Advertisement

Using Deep Learning and Radio Virtualisation for Efficient Spectrum Sharing Among Coexisting Networks

  • Wei Liu
  • Joao F. Santos
  • Xianjun Jiao
  • Francisco Paisana
  • Luiz A. DaSilva
  • Ingrid Moerman
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 261)

Abstract

This work leverages recent advances in machine learning for radio environment monitoring with context awareness, and uses the obtained information for creating radio slices that can optimally coexist with ongoing traffic in a given spectrum band. We instantiate radio slices as virtualised radios built on a software-defined radio platform. Then, we describe a proof-of-concept experiment that validates and demonstrates our proposed solution.

Keywords

Machine learning Radio access technology classification Radio virtualisation Software-defined radio 

References

  1. 1.
    3rd Generation Partnership Project: 3GPP TR 28.801: study on management and orchestration of network slicing for next generation network. 3rd Generation Partnership Project, Technical report, May 2017Google Scholar
  2. 2.
    Rost, P., et al.: Network slicing to enable scalability and flexibility in 5G mobile networks. IEEE Commun. Mag. 55(5), 72–79 (2017)CrossRefGoogle Scholar
  3. 3.
    Khan, S.N., et al.: Virtualization of spectrum resources for 5G networks, In: 2017 European Conference on Networks and Communications (EuCNC), pp. 1–5 (2017)Google Scholar
  4. 4.
    van de Belt, J., et al.: Defining and surveying wireless link virtualization and wireless network virtualization. IEEE Commun. Surv. Tutor. 19(3), 1603–1627 (2017)CrossRefGoogle Scholar
  5. 5.
    Liang, C., et al.: Wireless network virtualization: a survey, some research issues and challenges. IEEE Commun. Surv. Tutor. 17(1), 358–380 (2015)CrossRefGoogle Scholar
  6. 6.
    Wunsch, F., et al.: DySPAN spectrum challenge: situational awareness and opportunistic spectrum access benchmarked. IEEE Trans. Cogn. Commun. Netw. 3(3), 550–562 (2017)CrossRefGoogle Scholar
  7. 7.
    Selim, A., et al.: Spectrum monitoring for radar bands using deep convolutional neural networks. IEEE Globecom (2017)Google Scholar
  8. 8.
    de Figueiredo, F.A.P., et al.: Radio hardware virtualization for software-defined wireless networks. Wirel. Pers. Commun. 100(1), 113–126 (2018).  https://doi.org/10.1007/s11277-018-5619-3CrossRefGoogle Scholar
  9. 9.
    Mendes, J., et al.: Cellular access multi-tenancy through small cell virtualization and common RF front-end sharing. In: Workshop on Wireless Network Testbeds, Experimental evaluation and Characterization. ACM, pp. 35–42 (2017)Google Scholar
  10. 10.
    Jiao, X., Moerman, I., Liu, W., de Figueiredo, F.A.P.: Radio hardware virtualization for coping with dynamic heterogeneous wireless environments. In: Marques, P., Radwan, A., Mumtaz, S., Noguet, D., Rodriguez, J., Gundlach, M. (eds.) CrownCom 2017. LNICST, vol. 228, pp. 287–297. Springer, Cham (2018).  https://doi.org/10.1007/978-3-319-76207-4_24CrossRefGoogle Scholar
  11. 11.
    Zynq-7000 All Programmable SoC ZC706 evaluation kit, Xilinx (2015). https://www.xilinx.com/support/documentation/boards_and_kits/zc706/2015_4/ug961-zc706-GSG.pdf
  12. 12.
    AD-FMCOMMS2-EBZ User Guide, Analog Device (2018). https://wiki.analog.com/resources/eval/user-guides/ad-fmcomms2-ebz

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2019

Authors and Affiliations

  • Wei Liu
    • 1
  • Joao F. Santos
    • 2
  • Xianjun Jiao
    • 1
  • Francisco Paisana
    • 2
  • Luiz A. DaSilva
    • 2
  • Ingrid Moerman
    • 1
  1. 1.IDLab University Ghent - IMECGhentBelgium
  2. 2.Trinity College Dublin - CONNECT CentreDublinIreland

Personalised recommendations