Advertisement

Improved Flow Awareness Among Edge Nodes by Learning-Based Sampling in Software Defined Networks

  • Jun Deng
  • He Cai
  • Sheng Chen
  • Jianji Ren
  • Xiaofei WangEmail author
Article
  • 29 Downloads

Abstract

To improve the specific quality of service, internal network management and security analysis in the future mobile network, accurate flow-awareness in the global network through packet sampling has been a viable solution. However, the current traffic measurement method with the five tuples cannot recognize the deep information of flows, and the Deep Packet Inspection (DPI) deployed at the gateways or access points is lack of traffic going through the internal nodes(e.g., base station, edge server). In this paper, by means of Deep Q-Network (DQN) and Software-Defined Networking (SDN) technique, we propose a flow-level sampling framework for edge devices in the Mobile Edge Computing (MEC) system. In the framework, an original learning-based sampling strategy considering the iterative influences of nodes is used for maximizing the long-term sampling accuracy of both mice and elephant flows. We present an approach to effectively collect traffic packets generated from base stations and edge servers in two steps: 1) adaptive node selection, and 2) dynamic sampling duration allocation by Deep Q-Learning. The results show that the approach can improve the sampling accuracy, especially for mice flows.

Keywords

Edge computing Deep Q-learning SDN Flow-awareness Resource allocation 

Notes

Acknowledgments

This work is partially supported by the National Key R&D Program of China (2018YFC0809803), China NSFC (Youth) through grant 61702364, China NSFC GD Joint fund U1701263.

References

  1. 1.
    Li XH, Wang XF, Li KQ, Han Z, Leung VCM (2017) Collaborative Multi-Tier caching in heterogeneous networks: modeling, analysis, and design. IEEE Trans 16(10):6926–6939Google Scholar
  2. 2.
    Wang XF, Zhang Y, Leung VCM, Guizani N, Jiang TP (2018) D2D big data: content deliveries over wireless device-to-device sharing in realistic large scale mobile networks. IEEE Wirel Commun 25(1):32–38CrossRefGoogle Scholar
  3. 3.
    Wang XF, Chen M, Leung VCM, Hwang Z, Hwang K (2018) Integrating social networks with mobile device-to-device services, IEEE Trans,  https://doi.org/10.1109/TSC.2018.2867437
  4. 4.
    Wang XF, Hang YW, Wang CY et al In-edge AI: intelligentizing mobile edge computing, caching and communication by federated learning, IEEE Network Magazine, arXiv:1809.07857
  5. 5.
    Li XH, Wang XF, Wang PJ, Han Z (2018) Hierarchical edge caching in device-to-device aided mobile networks: modeling, optimization, and design. IEEE JSAC 36(8):1768–1785Google Scholar
  6. 6.
    Nunna S, Kousaridas A, Ibrahim M et al (2015) Enabling real-time context-aware collaboration through 5G and mobile edge computing, in ITNG, pp 601–605Google Scholar
  7. 7.
    Benson T, Akella A, Maltz DA (2010) Network traffic characteristics of data centers in the wild, in ACM SIGCOMM, pp 267–280Google Scholar
  8. 8.
    Patel M et al (2014) Mobile-edge computing introductory technical white paper. White Paper, Mobile-Edge Computing (MEC) Industry InitiativeGoogle Scholar
  9. 9.
    Barr AB, Harchol Y, Hay D, Koral Y (2014) Deep packet inspection as a service, in ACM coNEXT, pp 271–282Google Scholar
  10. 10.
    Zhu YB, Kang NX, Cao JX, Greenberg A, Lu GH (2015) Packet-level telemetry in large datacenter networks. ACM SIGCOMM 45(4):479–491Google Scholar
  11. 11.
    Paolucci F, Sgambelluri A, Cugini F (2018) Network telemetry streaming services in SDN-based disaggregated optical networks. J Lightwave Technol 32(15):3142–3149CrossRefGoogle Scholar
  12. 12.
    Su Z, Wang T, Hamdi M (2015) COSTA: cross-layer Optimization for sketch-based software defined measurement task assignment, in IEEE IWQos, pp 183–188Google Scholar
  13. 13.
    Yu M, Jose L, Miao R (2013) Software defined traffic measurement with OpenSketch, in USENIX NSDI, pp 29–42Google Scholar
  14. 14.
    Bouet M, Leguay J, Conan V (2014) Cost-based placement of virtualized deep packet inspection functions in SDN, in IEEE MILCOM, pp 992–997Google Scholar
  15. 15.
    Suh J, Kwon TT, Dixon C, Felter W, Carter J (2014) Opensample: a low-latency, sampling-based measurement platform for commodity SDN, in IEEE ICDCS, pp 228–237Google Scholar
  16. 16.
    Xing CY, Ding K, Hu C, Chen M (2016) Sample and fetch-based large flow detection mechanism in software defined networks. IEEE Communication Letters 20(9):1764–1767CrossRefGoogle Scholar
  17. 17.
    Liu Q, Li P, Zhao W, Cai W, Yu S, Leung VCM (2018) A survey on security threats and defensive techniques of machine learning: a data driven view. IEEE Access 6:12103–12117CrossRefGoogle Scholar
  18. 18.
    Yoon S, Ha T, Kim S, Lim H (2017) Scalable traffic sampling using centrality measure on software-defined networks. IEEE Communications Magazine 55(7):43–49CrossRefGoogle Scholar
  19. 19.
    Ha T, Kim S, An N, Narantuya J, Jeong C, Kim JW (2016) Suspicious traffic sampling for intrusion detection in software-defined networks. Comput Netw 109(2):172–182CrossRefGoogle Scholar
  20. 20.
    Abbas N, Zhang Y, Taherkordi A, Skeie T (2018) Mobile edge computing: a survey. IEEE Internet Things J 5(1):450–465CrossRefGoogle Scholar
  21. 21.
    Su Z, Wang T, Xia Y, Hamdi M (2015) CeMon: a cost-effective flow monitoring system in software defined networks. Comput Netw 92(1):101–115CrossRefGoogle Scholar
  22. 22.
    Tahaei H, Salleh RB, Razak MF, Ko K, Anuar NB (2017) An efficient sampling and classification approach for flow detection in SDN-based big data centers, in IEEE AINA, pp 1106–1115Google Scholar
  23. 23.
    He Y, Zhao N, Yin HX (2018) Integrated networking, caching, and computing for connected vehicles: a deep reinforcement learning approach. IEEE Trans 67(1):44–55Google Scholar
  24. 24.
    Qiu C, Yao HP, Yu R, Xu FM, Zhao CL (2019) Deep Q-learning aided networking, caching, and computing resources allocation in software-defined satellite-terrestrial networks, in IEEE TransactionsGoogle Scholar
  25. 25.
    Li H, Gao H, Lv TJ, Lu Y (2018) Deep Q-learning based dynamic resource allocation for self-powered ultra-dense networks, in IEEE ICC, pp 1–6Google Scholar
  26. 26.
    He Y, Zhang Z, Yu FR, Zhao N (2017) Deep-reinforcement-learning-based optimization for cache-enabled opportunistic interference alignment wireless networks. IEEE Trans 66(11):10433–10445Google Scholar
  27. 27.
    Taleb T, Samdanis K, Mada B, Flinck H, Dutta S (2017) On multi-access edge computing: a survey of the emerging 5g network edge cloud architecture and orchestration. IEEE Communications Surveys & Tutorials 19 (3):1657–1687CrossRefGoogle Scholar
  28. 28.
    Tong L, Gao W (2016) Application-aware traffic scheduling for workload offloading in mobile clouds, in IEEE INFOCOM, pp 1–9Google Scholar
  29. 29.
    Lu L, Chen D, Ren XL, Zhang QM, Zhang YC, Zhou T (2016) Vital nodes identification in complex networks. Phys Rep 65:1–63MathSciNetGoogle Scholar
  30. 30.
    Bai W, Chen L, Chen K, Han DS, Tian C, Wang H (2017) PIAS: practical information-agnostic flow scheduling for commodity data centers. IEEE TON 25(4):1954–1967CrossRefGoogle Scholar
  31. 31.
    Vanini E, Pan R, Alizadeh M, Taheri P (2017) Let it flow resilient asymmetric load balancing with flowlet switching, in USENIX NSDI, pp 407–420Google Scholar
  32. 32.
    Alizadeh M, Yang S, Sharif M, Taheri P, Katti S (2013) pFabric: minimal near-optimal datacenter transport. ACM SIGCOMM 43(4):435–446CrossRefGoogle Scholar
  33. 33.
    Mnih V, Kavukcuoglu K, Silver D, Rusu AA (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529–533CrossRefGoogle Scholar
  34. 34.
    Van Hasselt H, Guez A, Silver D (2016) Deep reinforcement learning with double q-learning, in AAAI, pp 2094–2100Google Scholar
  35. 35.
    Wilson AC, Roelofs R, Stern M, Srebro N, Recht B (2017) The marginal value of adaptive gradient methods in machine learning, in NIPS, vol 30Google Scholar
  36. 36.
    Wang S, Zhao Y, Xu J, Yuan J, Hsu CH (2018) Edge server placement in mobile edge computing, in  https://doi.org/10.1016/j.jpdc.2018.06.008 CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Tianjin Key Laboratory of Advanced Networking, College of Intelligence and ComputingTianjin UniversityTianjinChina
  2. 2.Henan Polytechnic UniversityJiaozuoChina

Personalised recommendations