Real-Time Spectrum Sensing on an RTL-SDR-Based IoT Platform
Keywords:
Cognitive Radio (CR), Spectrum sensing, Real-time, Internet of Things (IoT) networks, Machine Learning (ML).Abstract
This focuses on the application of cognitive radio (CR) technologies in Internet of Things (IoT) networks for dynamic spectrum access among a large number of IoT end nodes. Spectrum Sensing (SS) is a fundamental function in CR-IoT nodes, which allows cognitive devices to sense and identify spectrum holes. In this research, we realize a real-time implementation of SS based on SDRs and ED. Furthermore, we use Machine Learning (ML) tools, specifically Support Vector Machine (SVM), to develop an offline sample of energy detection. We use USRP N210 and RTL-SDRs as hardware in the laboratory's unblended test bed for the SS methodology. The results obtained have shown that energy detection is the promising method at SNR -10 dB and higher. This is because of the difficulty in accurately choosing λ when SNR < -10 dB. The investigation also used SVM with an off-line training of a set of energy detection samples to estimate status of the channel. Simulation reveals however that energy detection is limited in low SNR regimes, notably in the selection of an adequate threshold. Alternatively, we have introduced a novel machine learning technique using SVM that can operate more effectively than the existing ones for spectrum sensing in harsh environment. It is successful due to SVM’s capability to accommodate complicated decision boundaries and learns from samples.
References
[1] Ghasemi, A., & Sousa, E. S. (2008). Spectrum sensing in cognitive radio networks: Requirements, challenges and design trade-offs. IEEE Communications Magazine, 46(4), 32–39. https://doi.org/10.1109/MCOM.2008.4481338
[2] Biglieri, E., Goldsmith, A. J., Greenstein, L. J., Mandayam, N. B., & Poor, H. V. (2013). Principles of cognitive radio. Cambridge University Press.
[3] Sadhukhan, P., Kumar, N., & Bhatnagar, M. R. (2013). Improved energy detector based spectrum sensing for cognitive radio: An experimental study. In Proceedings of the 2013 IEEE Annual India Conference (INDICON). https://doi.org/10.1109/INDCON.2013.6725925
[4] Subhedar, M., & Birajdar, G. (2011). Spectrum sensing techniques in cognitive radio networks: A survey. International Journal of Next-Generation Networks, 3(2), 37–51. https://doi.org/10.5121/ijngn.2011.3203
[5] Yusof, K. H., Rahim, M. K. A., Yusof, K. M., & Jalil, M. E. (2015). Energy detection spectrum sensing measurement using GNU radio and USRP B200 at Wi-Fi frequency. Lecture Notes in Electrical Engineering, 344, 223–230. https://doi.org/10.1007/978-3-319-17269-9_24
[6] Grönroos, S., Nybom, K., Björkqvist, J., Hallio, J., Auranen, J., & Ekman, R. (2016). Distributed spectrum sensing using low cost hardware. Journal of Signal Processing Systems, 83(1), 5–17. https://doi.org/10.1007/S11265-015-1033-1
[7] Huang, Z., Wang, W., & Zhang, Y. (2012). Design and implementation of cognitive radio hardware platform based on USRP. In IET Conference Publications (Vol. 2011, No. 586 CP, pp. 160–164). https://doi.org/10.1049/CP.2011.0651
[8] Hussein, A. T., Kivanc, D., Abdullah, H., & Falih, M. S. (2023). Deep learning based spectrum sensing method for cognitive radio system (pp. 319–331). https://doi.org/10.1007/978-3-031-27099-4_25
[9] Yücek, T., & Arslan, H. (2009). A survey of spectrum sensing algorithms for cognitive radio applications. IEEE Communications Surveys & Tutorials, 11(1), 116–130. https://doi.org/10.1109/SURV.2009.090109
[10] Gandhiraj, R., & Soman, K. P. (2014). Modern analog and digital communication systems development using GNU Radio with USRP. Telecommunication Systems, 56(3), 367–381. https://doi.org/10.1007/S11235-013-9850-7
[11] Bharadwaj, A. S., Rego, R., & Chowdhury, A. (2017). IoT based solid waste management system: A conceptual approach with an architectural solution as a smart city application. In Proceedings of the 2016 IEEE Annual India Conference (INDICON). https://doi.org/10.1109/INDICON.2016.7839147
