pedregosa, A. Mueller, Scikit-learn: machine learning without learning the machinery, GetMobile Mob. Comput. Commun., 19 (2015), 29–33. https://doi.org/10.1145/2786984.2786995 doi: 10.1145/2786984.2786995
|
Figures(16) / Tables(16)
Gang Wang, Adilanmu Sitahong, Yiping Yuan, Peiyin Mo, Areziguli Wubuli, Junyan Ma. Surrogate-assisted automatic design of dispatching rules using ensemble genetic programming for multi-objective dynamic job shop scheduling[J]. Journal of Industrial and Management Optimization, 2026, 22(10): 5466-5506. doi: 10.3934/jimo.2026187
DownLoad: