Real-Time Spectrum Occupancy Prediction

  • S. A. Abdelrahman
  • Omar Khaled
  • Amr Alaa
  • Mohamed Ali
  • Injy Mohy
  • Ahmed H. ElDieb
Conference paper
Part of the Lecture Notes on Data Engineering and Communications Technologies book series (LNDECT, volume 27)


Spectrum shortage and scarcity have been a strong research motivation for implementing cognitive radio to utilize the electromagnetic spectrum efficiently. Several spectrum sensing techniques have been proposed to trace and detect the primary user activity. Therefore, we can fully utilize the frequency spectrum. In this chapter, we propose an artificial neural network-based energy detection method to maximize the probability of detecting primary users in varying and dynamic environmental conditions. This is achieved by deploying cognitive engines in software-defined radios outside of the traditional simulation environment to realize the reliability of detection for real-time and over-the-air transmission. Therefore, the neural network-based energy detection algorithm is usually employed for classifying whether the channel is free or occupied with a remarkable increase in the continuous sensing and prediction accuracy in real time.



We would like to thank Virginia Tech CORNET Testbed. This work would not have been possible without the open remote access to their computational resources.


  1. 1.
    J. Mitola, G. Maguire, IEEE Pers. Commun. 6(4), 13–18 (1999). CrossRefGoogle Scholar
  2. 2.
    S.S. Haykin, Cognitive Dynamic Systems: Perception-Action Cycle, Radar, and Radio (Cambridge University Press, Cambridge, 2012)CrossRefGoogle Scholar
  3. 3.
    P.T.V. Bhuvaneswari, in Introduction to Cognitive Radio Networks and Applications (CRC Press, Boca Raton, 2016), pp. 83–97. Google Scholar
  4. 4.
    M. Sherman, A. Mody, R. Martinez, C. Rodriguez, R. Reddy, IEEE Commun. Mag. 46(7), 72–79 (2008). CrossRefGoogle Scholar
  5. 5.
    D.R. DePoy, Cognitive Radio Network Testbed (Cornet): Design, Deployment, Administration and Examples, Master’s thesis, Virginia Polytechnic Institute and State University, 2012Google Scholar
  6. 6.
    E. Sollenberger, F. Romano, C. Dietrich, in 2015 IEEE 82nd Vehicular Technology Conference (VTC2015-Fall) (2015).
  7. 7.
    T. Yucek, H. Arslan, IEEE Commun. Surv. Tutor. 11(1), 116–130 (2009). CrossRefGoogle Scholar
  8. 8.
    F. Xu, X. Zheng, Z. Zhou, in 2009 9th International Symposium on Communications and Information Technology (2009).
  9. 9.
    I.F. Akyildiz, W.Y. Lee, M.C. Vuran, S. Mohanty, Comput. Netw. 50(13), 2127–2159 (2006). CrossRefGoogle Scholar
  10. 10.
    R. Singh, S. Kansal, in 2016 IEEE Students Conference on Electrical, Electronics and Computer Science (SCEECS) (2016).
  11. 11.
    Open-access research testbed for next-generation wireless networks (orbit) (n.d.).
  12. 12.
    Network implementation testbed using open source platforms (n.d.).
  13. 13.
    Fit/cortexlab, cognitive radio testbed (n.d.).
  14. 14.
    Cognitive radio network testbed (n.d.).
  15. 15.
    T.R. Newman, A. He, J. Gaeddert, B. Hilburn, T. Bose, J.H. Reed, in 2009 5th International Conference on Testbeds and Research Infrastructures for the Development of Networks & Communities and Workshops (2009).
  16. 16.
    T.R. Newman, T. Bose, in 2009 IEEE 13th Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop (2009).
  17. 17.
  18. 18.
    Cognitive radio test system (2015).
  19. 19.

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • S. A. Abdelrahman
    • 1
  • Omar Khaled
    • 2
  • Amr Alaa
    • 2
  • Mohamed Ali
    • 2
  • Injy Mohy
    • 2
  • Ahmed H. ElDieb
    • 2
  1. 1.Scuola Superiore Sant’AnnaPisaItaly
  2. 2.CIC - Canadian International CollegeCairoEgypt

Personalised recommendations