Reinforcement Learning-Driven Resource Allocation in Edge Computing Networks
Keywords:
Edge computing; reinforcement learning; resource allocation; distributed systems; intelligent orchestration; network optimization; autonomous infrastructure; latency management; multi-agent systems; sustainable computingAbstract
Edge computing has emerged as a foundational architectural paradigm for supporting latency-sensitive, data-intensive, and geographically distributed digital services. As intelligent applications increasingly rely on heterogeneous networks of sensors, mobile devices, micro-data centers, and distributed cloud infrastructures, the problem of resource allocation has become significantly more complex. Conventional optimization strategies often struggle to accommodate the dynamic, stochastic, and decentralized operational characteristics of edge environments. Reinforcement learning has therefore attracted considerable attention as a mechanism for enabling adaptive and autonomous resource management across distributed computational ecosystems. This paper presents a comprehensive system-level examination of reinforcement learning-driven resource allocation in edge computing networks. The study investigates the architectural foundations of edge computing, the limitations of traditional allocation frameworks, and the operational rationale for adopting reinforcement learning approaches in large-scale distributed infrastructures. Particular attention is devoted to orchestration challenges involving latency management, workload scheduling, energy efficiency, service migration, fairness, scalability, and security resilience. The paper further analyzes the interplay between reinforcement learning agents and heterogeneous edge infrastructures under real-world deployment constraints, including unstable connectivity, incomplete observability, and governance fragmentation. Comparative discussion is provided across industrial domains such as healthcare, transportation, manufacturing, and smart urban systems to illustrate the broader socio-technical implications of intelligent edge resource management. The study also evaluates sustainability considerations, regulatory implications, and emerging directions involving federated learning, multi-agent coordination, explainable artificial intelligence, and autonomous infrastructure governance. The paper concludes that reinforcement learning-driven orchestration frameworks represent a transformative but still evolving approach to edge resource management whose effectiveness depends not only on algorithmic sophistication but also on infrastructural interoperability, institutional trust, and operational accountability.
References
Abbas, N., Zhang, Y., Taherkordi, A., & Skeie, T. (2018). Mobile edge computing: A survey. IEEE Internet of Things Journal, 5(1), 450–465.
Agarwal, Y., Hodges, S., Chandra, R., Scott, J., Bahl, P., & Gupta, R. (2010). Somniloquy: Augmenting network interfaces to reduce PC energy usage. USENIX Symposium on Networked Systems Design and Implementation, 365–380.
Akrout, M., Feriani, A., & Akrout, S. (2020). Reinforcement learning-based resource management in edge computing: A review. Future Internet, 12(3), 46–61.
Al-Fuqaha, A., Guizani, M., Mohammadi, M., Aledhari, M., & Ayyash, M. (2015). Internet of Things: A survey on enabling technologies, protocols, and applications. IEEE Communications Surveys & Tutorials, 17(4), 2347–2376.
Baktir, S., Ozgovde, A., & Ersoy, C. (2017). How can edge computing benefit from software-defined networking: A survey, use cases, and future directions. IEEE Communications Surveys & Tutorials, 19(4), 2359–2391.
Chen, X., Jiao, L., Li, W., & Fu, X. (2016). Efficient multi-user computation offloading for mobile-edge cloud computing. IEEE/ACM Transactions on Networking, 24(5), 2795–2808.
Chiang, M., & Zhang, T. (2016). Fog and IoT: An overview of research opportunities. IEEE Internet of Things Journal, 3(6), 854–864.
Deng, R., Lu, R., Lai, C., Luan, T. H., & Liang, H. (2016). Optimal workload allocation in fog-cloud computing toward balanced delay and power consumption. IEEE Internet of Things Journal, 3(6), 1171–1181.
Dinh, T. Q., Tang, J., La, Q. D., & Quek, T. Q. (2017). Offloading in mobile edge computing: Task allocation and computational frequency scaling. IEEE Transactions on Communications, 65(8), 3571–3584.
Duan, Y., Liu, J., Ren, W., Li, T., & Fortino, G. (2021). Artificial intelligence for edge service optimization in Internet of Vehicles: A survey. Tsinghua Science and Technology, 26(2), 270–287.
He, Y., Yu, F. R., Zhao, N., Yin, H., Yao, H., & Han, Z. (2020). Software-defined networks with mobile edge computing and caching for smart cities. IEEE Communications Magazine, 55(12), 48–53.
Kang, J., Xiong, Z., Niyato, D., Ye, D., Kim, D. I., & Zhao, J. (2019). Toward secure blockchain-enabled Internet of Vehicles: Optimizing consensus management using reputation and contract theory. IEEE Transactions on Vehicular Technology, 68(3), 2906–2920.
Li, Y., & Wang, M. (2021). Deep reinforcement learning for resource allocation in network slicing: A survey. Sensors, 21(18), 5845–5868.
Liu, J., Mao, Y., Zhang, J., & Letaief, K. B. (2016). Delay-optimal computation task scheduling for mobile-edge computing systems. IEEE International Symposium on Information Theory, 1451–1455.
Mach, P., & Becvar, Z. (2017). Mobile edge computing: A survey on architecture and computation offloading. IEEE Communications Surveys & Tutorials, 19(3), 1628–1656.
Mao, Y., You, C., Zhang, J., Huang, K., & Letaief, K. B. (2017). A survey on mobile edge computing: The communication perspective. IEEE Communications Surveys & Tutorials, 19(4), 2322–2358.
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A., Veness, J., Bellemare, M., Graves, A., Riedmiller, M., Fidjeland, A., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., & Hassabis, D. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529–533.
Pan, J., & McElhannon, J. (2018). Future edge cloud and edge computing for Internet of Things applications. IEEE Internet of Things Journal, 5(1), 439–449.
Park, J., Samarakoon, S., Bennis, M., & Debbah, M. (2019). Wireless network intelligence at the edge. Proceedings of the IEEE, 107(11), 2204–2239.
Rahmani, A. M., Liljeberg, P., Jantsch, A., Tenhunen, H., & Nikander, P. (2018). Fog computing in the Internet of Things: Intelligence at the edge. Springer.
Saha, P. K., Kumar, N., & Mukherjee, M. (2019). A review on edge computing: Issues and challenges. Journal of Parallel and Distributed Computing, 128, 78–85.
Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2016). Edge computing: Vision and challenges. IEEE Internet of Things Journal, 3(5), 637–646.
Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction (2nd ed.). MIT Press.
Taleb, T., Samdanis, K., Mada, B., Flinck, H., Dutta, S., & Sabella, D. (2017). On multi-access edge computing: A survey of the emerging 5G network edge architecture and orchestration. IEEE Communications Surveys & Tutorials, 19(3), 1657–1681.
Wang, S., Zhang, X., Zhang, Y., Wang, L., Yang, J., & Wang, W. (2017). A survey on mobile edge networks: Convergence of computing, caching and communications. IEEE Access, 5, 6757–6779.
Xu, X., Li, H., Xu, W., Liu, Z., Yao, L., & Dai, F. (2018). Artificial intelligence for edge service optimization in Internet of Vehicles: A survey. Tsinghua Science and Technology, 26(2), 270–287.
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019). Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology, 10(2), 1–19.
Yu, W., Liang, F., He, X., Hatcher, W., Lu, C., Lin, J., & Yang, X. (2018). A survey on the edge computing for the Internet of Things. IEEE Access, 6, 6900–6919.
Zhang, K., Mao, Y., Leng, S., Maharjan, S., & Zhang, Y. (2017). Optimal delay constrained offloading for vehicular edge computing networks. IEEE International Conference on Communications, 1–6.
Zhao, Y., Liu, Y., Gong, C., & Chen, H. (2020). A survey of intelligent edge computing for Internet of Things. IEEE Internet of Things Journal, 8(10), 7846–7867.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Computational Intelligence Systems
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
