Spectrum Occupancy Prediction for Realistic Traffic Scenarios: Time Series versus Learning-Based Models

  • Anirudh Agarwal
  • Aditya S. Sengar
  • Ranjan Gangopadhyay
Research paper


Spectrum occupancy information is necessary in a cognitive radio network (CRN) as it helps in modeling and predicting the spectrum availability for efficient dynamic spectrum access (DSA). However, in a CRN, it is difficult to ascertain a priori the pattern of the spectrum usage of the primary user due to its stochastic behavior. In this context, the spectrum occupancy prediction proves to be very useful in enhancing the quality of experience of the secondary user. This paper investigates the practical prowess of various time-series modeling approaches and the machine learning (ML) techniques for predicting spectrum occupancy, based on a spectrum measurement campaign conducted in Jaipur, Rajasthan, India. Moreover, the comparison analysis conducted between the above two approaches highlights the trade-off in terms of the respective performance depending upon the nature of the spectrum occupancy data. Nevertheless, prediction through ML-based recurrent neural network proves to perform reasonably well, thereby providing an accurate future spectrum occupancy information for DSA.


machine learning time-series models spectrum occupancy prediction dynamic spectrum access 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    G. Ding, J. Wang, Q. Wu, et al. On the limits of predictability in realworld radio spectrum state dynamics: from entropy theory to 5G spectrum sharing [J]. IEEE Communications Magazine, 2015, 53(7): 178–183CrossRefGoogle Scholar
  2. [2]
    J. Sun, L. Shen, G. Ding, et al. Predictability analysis of spectrum state evolution: performance bounds and real-world data analytics [J]. IEEE Access, 2017, 5(1): 22760–22774CrossRefGoogle Scholar
  3. [3]
    Y. Yu, J. Wang, M. Song, et al. Network traffic prediction and result analysis based on seasonal ARIMA and correlation coefficient [C]//IEEE International Conference on Intelligent System Design and Engineering Application (ISDEA), Changsha, 2010, 1: 980–983Google Scholar
  4. [4]
    Z. Wang, S. Salous. Spectrum occupancy statistics and time series models for cognitive radio [J]. Journal of Signal Processing Systems, 2011, 62(2): 145–155CrossRefGoogle Scholar
  5. [5]
    M. Wellens, P. Mähönen. Lessons learned from an extensive spectrum occupancy measurement campaign and a stochastic duty cycle model [J]. Mobile Networks and Applications, 2010, 15(3): 461–474CrossRefGoogle Scholar
  6. [6]
    F. Azmat, Y. Chen, N. Stocks. Analysis of spectrum occupancy using machine learning algorithms [J]. IEEE Transactions on Vehicular Technology, 2016, 65(9): 6853–6860CrossRefGoogle Scholar
  7. [7]
    G. R. Ding, Y. T. Jiao, J. L. Wang, et al. Spectrum inference in cognitive radio networks: algorithms and applications [J]. IEEE Communications Surveys and Tutorials, 2017, 20: 150–182CrossRefGoogle Scholar
  8. [8]
    S. Yarkan, H. Arslan. Binary time series approach to spectrum prediction for cognitive radio [C]//66th IEEE Vehicular Technology Conference (VTC 2007 Fall), Baltimore, 2007: 1563–1567CrossRefGoogle Scholar
  9. [9]
    S. Kaneko, S. Nomoto, T. Ueda, et al. Predicting radio resource availability in cognitive radio—an experimental examination [C]//3rd IEEE International Conference on Cognitive Radio Oriented Wireless Networks and Communications (CrownCom 2008), Singapore, 2008: 1–6Google Scholar
  10. [10]
    L. Pedraza, C. Hernandez, E. Rodriguez. Modeling of GSM spectrum based on seasonal arima model [C]//6th IEEE Latin-American Conference on Communications, Cartagena, 2014: 5–7Google Scholar
  11. [11]
    S. Iliya, E. Goodyer, J. Gow, et al. Application of artificial neural network and support vector regression in cognitive radio networks for RFpower prediction using compact differential evolution algorithm [C]//IEEE Federated Conference on Computer Science and Information Systems (FedCSIS), Lódz, 2015: 55–66Google Scholar
  12. [12]
    D. Das, D. W. Matolak, S. Das. Spectrum occupancy prediction based on functional link artificial neural network (FLANN) in ISM band [J]. Neural Computing and Applications, 2016: 1–14Google Scholar
  13. [13]
    A. A. Eltholth. Spectrum prediction in cognitive radio systems using a wavelet neural network [C]//24th IEEE International Conference on Software, Telecommunications and Computer Networks (SoftCOM), Split, 2016: 1–6Google Scholar
  14. [14]
    A. Agarwal, S. Dubey, M. A. Khan, et al. Learning based primary user activity prediction in cognitive radio networks for efficient dynamic spectrum access [C]//IEEE International Conference on Signal Processing and Communications (SPCOM), Bangalore, 2016: 1–5Google Scholar
  15. [15]
    M. Nekovee. A survey of cognitive radio access to TVWhite Spaces [C]//International Conference on Ultra Modern Telecommunications & Workshops, St. Petersburg, 2010: 1–8Google Scholar
  16. [16]
    G. Ding, F. Wu, Q. Wu, et al. Robust online spectrum prediction with incomplete and corrupted historical observations [J]. IEEE Transactions on Vehicular Technology, 2017, 66(9): 8022–8036CrossRefGoogle Scholar
  17. [17]
    J. T. Xue, Z. Y. Feng, P. Zhang. Spectrum occupancy measurements and analysis in Beijing [J]. IERI Procedia, 2013, 4: 295–302CrossRefGoogle Scholar
  18. [18]
    G. E. Box, G. M. Jenkins, G. C. Reinsel, et al. Time Series Analysis: Forecasting and Control [M]. John Wiley & Sons, 2015Google Scholar
  19. [19]
    C. J. Burges. A tutorial on support vector machines for pattern recognition [J]. Data Mining and Knowledge Discovery, 1998, 2(2): 121–167CrossRefGoogle Scholar
  20. [20]
    C. C. Chang, C. J. Lin. Libsvm: a library for support vector machines [J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3): 27CrossRefGoogle Scholar
  21. [21]
    M. Cacciola, G. Megalli, D. Pellicano, et al. Elman neural networks for characterizing voids in welded strips: a study [J]. Neural Computing and Applications, 2012, 21(5): 869–875CrossRefGoogle Scholar
  22. [22]
    J. S. Armstrong, F. Collopy. Error measures for generalizing about forecasting methods: Empirical comparisons [J]. International Journal of Forecasting, 1992, 8(1): 69–80CrossRefGoogle Scholar

Copyright information

© Posts & Telecom Press and Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • Anirudh Agarwal
    • 1
  • Aditya S. Sengar
    • 1
  • Ranjan Gangopadhyay
    • 1
  1. 1.Rupa Ki Nangal, Post-Sumel, via-JamdoliThe LNM Institute of Information TechnologyJaipurIndia

Personalised recommendations