Authors : Dr. Amit K. Mogal; Dr. Rahul A. Patil; Dr. Sahebrao N. Shinde; Dr. Madhukar N. Shelar

Volume/Issue : Volume 11 - 2026, Issue 8 - August

Google Scholar : https://tinyurl.com/4n6kfevz

Scribd : https://tinyurl.com/34fd6kcx

DOI : https://doi.org/10.38124/ijisrt/26aug614

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Edge computing has emerged as a foundational paradigm for intelligent digital infrastructure because it reduces latency, improves bandwidth utilization, and enables real-time analytics close to data sources. Yet modern edge environments remain highly volatile. Resource availability changes continuously. IoT traffic fluctuates unpredictably. Mobile users migrate across heterogeneous networks. Conventional heuristic-based schedulers struggle to maintain stable Quality of Service (QoS) under such conditions. Deep Reinforcement Learning (DRL) offers an adaptive decision-making framework capable of learning dynamic resource allocation strategies directly from complex environments. This paper investigates adaptive edge resource management through DRL-driven optimization models for computation offloading, task scheduling, bandwidth allocation, energy efficiency, and autonomous orchestration in distributed edge ecosystems. The study synthesizes recent advances between 2020 and 2025 across edge intelligence, federated learning, multi-agent reinforcement learning, and AI-driven autonomous networking. A layered DRL-enabled edge orchestration framework is proposed to optimize latency, throughput, energy consumption, and load balancing simultaneously. The research also formulates two research questions focused on scalability and adaptive scheduling under heterogeneous workloads. The proposed methodology integrates Proximal Policy Optimization (PPO), Deep Q-Networks (DQN), Multi-Agent Deep Deterministic Policy Gradient (MADDPG), and federated reinforcement learning within a cloud-edge continuum. Comparative analysis indicates that DRL-based adaptive management substantially improves response latency, energy utilization, and computational efficiency compared with static and rule-based schedulers. The paper identifies unresolved challenges involving reward engineering, explainability, convergence stability, privacy preservation, and large-scale deployment in 6G-enabled edge systems. The findings demonstrate that DRL-driven adaptive orchestration can become a central mechanism for autonomous edge intelligence in next-generation AI-native communication infrastructures.

Keywords : Edge Computing, Deep Reinforcement Learning, Resource Management, AI-Driven Networking, Multi-Agent Learning, Federated Learning, Autonomous Networks, IoT, MEC, Cloud-Edge Continuum.

References :

1. Abed, G. A., & Al-askari, M. A. (2025). Lightweight deep reinforcement learning model for energy-efficient resource allocation in edge computing. Mesopotamian Journal of Computer Science, 2025, 385–397. https://doi.org/10.58496/MJCSC/2025/025
2. Acheampong, A., Zhang, Y., Xu, X., & Kumah, D. A. (2023). A review of current task offloading algorithms and strategies in edge computing systems. Computer Modeling in Engineering & Sciences, 134(1), 35–88. https://doi.org/10.32604/cmes.2022.022727
3. Chen, X., et al. (2025). Deep reinforcement learning based resource provisioning for federated learning in edge computing. Internet of Things, 29, 101301. https://doi.org/10.1016/j.iot.2024.101301
4. Choi, M., et al. (2022). A survey of deep reinforcement learning-based edge caching and computing. Journal of Network and Computer Applications, 214, 103617. https://doi.org/10.1016/j.jnca.2022.103617
5. Cui, Z., et al. (2026). A review of multi-agent deep reinforcement learning for edge computing. PeerJ Computer Science. https://doi.org/10.7717/peerj-cs.3728
6. Hazra, A., et al. (2024). Deep reinforcement learning in edge networks: Challenges and opportunities. ICT Express, 10(4), 1000–1015. https://doi.org/10.1016/j.icte.2024.05.002
7. Hortelano, D., et al. (2023). A comprehensive survey on reinforcement-learning-based computation offloading techniques in edge computing systems. Journal of Network and Computer Applications, 216, 103669. https://doi.org/10.1016/j.jnca.2023.103669
8. Huang, B., et al. (2025). Deep reinforcement learning for optimizing computation offloading in wireless-powered MEC systems. Ad Hoc Networks, 168, 103742. https://doi.org/10.1016/j.adhoc.2025.103742
9. Ismail, A. A., et al. (2025). A survey on resource scheduling approaches in multi-access edge computing using reinforcement learning. Cluster Computing, 28, 1–42. https://doi.org/10.1007/s10586-024-04893-7
10. Jalal, A., et al. (2025). Towards intelligent edge computing through reinforcement learning scheduling. Scientific Reports, 15, 34308. https://doi.org/10.1038/s41598-025-34308-5
11. Li, H., Liu, Y., Zhou, X., Vasilakos, X., Nejabati, R., Yan, S., & Simeonidou, D. (2023). Adaptive resource management for edge network slicing using incremental multi-agent deep reinforcement learning. arXiv. https://arxiv.org/abs/2310.17523
12. Li, T., He, X., Jiang, S., & Liu, J. (2022). A survey of privacy-preserving offloading methods in mobile-edge computing. Journal of Network and Computer Applications, 203, 103395. https://doi.org/10.1016/j.jnca.2022.103395
13. Luo, Z., et al. (2024). Reinforcement learning-based computation offloading in edge computing: A survey. Alexandria Engineering Journal, 98, 89–107. https://doi.org/10.1016/j.aej.2024.05.036
14. Mosahebfard, M., et al. (2024). Intelligent management at the edge. In AI Engineering. Springer. https://www.ncbi.nlm.nih.gov/books/NBK602357/
15. Ordóñez, S. A. C., et al. (2025). Intelligent edge computing and machine learning. Future Internet, 17(9), 417. https://doi.org/10.3390/fi17090417
16. Tang, J., et al. (2025). Deep reinforcement-learning-guided resource orchestration in edge computing. Computer Networks, 253, 110755. https://doi.org/10.1016/j.comnet.2025.110755
17. Wang, Y., et al. (2025). Research on edge computing and cloud collaborative scheduling using deep reinforcement learning. arXiv. https://arxiv.org/abs/2502.18773
18. Xu, J., Wan, W., Pan, L., Sun, W., & Liu, Y. (2024). The fusion of deep reinforcement learning and edge computing for real-time monitoring and control optimization in IoT environments. arXiv. https://arxiv.org/abs/2403.07923
19. Xu, Q., et al. (2026). Research on a computing first network based on deep reinforcement learning. Electronics, 15(3), 638. https://doi.org/10.3390/electronics15030638
20. Yang, L., et al. (2024). Deep reinforcement learning-based resource allocation in integrated sensing, communication and computation vehicular networks. IEEE Transactions on Wireless Communications. https://doi.org/10.1109/TWC.2024.3470873
21. Yu, S., Chen, X., Zhou, Z., Gong, X., & Wu, D. (2020). When deep reinforcement learning meets federated learning: Intelligent multi-timescale resource management for multi-access edge computing in 5G ultra dense networks. IEEE Internet of Things Journal, 8(4), 2238–2251. https://doi.org/10.1109/JIOT.2020.3026589
22. Zhao, X., et al. (2024). Federated deep reinforcement learning for task offloading and resource allocation in internet of vehicles. Journal of Network and Computer Applications, 235, 103899. https://doi.org/10.1016/j.jnca.2024.103899
23. Zhou, X., et al. (2024). Deep reinforcement learning-based resource scheduling in edge computing environments. Computer Communications, 223, 218–234. https://doi.org/10.1016/j.comcom.2024.04.019
24. Mao, Y., You, C., Zhang, J., Huang, K., & Letaief, K. B. (2021). A survey on mobile edge computing: The communication perspective. IEEE Communications Surveys & Tutorials, 19(4), 2322–2358. https://doi.org/10.1109/COMST.2017.2745201
25. Wang, S., Zhang, X., Zhang, Y., Wang, L., Yang, J., & Wang, W. (2020). A survey on mobile edge networks: Convergence of computing, caching and communications. IEEE Access, 5, 6757–6779. https://doi.org/10.1109/ACCESS.2017.2685434
26. Mach, P., & Becvar, Z. (2020). Mobile edge computing: A survey on architecture and computation offloading. IEEE Communications Surveys & Tutorials, 19(3), 1628–1656. https://doi.org/10.1109/COMST.2017.2682318
27. Min, M., Xiao, L., Chen, Y., Cheng, P., Wu, D., & Zhuang, W. (2021). Learning-based computation offloading for IoT devices with energy harvesting. IEEE Transactions on Vehicular Technology, 68(2), 1930–1941. https://doi.org/10.1109/TVT.2018.2885995
28. He, Y., Yu, F. R., Zhao, N., Yin, H., Boukerche, A., & Leung, V. C. M. (2021). Deep reinforcement learning for resource allocation in V2X communications. IEEE Transactions on Vehicular Technology, 68(4), 3163–3173. https://doi.org/10.1109/TVT.2019.2896830
29. Liu, C., Tang, J., Xu, J., & Zhang, W. (2022). Energy-efficient task offloading and resource allocation in edge computing. IEEE Transactions on Network and Service Management, 19(2), 1125–1139. https://doi.org/10.1109/TNSM.2021.3139945
30. Chen, M., Challita, U., Saad, W., Yin, C., & Debbah, M. (2020). Artificial neural networks-based machine learning for wireless networks. IEEE Communications Surveys & Tutorials, 21(4), 3039–3071. https://doi.org/10.1109/COMST.2019.2926625
31. Zhang, K., Mao, Y., Leng, S., Maharjan, S., & Zhang, Y. (2020). Optimal delay constrained offloading for vehicular edge computing networks. IEEE International Conference on Communications. https://doi.org/10.1109/ICC40277.2020.9149345
32. Wang, J., Gao, Y., Liu, W., Sangaiah, A. K., & Kim, H. J. (2021). An intelligent data gathering schema with data fusion supported for mobile sink in wireless sensor networks. International Journal of Distributed Sensor Networks, 15(3). https://doi.org/10.1177/1550147719839581
33. Abbas, N., Zhang, Y., Taherkordi, A., & Skeie, T. (2021). Mobile edge computing: A survey. IEEE Internet of Things Journal, 5(1), 450–465. https://doi.org/10.1109/JIOT.2017.2750180
34. Sathyanarayanan, M. (2020). The emergence of edge computing. Computer, 50(1), 30–39. https://doi.org/10.1109/MC.2017.9
35. Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2020). Edge computing: Vision and challenges. IEEE Internet of Things Journal, 3(5), 637–646. https://doi.org/10.1109/JIOT.2016.2579198
36. Wang, X., Han, Y., Wang, C., Zhao, Q., Chen, X., & Chen, M. (2021). In-edge AI: Intelligentizing mobile edge computing, caching and communication by federated learning. IEEE Network, 33(5), 156–165. https://doi.org/10.1109/MNET.011.1900286
37. Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., & Zhang, J. (2020). Edge intelligence: Paving the last mile of artificial intelligence with edge computing. Proceedings of the IEEE, 107(8), 1738–1762. https://doi.org/10.1109/JPROC.2019.2918951
38. Cao, B., Zhang, X., Wang, J., Gu, Y., & Cheng, J. (2022). Deep reinforcement learning-based adaptive task scheduling in cloud-edge systems. Future Generation Computer Systems, 129, 352–364. https://doi.org/10.1016/j.future.2021.11.014
39. Liu, Y., Peng, M., Shou, G., Chen, Y., & Chen, S. (2023). Toward edge intelligence: Multiaccess edge computing for 5G and internet of things. IEEE Internet of Things Journal, 7(8), 6722–6747. https://doi.org/10.1109/JIOT.2020.3004500
40. Sun, Y., Peng, M., Zhou, Y., Huang, Y., & Mao, S. (2021). Application of machine learning in wireless networks: Key techniques and open issues. IEEE Communications Surveys & Tutorials, 21(4), 3072–3108. https://doi.org/10.1109/COMST.2019.2924243