A Machine Learning Framework for Spectrum Sensing and Occupancy Analysis Using Satellite Data

(Sreerama Samartha J.G., Archana N.V., Dayananda GK and Vayusutha M.)

---

Abstract

In satellite communication systems, effective spectrum sensing and management are essential, especially in scenarios involving both geostationary Earth orbit (GEO) and non-geostationary Earth orbit (NGEO) satellites. As the number of NGEO satellites increases, managing interference with GEO signals becomes more complex. This study introduces a machine learning (ML) framework for spectrum sensing, spectrum hole detection and occupancy prediction based on satellite data. The framework utilizes two ML models, support vector machine (SVM) and random forest (RF), along with a hybrid model combining both. SVM is used to classify spectrum occupancy based on GEO signals, while RF is employed to detect spectrum holes and predict future occupancy patterns. The hybrid model merges the strengths of both to enhance prediction accuracy and robustness. A comparative analysis of the models evaluated accuracy, computation time and robustness against interference. The results show that SVM achieved 99.17% accuracy, excelling in precision, while RF reached 99.12% accuracy, demonstrating better recall and more effective identification of occupied spectrum regions. The hybrid model outperformed both, achieving 99.25% accuracy, with an improved balance between precision and recall and superior performance under complex interference conditions. This study highlights the effectiveness of SVM, RF and their hybrid in optimizing spectrum management.
KEYWORDS
Hybrid Model, machine learning, random forest, satellite communication, spectrum management, support vector-machine

PDF

References

Al-Hraishawi, H., Soultanopoulos, S. and Bhat, S.M. (2022). A survey on nongeostationary satellite systems: The communication perspective. IEEE Communications Surveys and Tutorials, 25(1), 101–32.  DOI: 10.1109/COMST.2022.3142080
Cullen, A.C., Martindale, C.F., Taylor, C.M., Al-Shabibi, A. and Ajit, H. (2023). Predicting dynamic spectrum allocation: A review covering simulation, modelling, and prediction. Artificial Intelligence Review, 56(10), 10921–59. DOI: 10.1007/s10462-023-10402-7
Ding, X., Feng, L., Zou, Y. and Zhang, G. (2020). Deep learning aided spectrum prediction for satellite communication systems. IEEE Transactions on Vehicular Technology, 69(12), 16314–9. DOI: 10.1109/TVT.2020.3039112
Feng, T., Fan, F. and Bednarz, T. (2021). A review of computer graphics approaches to urban modeling from a machine learning perspective. Frontiers of Information Technology and Electronic Engineering, 22(7), 915–25. DOI: 10.1631/FITEE.2000065
Fernández-Rodrígueza, E. and Rowlandb, Z. (2022). Current status and future trends in radio link interference research for the planning of sustainable geocentric satellite constellations. In: 73rd International Astronautical Congress (IAC), Paris, France, 18-22 /9/ 2022.
Fourati, F. and Alouini, M.S. (2021). Artificial intelligence for satellite communication: A review. Intelligent and Converged Networks, 2(3), 213–43. DOI: 10.23919/ICN.2021.0014
Kaur, R., Goyal, N., Goyal, D. and Goyal, N. (2017). Analysis of energy detection and cyclostationary feature detection under fading channels in CRNs. Communication and Computing Systems, n/a(n/a) 327–34. DOI: 10.1201/9781315152651-45
Liu, C. and Gryllias, K. (2020). A semi-supervised support vector data description-based fault detection method for rolling element bearings based on cyclic spectral analysis. Mechanical Systems and Signal Processing, 140(n/a), 106682. DOI: 10.1016/j.ymssp.2020.106682
Nasser, A., Hosseini, S.A., Zargari, M.D. and Duong, T.Q. (2021). Spectrum sensing for cognitive radio: Recent advances and future challenges. Sensors, 21(7), 2408. DOI: 10.3390/s21072408
Ren, S., Wang, Q., Wang, M. and Yu, C. (2021). An adaptive compressive wideband spectrum sensing algorithm based on least squares support vector machine. IEEE Access, 9(n/a), 116594–603. DOI: 10.1109/ACCESS.2021.3104162.
Sabir, B., Yang, S., Nguyen, D., Wu, N., Abuadbba, A., Suzuki, H. and Nepal, S. (2024). Systematic Literature Review of AI-enabled Spectrum Management in 6G and Future Networks. arXiv preprint arXiv, 2407(n/a). 10981. DOI: 10.48550/arXiv.2407.10981
Sharma, S.K., Chatzinotas, S. and Ottersten, B. (2016). In‐line interference mitigation techniques for spectral coexistence of GEO and NGEO satellites. International Journal of Satellite Communications and Networking, 34(1), 11–39. DOI: 10.1002/sat.1127
Sirohiya, S., Baghel, A. and Bhatia, V. (2022). Enhancement of Spectrum Efficiency in Satellite Communication Applying Prediction Model of Machine Learning Technique. In: Second International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT).  Bhilai, India 21-22 /4/ 2022. DOI:10.1109/ICAECT54875.2022.9808054
Soares, M.D., Passos, D. and Castellanos, P.V.G. (2023). Cognitive Radio with Machine Learning to Increase Spectral Efficiency in Indoor Applications on the 2.5 GHz Band. Sensors, 23(10), 4914. DOI:10.3390/s23104914
Venkatapathi, P., Khan, H., Rao, S.S. and Immadi, G. (2024). Cooperative spectrum sensing performance assessment using machine learning in cognitive radio sensor networks. Engineering, Technology and Applied Science Research, 14(1), 12875–9. DOI: 10.48084/etasr.6639
Wang, Y., Ding, X. and Zhang, G. (2020). A novel dynamic spectrum-sharing method for GEO and LEO satellite networks. IEEE Access, 8(n/a), 147895–906. DOI: 10.1109/ACCESS.2020.3015705
Zaeemzadeh, A. (2017). Reliable Spectrum Hole Detection in Spectrum-Heterogeneous Mobile CRNs via Sequential Bayesian non-Parametric Clustering. MSc Thesis, University of Central Florida, Florida, US. Available at: https://stars.library.ucf.edu/cgi/viewcontent.cgi?article=6687&context=etd (accessed on 01/02/2025).
Zhang, C., Hu, Z., Guo, T.N., Qiu, R.C. and Currie, K. (2012). Cognitive Radio Network as Wireless Sensor Network (III): Passive target intrusion detection and experimental demonstration. IEEE Radar Conference, n/a(n/a), 0293–8. DOI: 10.1109/RADAR.2012.6212173
Zhang, Y. (2022). Machine Learning-Based Full-Duplex Communications and CRNs. PhD Thesis, King's College, London, UK.