Service Chain Orchestration Based on Deep Reinforcement Learning in Intent-Based IoT

  • Zhan ShiEmail author
  • Ying Zeng
  • Zanhong Wu
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1143)


Intent-based network (IBN) is a novel approach to network management and automation designed to simplify a generic high-level policy called intent to a specific low-level network configuration. At present, plenty of researches have focused more on definition of intent-based northbound interface (NBI) but less on methods for intent-based service orchestration. In this paper, an IBN reference architecture is presented to manage IoT infrastructure and deliver end-to-end services across multi-domains. After that, this paper introduces a DDQN-based heuristic algorithm to solve the dynamic service chain orchestration problem. Simulation results clearly show that the proposed algorithm has better cost efficiency and convergence than those of compared algorithms, and can also guarantee the QoS requirements and make the traffic balanced.


Deep reinforcement learning Intent-based Service chain IoT Orchestration 



This work was supported by the science and technology project of Guangdong power grid (036000KK52160025).


  1. 1.
    Cerroni, W., Buratti, C., Cerboni, S., Davoli, G., Contoli, C., et al.: Intent-based management and orchestration of heterogeneous openflow/IoT SDN domains. In: 2017 IEEE Conference on Network Softwarization (NetSoft), Bologna, pp. 1–9 (2017)Google Scholar
  2. 2.
    Chao, W., Horiuchi, S.: Intent-based cloud service management. In: 2018 21st Conference on Innovation in Clouds, Internet and Networks and Workshops (ICIN), Paris, pp. 1–5 (2018)Google Scholar
  3. 3.
    Callegati, F., Cerroni, W., Contoli, C., Foresta, F.: Performance of intent-based virtualized network infrastructure management. In: 2017 IEEE International Conference on Communications (ICC), Paris, pp. 1–6 (2017)Google Scholar
  4. 4.
    Subramanya, T., Riggio, R., Rasheed, T.: Intent-based mobile backhauling for 5G networks. In: 2016 12th International Conference on Network and Service Management (CNSM), Montreal, QC, pp. 348–352 (2016)Google Scholar
  5. 5.
    Paganelli, F., Paradiso, F., Gherardelli, M., Galletti, G.: Network service description model for VNF orchestration leveraging intent-based SDN interfaces. In: 2017 IEEE Conference on Network Softwarization (NetSoft), Bologna, pp. 1–5 (2017)Google Scholar
  6. 6.
    Chen, Y., Wang, L., Lin, F., Lin, B.P.: Deterministic quality of service guarantee for dynamic service chaining in software defined networking. IEEE Trans. Netw. Serv. Manage. 14(4), 991–1002 (2017)CrossRefGoogle Scholar
  7. 7.
    Gu, L., Chen, X., Jin, H., Lu, F.: VNF deployment and flow scheduling in geo-distributed data centers. In: 2018 IEEE International Conference on Communications (ICC), Kansas City, MO, pp. 1–6 (2018)Google Scholar
  8. 8.
    Gupta, A., Jaumard, B., Tornatore, M., Mukherjee, B.: A scalable approach for service chain mapping with multiple SC instances in a wide-area network. IEEE J. Sel. Areas Commun. 36(3), 529–541 (2018)CrossRefGoogle Scholar
  9. 9.
    Carpio, F., Jukan, A., Pries, R.: Balancing the migration of virtual network functions with replications in data centers. In: NOMS 2018—2018 IEEE/IFIP Network Operations and Management Symposium, Taipei, pp. 1–8 (2018)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2021

Authors and Affiliations

  1. 1.Guangdong Power Grid Co., Ltd., Electric Power Dispatch & Control CenterGuangzhouChina

Personalised recommendations