LEO UYDU AĞLARINDA BULANIK SİNİR AĞI TABANLI DEVİR ALGORİTMASININ PERFORMANS ANALİZİ

Abstract

Alçak Dünya Yörüngesi (LEO) uydu ağları, 5G ve ötesi ile 6G haberleşme sistemleri için küresel kapsama sağlama potansiyeline sahiptir. Ancak bu teknolojiler beraberinde uyduların yüksek hızı nedeniyle uydular arasında yoğun devir (handover) zorunluluğunu da ortaya çıkarmaktadır. Geleneksel Alınan Sinyal Gücü Göstergesi (RSSI) tabanlı handover yaklaşımı, bu dinamik yapıda gereksiz handover durumlarına ve ping-pong etkisine yol açarak kullanıcıların Hizmet Kalitesini (QoS) düşürebilmektedir. Bu çalışmada, LEO uydu ağları için Bulanık Sinir Ağı tabanlı bir handover algoritması önerilmiştir. Starlink yörünge parametreleri ile gerçekleştirilen benzetimler aracılığıyla, önerilen Bulanık Sinir Ağı (FNN) modeli, RSSI ve Bulanık Mantık (FL) tabanlı handover yöntemleriyle karşılaştırılmıştır. Benzetim sonucu elde edilen bulgular göre, önerilen FNN tabanlı handover algoritması literatürde önerilen FL tabanlı yaklaşıma göre %51,7, geleneksel RSSI yöntemine göre ise %71,8 böoranında handover sayısını azalttığı tespit edilmiştir. Ayrıca, önerilen yaklaşım ağ kararlılığını artırmanın yanı sıra, ortalama veri hızını da 3269,7 Mbps seviyesine yükselterek handover-QoS ödünleşimi açısından dengeli bir performans sergilemiştir.

Keywords

• LEO Uydu Ağları
• Handover Yönetimi
• FNN
• Ping-Pong

Fuzzy Neural Network based Handover Algorithms in LEO Satellite Networks

Abstract

Low Earth Orbit (LEO) satellite networks have the potential to provide global coverage for 5G and beyond and 6G communication systems. However, these technologies also introduce the necessity of frequent handovers between satellites due to their high orbital velocity. In this dynamic structure, the conventional Received Signal Strength Indicator (RSSI)-based handover approach may lead to unnecessary handovers and the ping-pong effect, thereby reducing users’ Quality of Service (QoS). In this study, a Fuzzy Neural Network-based handover algorithm is proposed for LEO satellite networks. Through simulations conducted using Starlink orbital parameters, the proposed Fuzzy Neural Network (FNN) model was compared with RSSI- and Fuzzy Logic (FL)-based handover methods. According to the simulation findings, it was determined that the proposed FNN-based handover algorithm reduced the number of handovers by 51.7% compared to the FL-based approach proposed in the literature and by 71.8% compared to the conventional RSSI method. In addition, the proposed approach not only improved network stability but also exhibited a balanced performance in terms of the handover–QoS trade-off by increasing the average data rate to 3269.7 Mbps.

Keywords

• LEO Satellite Networks
• Handover Management
• FNN
• Ping-Pong

References

1. Adewale, A. A., Ekong, E. E., Ibikunle, F. A., Orimogunje, A., & Abolade, J. (2019). Ping-pong reduction for handover process using adaptive hysteresis margin: A methodological approach. IOP Conference Series: Materials Science and Engineering, 640(1). https://doi.org/10.1088/1757-899X/640/1/012118
2. Bishop, C. M. (2006). Pattern recognition and machine learning (Information Science and Statistics). Springer.
3. Cakaj, S. (2021). The Parameters Comparison of the “Starlink” LEO Satellites Constellation for Different Orbital Shells. Frontiers in Communications and Networks, 2. https://doi.org/10.3389/frcmn.2021.643095
4. CelesTrak. Starlink NORAD general perturbations (GP) element sets. https://celestrak.org/NORAD/elements/?utm_source
5. Chowdhury, P. K., Atiquzzaman, M., & Ivancic, W. (2007). Handover Schemes in Satellite Networks: State-of-the-Art and Future Research Directions.
6. Friis, H. T. (1946). A note on a simple transmission formula. proc. IRE, 34(5), 254-256.
7. Gao, Y., Yang, H., Wang, X., Chen, Y., Li, C., & Zhang, X. (2022). A Fuzzy-Logic-Based Load Balancing Scheme for a Satellite–Terrestrial Integrated Network. Electronics (Switzerland), 11(17). https://doi.org/10.3390/electronics11172752
8. Gkizeli, M., Tafazolli, R., & Evans, B. (2001). Modeling Handover in Mobile Satellite Diversity Based Systems.

9. Hozayen, M., Darwish, T., Karabulut Kurt, G., & Yanikomeroglu, H. (2022). A Graph-Based Customizable Handover Framework for LEO Satellite Networks. Proceedings of the 2022 IEEE Globecom Workshops (GC Wkshps), 868-873. https://doi.org/10.1109/GCWkshps56602.2022.10008514
10. Jiang, W., Zhan, Y., & Fang, X. (2025). Fuzzy neural network based access selection in satellite–terrestrial integrated networks. Journal of Network and Computer Applications, 236. https://doi.org/10.1016/j.jnca.2025.104108
11. Karapantazis, S., & Pavlidou, F. N. (2006). QoS handover management for multimedia LEO satellite networks. Telecommunication Systems, 32(4), 225-245. https://doi.org/10.1007/s11235-006-9000-6
12. Kaur, H., & Kaur, E. A. (2014). Fuzzy Logic Based Handover Decision Procedure Involving Multiple Matrices. International Journal of Advanced Engineering Research and Science (IJAERS), 1(1).
13. Kiamouche, W., & Benslama, M. (2008). Fuzzy Decision Priority Scheme for Handovers In Low Earth Orbit Mobile Satellite Networks.
14. Lagunas, E., Chatzinotas, S., & Ottersten, B. E. (2024). Low-Earth orbit satellite constellations for global communication network connectivity. Nature Reviews Electrical Engineering, 1, 656-665. https://api.semanticscholar.org/CorpusID:272671561
15. Lee, J. W., Lim, B., Kim, K. H., Lee, J. M., Ha, Y. S., Han, Y. J., & Ko, Y. C. (2025). Handover strategy for LEO satellite communication using graph neural network. ICT Express, 11(2), 239-244. https://doi.org/10.1016/j.icte.2025.01.009
16. Leng, T., Xu, Y., Cui, G., & Wang, W. (2021). Caching-aware intelligent handover strategy for leo satellite networks. Remote Sensing, 13(11). https://doi.org/10.3390/rs13112230
17. Li, N., Gong, B., & Deng, Z. (2017). A handoff algorithm based on parallel fuzzy neural network in mobile satellite networks. Journal of Communications, 12(7), 395-404. https://doi.org/10.12720/jcm.12.7.395-404
18. Liu, S., Gao, Z., Wu, Y., Kwan Ng, D. W., Gao, X., Wong, K. K., Chatzinotas, S., & Ottersten, B. (2021). LEO Satellite Constellations for 5G and Beyond: How Will They Reshape Vertical Domains? IEEE Communications Magazine, 59(7), 30-36. https://doi.org/10.1109/MCOM.001.2001081
19. Promwong, S., Takada, J., Supanakoon, P., & Tangtisanon, P. (2004). Path loss and matched filter gain of free space and ground reflection channels for UWB radio systems. 2004 IEEE Region 10 Conference TENCON 2004., C, 125-128 Vol. 3. https://doi.org/10.1109/TENCON.2004.1414723
20. Ross, T. J. (2005). Fuzzy logic with engineering applications. John Wiley & Sons.
21. Sorour, S., Valaee, S., & Alagha, N. (2010). Joint control of delay and packet drop rate in satellite systems using network coding. 2010 5th Advanced Satellite Multimedia Systems Conference and the 11th Signal Processing for Space Communications Workshop, 46-53.
22. Takagi, T., & Sugeno, M. (1985). Fuzzy identification of systems and its applications to modeling and control. IEEE transactions on systems, man, and cybernetics, (1), 116-132.
23. Tan, Y., Li, J., Wonders, M., Chao, F., Shum, H. P. H., & Yang, L. (2016). Towards sparse rule base generation for fuzzy rule interpolation. 2016 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 110-117. https://doi.org/10.1109/FUZZ-IEEE.2016.7737675
24. Tan, Y., Shum, H. P. H., Chao, F., Vijayakumar, V., & Yang, L. (2019). Curvature-Based Sparse Rule Base Generation for Fuzzy Rule Interpolation. Journal of Intelligent and Fuzzy Systems, 36(5), 4201-4214. https://doi.org/10.3233/JIFS-169978
25. The MathWorks Inc. (2024). MATLAB (R2024a), Version 24.1. The MathWorks, Inc. https://www.mathworks.com/products/matlab.html
26. Wicker, T. (2025). Winsorizing and Trimming with Subgroups.
27. Wu, J., Su, S., Wang, X., Zhang, J., & Gao, Y. (2024). Accelerating Handover in Mobile Satellite Network. http://arxiv.org/abs/2403.11502
28. Wu, J., Su, S., Zhu, W., Wang, X., Zhang, J., He, X., & Gao, Y. (2025). PHandover: Parallel Handover in Mobile Satellite Network. http://arxiv.org/abs/2507.07437
29. Xie, H., Zhan, Y., Zeng, G., & Pan, X. (2021). LEO Mega-Constellations for 6G Global Coverage: Challenges and Opportunities. IEEE Access, 9, 164223-164244. https://doi.org/10.1109/ACCESS.2021.3133301
30. YIN, Z., CHEN, Q., YANG, L., ZHAO, Y., & CHEN, X. (2025). Routing cost-integrated intelligent handover strategy for multi-layer LEO mega-constellation networks. Chinese Journal of Aeronautics, 38(6). https://doi.org/10.1016/j.cja.2024.09.039
31. Yu, H., Gao, W., & Zhang, K. (2024). A Graph Reinforcement Learning-Based Handover Strategy for Low Earth Orbit Satellites under Power Grid Scenarios. Aerospace, 11(7). https://doi.org/10.3390/aerospace11070511
32. Zadeh, L. A. (1965). Fuzzy sets. Information and Control, 8(3), 338-353. https://doi.org/https://doi.org/10.1016/S0019-9958(65)90241-X