A passive optical network-approach for multiaccess edge computing optimization
-
Pritibha Sukhroop
,
Rajni Rani
Abstract
OptiDRL casts MEC resource allocation as a multiobjective decision-making problem, balancing latency, energy usage, and resource utilization. A DRL agent is learned in this context with a well-crafted reward function that balances these objectives. The optical integration provides ultra-low latency and high-throughput communication, further improving system efficiency. We deploy and test OptiDRL on simulation environments mimicking real-world MEC environments. Experimental results show that OptiDRL outperforms current state-of-the-art benchmark algorithms with a significant latency reduction of up to 35 %, resource saving of 25 %, and scalability improvement under changing workload scenarios. This paper proves the potential in integrating optical networking with DRL to advance intelligent MEC resource management.
Acknowledgments
Thanks to all my coauthors for the support.
-
Research ethics: Na.
-
Informed consent: We all are fully responsible for this paper.
-
Author contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Use of Large Language Models, AI and Machine Learning Tools: None declared.
-
Conflict of interest: The authors state no conflict of interest.
-
Research funding: None declared.
-
Data availability: Not applicable.
References
1. Zhang, H, Xiao, Y, Bu, S, Niyato, D, Yu, R, Han, Z. Fog computing in multi-tier data center networks: a hierarchical game approach. IEEE Trans Ind Inf 2019;15:4326–37.Search in Google Scholar
2. Han, Ansari, N. Auction-based resource allocation for cloud-assisted mobile edge computing. In: Proc. IEEE GLOBECOM; 2017.Search in Google Scholar
3. Mao, Y, Zhang, J, Letaief, KB. Dynamic computation offloading for mobile-edge computing with energy harvesting devices. IEEE J Sel Area Commun 2016;34:3590–605. https://doi.org/10.1109/jsac.2016.2611964.Search in Google Scholar
4. Chen, X, Jiao, L, Li, W, Fu, X. Efficient multi-user computation offloading for mobile-edge cloud computing. IEEE/ACM Trans Netw 2016;24:2795–808. https://doi.org/10.1109/tnet.2015.2487344.Search in Google Scholar
5. Chen, M, Hao, Y, Hu, L, Hossain, MS, Ghoneim, A. Edge-CoCaCo: toward joint optimization of computation, caching, and communication on edge cloud. IEEE Wireless Commun 2018;25:21–7. https://doi.org/10.1109/mwc.2018.1700308.Search in Google Scholar
6. He, Y, Yu, FR, Zhao, N, Yin, H. Software-defined networks with mobile edge computing and caching for smart cities: a big data deep reinforcement learning approach. IEEE Commun Mag 2017;55:31–7. https://doi.org/10.1109/mcom.2017.1700246.Search in Google Scholar
7. Wang, Z, Schaul, T, Hessel, M, van Hasselt, H, Lanctot, M, de Freitas, N. Dueling network architectures for deep reinforcement learning. In: Proc. ICML; 2016.Search in Google Scholar
8. Riera, AM, Do, TV, Chiumento, A, Pollin, S. NS3-gym: extending OpenAI gym for networking research. In: Proc. ACM CoNEXT; 2019.Search in Google Scholar
9. Liang, E, Liaw, R, Moritz, P, Nishihara, R, Fox, R, Goldberg, K, et al.. RLlib: abstractions for distributed reinforcement learning. In: Proc. ICML; 2018.Search in Google Scholar
10. Ling, J, Li, C, Zhang, L, Wu, Y, Tang, M, Zhu, F. Priority-Aware resource allocation for RIS-Assisted Mobile edge computing networks: a deep reinforcement learning approach. Wirel Pers Commun 2024;136:143–64. https://doi.org/10.1007/s11277-024-11227-8.Search in Google Scholar
11. Asim Ejaz, M, Wu, G, Ahmed, A, Iftikhar, S, Bawazeer, S. Utility-Driven end-to-end network slicing for diverse IoT users in MEC: a multi-agent deep reinforcement learning approach. Sensors 2024;24:5558. https://doi.org/10.3390/s24175558.Search in Google Scholar PubMed PubMed Central
12. Zhang, Y, Zhang, M, Fan, C, Li, F, Li, B. Computing resource allocation scheme of IoV using deep reinforcement learning in edge Computing environment. EURASIP J Appl Signal Process 2021;2021. https://doi.org/10.1186/s13634-021-00750-6.Search in Google Scholar
13. He, R, Li, Y. Deep reinforcement learning-based task offloading and resource allocation for MEC-Enabled IoT networks. In: Proceedings of the 2023 IEEE/CIC international conference on communications in China (ICCC workshops), Dalian, China; 2023.Search in Google Scholar
14. Pinto-Ríos, J, Calderón, F, Leiva, A, Hermosilla, G, Beghelli, A, Bórquez-Paredes, D, et al.. Resource allocation in multicore elastic optical networks: a deep reinforcement learning approach. arXiv preprint arXiv:2207.02074; 2022.10.2139/ssrn.4075565Search in Google Scholar
15. Bi, S, Huang, L, Wang, H, Zhang, Y-JA. Lyapunov-guided deep reinforcement learning for stable online computation offloading in mobile-edge computing networks. arXiv preprint arXiv:2010.01370; 2020.10.1109/TWC.2021.3085319Search in Google Scholar
16. Yan, J, Bi, S, Zhang, Y-JA. Offloading and resource allocation with general task graph in Mobile edge computing: a deep reinforcement learning approach. arXiv preprint arXiv:2002.08119; 2020.10.1109/TWC.2020.2993071Search in Google Scholar
17. Ale, L, Zhang, N, Fang, X, Chen, X, Wu, S, Li, L. Delay-aware and energy-efficient computation offloading in Mobile edge computing using deep reinforcement learning. arXiv preprint arXiv:2103.07811; 2021.10.1109/TCCN.2021.3066619Search in Google Scholar
18. Zhang, J, Chen, Z, Cheng, H, Li, J, Min, G. Resource-efficient offloading and network access optimization using deep reinforcement learning in Mobile edge networks. TechRxiv 2024. https://doi.org/10.36227/techrxiv.173268561.19289750/v1.Search in Google Scholar
19. Aishwarya, M, Mathivanan, M. Joint task offloading and resource allocation for Mobile edge computing in ultra-dense network. In: GLOBECOM 2020 - 2020 IEEE global communications conference; 2020:1–6 pp.10.1109/GLOBECOM42002.2020.9322099Search in Google Scholar
20. Ning, Z, Dong, P, Wang, X, Guo, L. Deep reinforcement learning for resource allocation in vehicular network with MEC. IEEE Trans Netw Sci Eng 2021;8:404–16.Search in Google Scholar
21. Mao, Y, You, C, Zhang, J, Huang, K, Letaief, KB. A survey on Mobile edge computing: the communication perspective. IEEE Commun Surv Tutorials 2017;19:2322–58. https://doi.org/10.1109/comst.2017.2745201.Search in Google Scholar
22. Ye, H, Li, GY, Juang, B. Deep reinforcement learning based resource allocation for V2V communications. IEEE Trans Veh Technol 2019;68:3163–73. https://doi.org/10.1109/tvt.2019.2897134.Search in Google Scholar
23. Chen, M, Hao, Y, Hu, L, Hossain, MS, Ghoneim, A. Edge-CoCaCo: toward joint optimization of computation, caching, and communication on edge cloud. IEEE Wireless Commun 2018;25:21–7. https://doi.org/10.1109/mwc.2018.1700308.Search in Google Scholar
24. Xiao, Y, Krunz, M, Song, S. Quality-aware traffic engineering for SDN-based optical networks. IEEE J Sel Area Commun 2018;36:2401–14.Search in Google Scholar
25. Musumeci, F, Rottondi, C, Tornatore, M. A survey on application-aware traffic engineering and optimization for optical networks. IEEE Commun Surv Tutorials 2018;20:109–31.Search in Google Scholar
26. Sutton, RS, Barto, AG. Reinforcement learning: an introduction, 2nd ed Cambridge, MA: MIT Press; 2018.Search in Google Scholar
27. Nunes, BAA, Mendonca, M, Nguyen, XN, Obraczka, K, Turletti, T. A survey of software-defined networking: past, present, and future of programmable networks. IEEE Commun Surv Tutorials 2014;16:1617–34. https://doi.org/10.1109/surv.2014.012214.00180.Search in Google Scholar
28. Savi, M, Palazzi, CE, Verticale, G. Impact of network topologies on latency and bandwidth in 5G backhaul. IEEE Trans Netw Serv Manag 2019;16:568–82.Search in Google Scholar
29. Shen, G, Tucker, RS. Energy-minimized design for IP over WDM networks. J Opt Commun Netw 2009;1:176–86. https://doi.org/10.1364/jocn.1.000176.Search in Google Scholar
© 2025 Walter de Gruyter GmbH, Berlin/Boston
