AI-driven equipment scheduling under variable electricity pricing: A case study on dryer cluster efficiency and standby capacity planning

Guoliang Feng; Tianren Gao; Shaojun Bian; Tianming Yu; Guoliang Feng; Tianren Gao; Shaojun Bian; Tianming Yu

doi:10.3934/electreng.2025024

AIMS Electronics and Electrical Engineering

2025, Volume 9, Issue 4: 541-564. doi: 10.3934/electreng.2025024

Previous Article Next Article

Research article Special Issues

AI-driven equipment scheduling under variable electricity pricing: A case study on dryer cluster efficiency and standby capacity planning

1.
School of Automation Engineering, Northeast Electric Power University, Jilin City, People's Republic of China
2.
School of Creative and Digital Industries, Buckinghamshire New University, High Wycombe HP11 2JZ, UK

Academic Editor: Kit Zhang

Received: 01 May 2025 Revised: 03 August 2025 Accepted: 01 September 2025 Published: 05 September 2025

As contemporary industrial enterprises and manufacturing facilities expand in scale, the judicious scheduling of numerous in-house equipment clusters has become a critical factor in enhancing operational efficiency and reducing production costs. Traditional static algorithms merely sustain the baseline functionality of factory apparatuses, thereby failing to unlock the latent synergy among integrated equipment. In response to the advent of artificial intelligence and the maturation of machine learning algorithms, innovative solutions have emerged to address such operational scheduling challenges. This paper presents an algorithm predicated on a deep reinforcement learning-based optimization strategy, integrated with the localized time-of-use electricity tariff framework, to diminish the operating expenses of dryer clusters within the facility. Initially, an objective function aimed at minimizing total operating costs was constructed, alongside the formulation of constraint conditions derived from the operational protocols of the dryer clusters. Subsequently, under a reinforcement learning paradigm, the dryer clusters were modeled by delineating the state and action spaces and formulating a reward function contingent upon the tariff schedule and the degree of completion of gas-drying tasks. Ultimately, a neural network employing a double-DQN architecture was developed and utilized to resolve the scheduling strategy through model training. Empirical results from multiple training iterations with dryer clusters validated that the proposed algorithm can reduce electricity expenditures without necessitating alterations to the existing equipment, while also providing recommendations for the optimal number of additional standby dryers to further reduce operational costs.
- multi-agent systems,
- industrial operations scheduling,
- deep reinforcement learning (DRL)
Citation: Guoliang Feng, Tianren Gao, Shaojun Bian, Tianming Yu. AI-driven equipment scheduling under variable electricity pricing: A case study on dryer cluster efficiency and standby capacity planning[J]. AIMS Electronics and Electrical Engineering, 2025, 9(4): 541-564. doi: 10.3934/electreng.2025024

Related Papers:

Abstract

As contemporary industrial enterprises and manufacturing facilities expand in scale, the judicious scheduling of numerous in-house equipment clusters has become a critical factor in enhancing operational efficiency and reducing production costs. Traditional static algorithms merely sustain the baseline functionality of factory apparatuses, thereby failing to unlock the latent synergy among integrated equipment. In response to the advent of artificial intelligence and the maturation of machine learning algorithms, innovative solutions have emerged to address such operational scheduling challenges. This paper presents an algorithm predicated on a deep reinforcement learning-based optimization strategy, integrated with the localized time-of-use electricity tariff framework, to diminish the operating expenses of dryer clusters within the facility. Initially, an objective function aimed at minimizing total operating costs was constructed, alongside the formulation of constraint conditions derived from the operational protocols of the dryer clusters. Subsequently, under a reinforcement learning paradigm, the dryer clusters were modeled by delineating the state and action spaces and formulating a reward function contingent upon the tariff schedule and the degree of completion of gas-drying tasks. Ultimately, a neural network employing a double-DQN architecture was developed and utilized to resolve the scheduling strategy through model training. Empirical results from multiple training iterations with dryer clusters validated that the proposed algorithm can reduce electricity expenditures without necessitating alterations to the existing equipment, while also providing recommendations for the optimal number of additional standby dryers to further reduce operational costs.

References

[1]	Dauzère-Pérès S, Ding J, Shen L, Tamssaouet K (2024) The flexible job shop scheduling problem: A review. Eur J Oper Res 314: 409–432. https://doi.org/10.1016/j.ejor.2023.05.017 doi: 10.1016/j.ejor.2023.05.017
[2]	Katoch S, Chauhan SS, Kumar V (2021) A review on genetic algorithm: past, present, and future. Multimed Tools Appl 80: 8091–8126. https://doi.org/10.1007/s11042-020-10139-6 doi: 10.1007/s11042-020-10139-6
[3]	Gad AG (2022) Particle swarm optimization algorithm and its applications: a systematic review. Arch Comput Method Eng 29: 2531–2561. https://doi.org/10.1007/s11831-021-09694-4 doi: 10.1007/s11831-021-09694-4
[4]	Nayar N, Gautam S, Singh P, Mehta G (2021) Ant colony optimization: A review of literature and application in feature selection. Inventive Computation and Information Technologies: Proceedings of ICICIT 2020, 285–297. https://doi.org/10.1007/978-981-33-4305-4_22 doi: 10.1007/978-981-33-4305-4_22
[5]	Wu M, Yang D, Liu T (2022) An improved particle swarm algorithm with the elite retain strategy for solving flexible jobshop scheduling problem. In Journal of Physics: Conference Series 2173: 012082. IOP Publishing. https://doi.org/10.1088/1742-6596/2173/1/012082
[6]	Xu X, Wang L (2021) An improved gaming particle swarm algorithm based the rules of flexible job shop scheduling. In 2021 7th International Conference on Systems and Informatics (ICSAI), 1–5. IEEE. https://doi.org/10.1109/ICSAI53574.2021.9664124
[7]	Tutumlu B, Saraç T (2023) A mip model and a hybrid genetic algorithm for flexible job-shop scheduling problem with job-splitting. Comput Oper Res 155: 106222. https://doi.org/10.1016/j.cor.2023.106222 doi: 10.1016/j.cor.2023.106222
[8]	Zhang G, Hu Y, Sun J, Zhang W (2020) An improved genetic algorithm for the flexible job shop scheduling problem with multiple time constraints. Swarm Evol Comput 54: 100664. https://doi.org/10.1016/j.swevo.2020.100664 doi: 10.1016/j.swevo.2020.100664
[9]	Liu Z, Wang J, Zhang C, Chu H, Ding G, Zhang L (2021) A hybrid genetic-particle swarm algorithm based on multilevel neighbourhood structure for flexible job shop scheduling problem. Comput Oper Res 135: 105431. https://doi.org/10.1016/j.cor.2021.105431 doi: 10.1016/j.cor.2021.105431
[10]	Fontes DBMM, Homayouni SM, Gonçalves JF (2023) A hybrid particle swarm optimization and simulated annealing algorithm for the job shop scheduling problem with transport resources. Eur J Oper Res 306: 1140–1157. https://doi.org/10.1016/j.ejor.2022.09.006 doi: 10.1016/j.ejor.2022.09.006
[11]	Amirteimoori A, Mahdavi I, Solimanpur M, Ali SS, Tirkolaee EB (2022) A parallel hybrid pso-ga algorithm for the flexible flow-shop scheduling with transportation. Comput Ind Eng 173: 108672. https://doi.org/10.1016/j.cie.2022.108672 doi: 10.1016/j.cie.2022.108672
[12]	Torres-Tapia W, Montoya-Torres JR, Ruiz-Meza J, Belmokhtar-Berraf S (2022) A matheuristic based on ant colony system for the combined flexible jobshop scheduling and vehicle routing problem. IFAC-PapersOnLine 55: 1613–1618. https://doi.org/10.1016/j.ifacol.2022.09.621 doi: 10.1016/j.ifacol.2022.09.621
[13]	Vivek S, Rakesh K, Mohan BR (2022) Optimized distributed job shop scheduling using balanced job allocation and modified ant colony optimization. In Pattern Recognition and Data Analysis with Applications, 271–281. Springer. https://doi.org/10.1007/978-981-19-1520-8_21
[14]	Fan J, Zhang C, Liu Q, Shen W, Gao L (2022) An improved genetic algorithm for flexible job shop scheduling problem considering reconfigurable machine tools with limited auxiliary modules. J Manuf Syst 62: 650–667. https://doi.org/10.1016/j.jmsy.2022.01.014 doi: 10.1016/j.jmsy.2022.01.014
[15]	Sun K, Zheng D, Song H, Cheng Z, Lang X, Yuan W, Wang J (2023) Hybrid genetic algorithm with variable neighborhood search for flexible job shop scheduling problem in a machining system. Expert Syst Appl 215: 119359. https://doi.org/10.1016/j.eswa.2022.119359 doi: 10.1016/j.eswa.2022.119359
[16]	Vela A, Cruz-Duarte JM, carlos Ortiz-Bayliss J, Amaya I (2021) Tailoring job shop scheduling problem instances through unified particle swarm optimization. IEEE Access 9: 66891–66914. https://doi.org/10.1109/ACCESS.2021.3076426 doi: 10.1109/ACCESS.2021.3076426
[17]	Anuar NI, Fauadi MHFM (2021) A study on multi-objective particle swarm optimization in solving job-shop scheduling problems. International Journal of Computer Information Systems and Industrial Management Applications 13: 11–11.
[18]	Lachtar N, Driss I (2023) Application of ant colony optimization for job shop scheduling in the pharmaceutical industry. Journal Européen des Systèmes Automatisés 56. https://doi.org/10.18280/jesa.560501 doi: 10.18280/jesa.560501
[19]	Matrenin PV (2022) Improvement of ant colony algorithm performance for the job-shop scheduling problem using evolutionary adaptation and software realization heuristics. Algorithms 16: 15. https://doi.org/10.3390/a16010015 doi: 10.3390/a16010015
[20]	Alpaydin E (2021) Machine learning, MIT press.
[21]	Gupta V, Mishra VK, Singhal P, Kumar A (2022) An overview of supervised machine learning algorithm. In 2022 11th International Conference on System Modeling & Advancement in Research Trends (SMART), 87–92. IEEE. https://doi.org/10.1109/SMART55829.2022.10047618
[22]	Naeem S, Ali A, Anam S, Ahmed MM (2023) An unsupervised machine learning algorithms: Comprehensive review. International Journal of Computing and Digital Systems.
[23]	Yang X, Song Z, King I, Xu Z (2022) A survey on deep semi-supervised learning. IEEE T Knowl Data En 35: 8934–8954. https://doi.org/10.1109/TKDE.2022.3220219 doi: 10.1109/TKDE.2022.3220219
[24]	Abel D, Barreto A, Van Roy B, Precup D, van Hasselt HP, Singh S (2023) A definition of continual reinforcement learning. Advances in Neural Information Processing Systems 36: 50377–50407.
[25]	Sharifani K, Amini M (2023) Machine learning and deep learning: A review of methods and applications. World Information Technology and Engineering Journal 10: 3897–3904.
[26]	Li Y (2022) Research and application of deep learning in image recognition. In 2022 IEEE 2nd international conference on power, electronics and computer applications (ICPECA), 994–999. IEEE. https://doi.org/10.1109/ICPECA53709.2022.9718847
[27]	Huaysrijan A, Pongpinigpinyo S (2021) Deep convolution neural network for thai classical music instruments sound recognition. In 2021 25th International Computer Science and Engineering Conference (ICSEC), 283–288. IEEE. https://doi.org/10.1109/ICSEC53205.2021.9684611
[28]	Alsobhani A, ALabboodi HMA, Mahdi H (2021) Speech recognition using convolution deep neural networks. In Journal of Physics: Conference Series 1973: 012166. IOP Publishing. https://doi.org/10.1088/1742-6596/1973/1/012166
[29]	Tercan H, Meisen T (2022) Machine learning and deep learning based predictive quality in manufacturing: a systematic review. J Intell Manuf 33: 1879–1905. https://doi.org/10.1007/s10845-022-01963-8 doi: 10.1007/s10845-022-01963-8
[30]	Zamora-Hernandez MA, Castro-Vargas JA, Azorin-Lopez J, Garcia-Rodriguez J (2021) Deep learning-based visual control assistant for assembly in industry 4.0. Comput Ind 131: 103485. https://doi.org/10.1016/j.compind.2021.103485 doi: 10.1016/j.compind.2021.103485
[31]	Subramanian N, Elharrouss O, Al-Maadeed S, Chowdhury M (2022) A review of deep learning-based detection methods for covid-19. Comput Biol Med 143: 105233. https://doi.org/10.1016/j.compbiomed.2022.105233 doi: 10.1016/j.compbiomed.2022.105233
[32]	Kapoor S, Narayanan A (2023) Leakage and the reproducibility crisis in machine-learning-based science. Patterns 4. https://doi.org/10.1016/j.patter.2023.100804 doi: 10.1016/j.patter.2023.100804
[33]	Ladosz P, Weng L, Kim M, Oh H (2022) Exploration in deep reinforcement learning: A survey. Inform Fusion 85: 1–22. https://doi.org/10.1016/j.inffus.2022.03.003 doi: 10.1016/j.inffus.2022.03.003
[34]	Lv L, Zhang C, Fan J, Shen W (2025) Deep reinforcement learning for job shop scheduling problems: A comprehensive literature review. Knowledge-Based Syst, 113633. https://doi.org/10.1016/j.knosys.2025.113633 doi: 10.1016/j.knosys.2025.113633
[35]	Wang J, Li Y, Zhang Z, Wu Z, Wu L, Jia S, Peng T (2024) Dynamic integrated scheduling of production equipment and automated guided vehicles in a flexible job shop based on deep reinforcement learning. Processes 12: 2423. https://doi.org/10.3390/pr12112423 doi: 10.3390/pr12112423
[36]	Zulfiqar M, ul Abdeen Z, Kamran M (2024) Optimizing electric vehicle charging scheduling using enhanced multi-agent neural networks with dynamic pricing. J Energy Storage 99: 113317. https://doi.org/10.1016/j.est.2024.113317 doi: 10.1016/j.est.2024.113317

Reader Comments

Your name:*

Email:*
© 2025 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)