Abstract
The novel cloud-edge collaborative computing architecture can provide more efficient and intelligent services close to users. Reliable service function chain orchestration among datacenters is critical to ensuring computing efficiency. In this study, a service orchestration model is proposed to improve the reliability while reducing cost. The solution is a federated reinforcement learning framework that shares decision-making experiences to obtain reliable and effective service orchestration results between different datacenter environments. The simulation results demonstrate that the proposed orchestration method reaches convergence faster and has a significant performance in terms of improving service reliability.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Tai, Y.C., Yen, L.H.: Network service embedding in multiple edge systems: profit maximization by federation. In: IEEE International Conference on Communications (ICC), pp. 1–6. IEEE (2021)
Jia, Y., Wu, C., Li, Z., et al.: Online scaling of NFV service chains across geo-distributed datacenters. IEEE/ACM Trans. Netw. 26(2), 699–710 (2018). https://doi.org/10.1109/tnet.2018.2800400
Qing, H., Weifei, Z., Julong, L.: Virtual network protection strategy to ensure the reliability of SFC in NFV. In: Proceedings of the 6th International Conference on Information Engineering, pp. 1–5. ACM, New York (2017)
Wang, S., Zhou, A., Yang, M., et al.: Service composition in cyber-physical-social systems. IEEE Trans. Emerg. Topics Comput. 8(1), 82–91 (2020). https://doi.org/10.1109/TETC.2017.2675479
Qu, L., Assi, C., Khabbaz, M.J., et al.: Reliability-aware service function chaining with function decomposition and multipath routing. IEEE Trans. Netw. Serv. Manag. 17(2), 835–848 (2020)
Troia, S., Alvizu, R., Maier, G.: Reinforcement learning for service function chain reconfiguration in NFV-SDN metro-core optical networks. IEEE Access 7, 167944–167957 (2019). https://doi.org/10.1109/ACCESS.2019.2953498
Shah, H.A., Zhao, L.: Multiagent deep-reinforcement-learning-based virtual resource allocation through network function virtualization in internet of things. IEEE Internet Things J. 8(5), 3066–3074 (2020). https://doi.org/10.1109/JIOT.2020.3023111
Liu, X., Yu, J., Feng, Z., et al.: Multi-agent reinforcement learning for resource allocation in IoT networks with edge computing. China Commun. 17(9), 220–236 (2020). https://doi.org/10.23919/JCC.2020.09.017
Chen, H.M., Chen, S.Y., Wang, S.K., et al.: Designing a reinforcement learning approach for the NFV orchestration system with energy saving optimization. In 2022 8th International Conference on Applied System Innovation (ICASI), pp. 98–10. IEEE (2022)
Huang, H., Zeng, C., Zhao, Y., et al.: Scalable orchestration of service function chains in NFV-enabled networks: a federated reinforcement learning approach. IEEE J. Sel. Areas Commun. 39(8), 2558–2571 (2021). https://doi.org/10.1109/JSAC.2021.3087227
Zhang, P., Wang, C., Jiang, C., et al.: Deep reinforcement learning assisted federated learning algorithm for data management of IIoT. IEEE Trans. Industr. Inform. 17(12), 8475–8484 (2021). https://doi.org/10.1109/TII.2021.3064351
Nguyen, D.C., Ding, M., Pathirana, P.N., et al.: Federated learning for internet of things: a comprehensive survey. IEEE Commun. Surv. Tutor. 23(3), 1622–1658 (2021). https://doi.org/10.1109/JIOT.2022.3170449
Dieye, M., Ahvar, S., Sahoo, J., et al.: CPVNF: cost-efficient proactive VNF placement and chaining for value-added services in content delivery networks. IEEE Trans. Netw. Service Manag. 15(2), 774–786 (2018). https://doi.org/10.1109/TNSM.2018.2815986
Sang, I.K., Kim, H.S.: A VNF placement method based on VNF characteristics. In: International Conference on Information Networking, Jeju Island, pp. 864–869. IEEE (2021)
Yang, Z., Chen, B., Dai, M., et al.: VNF placement for service chaining in IP over WDM networks. In: Asia Communications and Photonics Conference, Hangzhou, pp. 1–3. IEEE (2018)
Kar, B., Wu, E.H.K., Lin, Y.D., et al.: Energy cost optimization in dynamic placement of virtualized network function chains. IEEE Trans. Netw. Service Manag. 15(1), 372–386 (2018). https://doi.org/10.1109/TNSM.2017.2782370
Varasteh, A., Madiwalar, B., Bemten, A.V., et al.: Holu: power-aware and delay-constrained VNF placement and chaining. IEEE Trans. Netw. Service Manag. 18(2), 1524–1539 (2021). https://doi.org/10.1109/TNSM.2021.3055693
Quang, P., Hadjadj-Aoul, Y., Outtagarts, A.: On using deep reinforcement learning for VNF forwarding graphs placement. In: 11th International Conference on Network of the Future, Bordeaux, pp. 126–128. IEEE (2020)
Pei, J., Hong, P., Pan, M., et al.: Optimal VNF placement via deep reinforcement learning in SDN/NFV-enabled networks. IEEE J. Sel. Areas Commun. 38(2), 263–278 (2020). https://doi.org/10.1109/JSAC.2019.2959181
Rui, L., Chen, X., Gao, Z., et al.: Petri net-based reliability assessment and migration optimization strategy of SFC. IEEE Trans. Netw. Service Manag. 18(1), 167–181 (2020). https://doi.org/10.1109/tnsm.2020.3045705
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Xiao, Z. et al. (2022). A Reliable Service Function Chain Orchestration Method Based on Federated Reinforcement Learning. In: Gao, H., Wang, X., Wei, W., Dagiuklas, T. (eds) Collaborative Computing: Networking, Applications and Worksharing. CollaborateCom 2022. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 460 . Springer, Cham. https://doi.org/10.1007/978-3-031-24383-7_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-24383-7_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-24382-0
Online ISBN: 978-3-031-24383-7
eBook Packages: Computer ScienceComputer Science (R0)