Abstract
The intelligent edge has accelerated the Internet of Things (IoT) revolution towards next-generation operational efficiency and massive connectivity. Supporting fast response, agility, and adaptive industrial IoT (IIoT) services, on the other hand, remains a challenge. In this paper, we investigate the dynamic service function chain (SFC) orchestration problem (i.e., SFC-DOP) in edge intelligence-empowered IIoT. By jointly considering the unique characteristics of IIoT service requests, i.e., specific delay constraints as well as the time-varying and heterogeneous natures of the IIoT, this optimization problem is modeled as a Markov decision process (MDP). The aforementioned MDP problem is then solved by the optimized soft actor-critic (SAC) deep reinforcement learning (DRL) method based on the maximum entropy framework. Simulation results demonstrate that compared to existing DRL-based methods (i.e., DDPG, TD3, and PPO), the optimized-SAC methods can achieve significant improvements in throughput and scalability with delay guarantee, and adapt to varying scenarios.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10922-023-09743-2/MediaObjects/10922_2023_9743_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10922-023-09743-2/MediaObjects/10922_2023_9743_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10922-023-09743-2/MediaObjects/10922_2023_9743_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10922-023-09743-2/MediaObjects/10922_2023_9743_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10922-023-09743-2/MediaObjects/10922_2023_9743_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10922-023-09743-2/MediaObjects/10922_2023_9743_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10922-023-09743-2/MediaObjects/10922_2023_9743_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10922-023-09743-2/MediaObjects/10922_2023_9743_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10922-023-09743-2/MediaObjects/10922_2023_9743_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10922-023-09743-2/MediaObjects/10922_2023_9743_Fig10_HTML.png)
Similar content being viewed by others
Data Availability
Not applicable.
References
Aazam, M., Zeadally, S., Harras, K.A.: Deploying fog computing in industrial Internet of Things and industry 4.0. IEEE Trans. Ind. Inf. 14(10), 4674–4682 (2018)
Chalapathi, G.S.S., Chamola, V., Vaish, A., Buyya, R.: Industrial Internet of Things (IIoT) applications of edge and fog computing: A review and future directions. Fog/Edge Comput. Secur. Privacy App. 293–325 (2021)
Abbas, N., Zhang, Y., Taherkordi, A., Skeie, T.: Mobile edge computing: A survey. IEEE Internet Things J. 5(1), 450–465 (2017)
Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., Zhang, J.: Edge intelligence: Paving the last mile of artificial intelligence with edge computing. Proc. IEEE 107(8), 1738–1762 (2019)
Fu, X., Yu, F.R., Wang, J., Qi, Q., Liao, J.: Dynamic service function chain embedding for NFV-enabled IoT: A deep reinforcement learning approach. IEEE Trans. Wireless Commun. 19(1), 507–519 (2019)
Cai, J., Huang, Z., Liao, L., Luo, J., Liu, W.-X.: APPM: Adaptive parallel processing mechanism for service function chains. IEEE Trans. Netw. Serv. Manage. 18(2), 1540–1555 (2021)
Fu, F., Kang, Y., Zhang, Z., Yu, F.R., Wu, T.: Soft actor-critic DRL for live transcoding and streaming in vehicular fog-computing-enabled IOV. IEEE Internet Things J. 8(3), 1308–1321 (2020)
Liu, Y., Lu, H., Li, X., Zhang, Y., **, L., Zhao, D.: Dynamic service function chain orchestration for NFV/MEC-enabled IoT networks: A deep reinforcement learning approach. IEEE Internet Things J. 8(9), 7450–7465 (2020)
Xu, S., Li, Y., Guo, S., Lei, C., Liu, D., Qiu, X.: Cloud-edge collaborative SFC map** for industrial IoT using deep reinforcement learning. IEEE Trans. Industr. Inf. 18(6), 4158–4168 (2021)
Chen, H., Wang, S., Li, G., Nie, L., Wang, X., Ning, Z.: Distributed orchestration of service function chains for edge intelligence in the industrial Internet of Things. IEEE Trans. Ind. Inf. 18(9), 6244–6254 (2021)
Zhang, K., Zhu, Y., Maharjan, S., Zhang, Y.: Edge intelligence and blockchain empowered 5G beyond for the industrial Internet of Things. IEEE Netw. 33(5), 12–19 (2019)
Hazra, A., Adhikari, M., Amgoth, T., Srirama, S.N.: Collaborative AI-enabled intelligent partial service provisioning in green industrial fog networks. IEEE Internet Things J. (2021)
Arulkumaran, K., Deisenroth, M.P., Brundage, M., Bharath, A.A.: Deep reinforcement learning: A brief survey. IEEE Signal Process. Mag. 34(6), 26–38 (2017)
Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: Proc. International Conference on Machine Learning, pp. 1861–1870 (2018). PMLR
Sun, W., Liu, J., Yue, Y.: AI-enhanced offloading in edge computing: When machine learning meets industrial IoT. IEEE Netw. 33(5), 68–74 (2019)
Amin, S.U., Hossain, M.S.: Edge intelligence and Internet of Things in healthcare: A survey. IEEE Access 9, 45–59 (2020)
**a, W., Zhang, J., Quek, T.Q., **, S., Zhu, H.: Mobile edge cloud-based industrial Internet of Things: Improving edge intelligence with hierarchical SDN controllers. IEEE Veh. Technol. Mag. 15(1), 36–45 (2020)
Bari, F., Chowdhury, S.R., Ahmed, R., Boutaba, R., Duarte, O.C.M.B.: Orchestrating virtualized network functions. IEEE Trans. Netw. Serv. Manage. 13(4), 725–739 (2016)
Li, G., Zhou, H., Feng, B., Zhang, Y., Yu, S.: Efficient provision of service function chains in overlay networks using reinforcement learning. IEEE Trans. Cloud Comput. 10(1), 383–395 (2022)
Guo, S., Dai, Y., Xu, S., Qiu, X., Qi, F.: Trusted cloud-edge network resource management: DRL-driven service function chain orchestration for IoT. IEEE Internet Things J. 7(7), 6010–6022 (2019)
Schneider, S., Khalili, R., Manzoor, A., Qarawlus, H., Schellenberg, R., Karl, H., Hecker, A.: Self-learning multi-objective service coordination using deep reinforcement learning. IEEE Trans. Netw. Serv. Manage. 18(3), 3829–3842 (2021)
Knight, S., Nguyen, H.X., Falkner, N., Bowden, R., Roughan, M.: The internet topology zoo. IEEE J. Sel. Areas Commun. 29(9), 1765–1775 (2011)
Fischer, W., Meier-Hellstern, K.: The Markov-modulated Poisson process (MMPP) cookbook. Perform. Eval. 18(2), 149–171 (1993)
Orlowski, S., Wessäly, R., Pióro, M., Tomaszewski, A.: SNDlib 1.0-survivable network design library. Netw.: Int. J 55(3), 276–286 (2010)
Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., Dormann, N.: Stable-baselines3: Reliable reinforcement learning implementations. J. Mach. Learn. Res. 268(22), 1–8 (2021)
Haarnoja, T., Zhou, A., Hartikainen, K., Tucker, G., Ha, S., Tan, J., Kumar, V., Zhu, H., Gupta, A., Abbeel, P., et al.: Soft actor-critic algorithms and applications. ar**v preprint ar**v:1812.05905 (2018)
Hieu, N.Q., Hoang, D.T., Niyato, D., Wang, P., Kim, D.I., Yuen, C.: Transferable deep reinforcement learning framework for autonomous vehicles with joint radar-data communications. IEEE Trans. Commun. 70(8), 5164–5180 (2022)
Zhang, X., **, X., Tripp, C., Biagioni, D.J., Graf, P., Jiang, H.: Transferable reinforcement learning for smart homes. In: Proceedings of the 1st International Workshop on Reinforcement Learning for Energy Management in Buildings & Cities, pp. 43–47 (2020)
Funding
This work was supported by the National Key R &D Program of China No. 2019YFB1804400, and MUST Faculty Research Grants No. FRG-21-031-IINGI.
Author information
Authors and Affiliations
Contributions
ZH: original draft writing and preparation, simulation implementation, and results analysis. ZH: Simulation & results analysis, Review & Editing. DL: methodology, review & editing manuscript, funding acquisition. HL: funding acquisition, supervision.
Corresponding author
Ethics declarations
Conflict of interest
The authors have no competing interests as defined by Springer.
Ethical Approval
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Huang, Z., Zhong, W., Li, D. et al. Delay Constrained SFC Orchestration for Edge Intelligence-Enabled IIoT: A DRL Approach. J Netw Syst Manage 31, 53 (2023). https://doi.org/10.1007/s10922-023-09743-2
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10922-023-09743-2