Intelligent Collaborative Resource Allocation for Mechanical Manufacturing Edge Networks: A Deep Reinforcement Learning Approach
DOI:
https://doi.org/10.4108/eetsis.13306Keywords:
Multi-agent deep reinforcement learning, edge intelligence, resource allocation, intelligent manufacturingAbstract
Industry 4.0 is transforming mechanical manufacturing systems into edge-enabled, networked, and intelligent environments, where concurrent task execution, heterogeneous resource coordination, and dependency-aware scheduling have become critical requirements. In such scenarios, resource allocation must jointly consider computational demand, storage demand, business priority, deadline urgency, and inter-task dependencies, while enabling coordinated decisions among distributed edge agents. However, existing single-agent reinforcement learning methods have limited capability to model complex dependency relationships and heterogeneous resource collaboration under concurrent workloads, whereas conventional multi-agent systems often rely on coarse-grained task modeling and simplified cooperation mechanisms. To address these limitations, this paper proposes MIRA, a multi-agent deep reinforcement learning-based method for resource allocation in mechanical manufacturing edge networks. MIRA first decomposes tasks into fine-grained dependent subtasks, constructs a deadline-aware multi-metric priority function, and introduces a dynamic weight adjustment mechanism to balance computational demand, storage demand, normalized business priority, and deadline urgency. It then employs an adjacency matrix to characterize topology-aware agent interactions, enabling coordinated decision-making between computing agents and storage agents. Furthermore, MIRA incorporates an event-triggered state-exchange mechanism that updates subtask priorities and agent policies under changing workload, deadline, resource, and topology conditions. Experimental results on a PCB-derived simulated scheduling workload show that MIRA outperforms the selected baselines across multiple scheduling metrics.
References
[1] Ahmed N, Girija S, Baker T, Al Aghbari Z. MAESTRO: A Multilayer Architecture Based on Fog Computing and SDN for Real-Time Emergency Routing in Urban Settings. IEEE Internet Things J. 2026;13(4):6370–6386.
[2] Zhou H, Jiang K, Liu X, Li X, Leung VCM. Deep Rein-forcement Learning for Energy-Efficient Computation Offloading in Mobile-Edge Computing. IEEE Internet Things J. 2022;9(2):1517–1530.
[3] Sadia H, Kamal Hassan A, Haq Abbas Z, Abbas G, Baker T, Saeed N. Maximizing Energy Efficiency in IRS-Assisted Phase Cooperative PS-SWIPT-Based Self-Sustainable IoT Network. IEEE Open J Commun Soc. 2025;6:4311–4327.
[4] Zaman SKu, Jehangiri AI, Maqsood T, et al. LiMPO: lightweight mobility prediction and offloading frame-work using machine learning for mobile edge comput-ing. Cluster Comput. 2023;26:99–117.
[5] Wu H, Geng J, Bai X, Jin S. Deep reinforcement learning-based online task offloading in mobile edge computing networks. Inf Sci. 2024;654:119849.
[6] Baker T, Al Aghbari Z, Khedr AM, Ahmed N, Girija S. EDITORS: Energy-aware Dynamic Task Offloading using Deep Reinforcement Transfer Learning in SDN-enabled Edge Nodes. Internet of Things. 2024;25:101118.
[7] Bhandari S, Vu TX, Chatzinotas S. LEO-Based Edge Computing Service Platform for Challenging Geograph-ical Terrain. IEEE Open J Commun Soc. 2025;6:9991–10009.
[8] Zhu D, Li T, Tian H, Yang Y, Liu Y, Liu H, Geng L, Sun J. Speed-Aware and Customized Task Offloading and Resource Allocation in Mobile Edge Computing. IEEE Commun Lett. 2021;25(8):2683–2687.
[9] Shamim N, Asim M, Baker T, Pervez Z, Awad AI, Zomaya AY. Integrating system calls and position-specific scoring for enhanced anomaly detection in Internet of Things environments. Comput Secur. 2025;158:104613.
[10] Gebrekidan TZ, Stein S, Norman TJ. Combinatorial Client-Master Multiagent Deep Reinforcement Learning for Task Offloading in Mobile Edge Computing. In: AAMAS ’24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems. 2024. p. 2273–2275.
[11] Al Aghbari Z, Khedr AM, Ahmed N, Girija S, Baker T. RedTops: real-time energy-aware dynamic task offloading via federated mountain gazelle optimisation in SDN-enhanced edge computing. Neural Comput Applic. 2025;37(19):13795–13833.
[12] Huang Z, Li D, Cai J, Lu H. Collective reinforce-ment learning based resource allocation for digital twin service in 6G networks. J Netw Comput Appl. 2023;217:103697.
[13] Zhou H, Elsayed M, Erol-Kantarci M. RAN Resource Slicing in 5G Using Multi-Agent Correlated Q-Learning. In: 2021 IEEE 32nd Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC). 2021. p. 1179–1184.
[14] Akyıldız HA, Gemici F, Hökelek I, Çırpan HA. Hierarchical Reinforcement Learning Based Resource Allocation for RAN Slicing. IEEE Access. 2024;12:75818–75831.
[15] Lei W, Zhao H, Liu X, Zhang Z, Xia XH, Evans S. Optimal Remanufacturing Service Resource Allocation for Gen-eralized Growth of Retired Mechanical Products: Maxi-mizing Matching Efficiency. IEEE Access. 2021;9:89655–89674.
[16] Yu H, Zhang G, Ran Y, Li M, Jiang D, Chen Y. A Reliability Allocation Method for Mechanical Product Based on Meta-Action. IEEE Trans Reliab. 2020;69(1):373–381.
[17] Wu SB, Baker T, Wang YJ, Tan YA, Li YZ, Ren MX. FRISC: Mitigating Privacy Leakage in Federated Learning through Frequency-domain Feature Screening. Concurrency Comput Pract Exper. 2026;38(6):e70640.
[18] Peng H, Shen X. Deep Reinforcement Learning Based Resource Management for Multi-Access Edge Comput-ing in Vehicular Networks. IEEE Trans Netw Sci Eng. 2020;7(4):2416–2428.
[19] Kong X, Duan G, Hou M, Shen G, Wang H, Yan X, Col-lotta M. Deep Reinforcement Learning-Based Energy-Efficient Edge Computing for Internet of Vehicles. IEEE Trans Ind Inform. 2022;18(9):6308–6316.
[20] Hussien A, Maksoud A, Al-Dahhan A, Abdeen A, Baker T. Machine learning model for predicting long-term energy consumption in buildings. Discover Internet of Things. 2025;5(1):18.
[21] Deng X, Zhang J, Zhang H, Jiang P. Deep-Reinforcement-Learning-Based Resource Allocation for Cloud Gam-ing via Edge Computing. IEEE Internet Things J. 2023;10(6):5364–5377.
[22] Lin P, Song Q, Wang D, Yu FR, Guo L, Leung VCM. Resource Management for Pervasive-Edge-Computing-Assisted Wireless VR Streaming in Industrial Internet of Things. IEEE Trans Ind Inform. 2021;17(11):7607–7617.
[23] Zhang S, Gu H, Chi K, Huang L, Yu K, Mumtaz S. DRL-Based Partial Offloading for Maximizing Sum Computation Rate of Wireless Powered Mobile Edge Computing Network. IEEE Trans Wireless Commun. 2022;21(12):10934–10948.
[24] Li X, Qin Y, Huo J, Huangfu W. Heuristically Assisted Multiagent RL-Based Framework for Computation Offloading and Resource Allocation of Mobile-Edge Computing. IEEE Internet Things J. 2023;10(17):15477–15487.
[25] Hazarika B, Singh K, Biswas S, Li CP. DRL-Based Resource Allocation for Computation Offloading in IoV Networks. IEEE Trans Ind Inform. 2022;18(11):8027–8038.
[26] Xiao K, Shi W, Gao Z, Yao C, Qiu X. DAER: A Resource Preallocation Algorithm of Edge Computing Server by Using Blockchain in Intelligent Driving. IEEE Internet Things J. 2020;7(10):9291–9292.
[27] Chai F, Zhang Q, Yao H, Xin X, Gao R, Guizani M. Joint Multi-Task Offloading and Resource Allocation for Mobile Edge Computing Systems in Satellite IoT. IEEE Trans Veh Technol. 2023;72(6):7783–7795.
[28] Waqar N, Hassan SA, Mahmood A, Dev K, Do DT, Gid-lund M. Computation Offloading and Resource Alloca-tion in MEC-Enabled Integrated Aerial-Terrestrial Vehic-ular Networks: A Reinforcement Learning Approach. IEEE Trans Intell Transp Syst. 2022;23(11):21478–21491.
[29] Xu J, Ai B, Chen L, Cui Y, Wang N. Deep Rein-forcement Learning for Computation and Communica-tion Resource Allocation in Multiaccess MEC Assisted Railway IoT Networks. IEEE Trans Intell Transp Syst. 2022;23(12):23797–23808.
[30] Yu J, Alhilal AY, Zhou T, Hui P, Tsang DHK. Attention-Based QoE-Aware Digital Twin Empowered Edge Computing for Immersive Virtual Reality. IEEE Trans Wireless Commun. 2024;23(9):11276–11290.
[31] Yu C, Velu A, Vinitsky E, Gao J, Wang Y, Bayen AM, Wu Y. The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games. In: Advances in Neural Information Processing Systems (NeurIPS). 2022. Vol. 35.
[32] Rashid T, Samvelyan M, Schroeder C, Farquhar G, Foerster J, Whiteson S. QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning. In: Proceedings of the 35th International Conference on Machine Learning (ICML). 2018. p. 4295–4304.
[33] Sunehag P, Lever G, Gruslys A, Czarnecki WM, Zambaldi V, Jaderberg M, Lanctot M, Sonnerat N, Leibo JZ, Tuyls K, Graepel T. Value-Decomposition Networks for Cooperative Multi-Agent Learning Based on Team Reward. In: Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems (AAMAS). 2018. p. 2085–2087.
[34] Liu C, Wang H, Zhao M, Liu J, Zhao X, Yuan P. Dependency-aware online task offloading based on deep reinforcement learning for IoV. J Cloud Comput. 2024;13:136.
[35] Chen Y, Luo X, Liang P, Han J, Xu Z. Priority-based DAG task offloading and secondary resource allocation in IoT edge computing environments. Computing. 2024;106:3229–3254.
[36] China Telecom, Raisecom Technology. The PCB-AoI Public Dataset [Internet]. 2022 [cited 2026 Jul 6]. Available from: https://www.kaggle.com/datasets/kubeedgeianvs/pcb-aoi
[37] Aloui A, Hadj-Hamou K. A heuristic approach for a scheduling problem in additive manufacturing under technological constraints. Comput Ind Eng. 2021;154:107115.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Kaile Xiao, Xiajing Wang, Jing Wang
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
