Handover in 5G Aerial Networks: A Solution Based on Reinforcement Learning

• Maria Barbosa UFPE
• Marcelo Batista UFPE
• Anderson Queiroz UFPE
• David Cavalcanti UFPE
• Kelvin Dias UFPE

DOI: https://doi.org/10.5753/semish.2024.3152

Abstract

Unmanned Aerial Vehicles (UAV) as Base Stations, serving ground users, has been gaining momentum with the new 5G releases and in future 6G systems. Providing ubiquitous connectivity in remote, underserved, or rural areas. However, ensuring service continuity in UAV networks, especially during handover, is more challenging than in ground cellular networks. This is due to the smaller network coverage, increasing the risk of the ping-pong effect. Therefore, this article proposes a solution based on reinforcement learning, which utilizes user mobility and network contexts. The results indicate the effectiveness of the proposal, with a 74% reduction in handover failures compared to state-of-the-art solutions.

References

Alsoliman, A., Rigoni, G., Levorato, M., Pinotti, C., Tippenhauer, N. O., and Conti, M. (2021). Cots drone detection using video streaming characteristics. In Proceedings of the 22nd International Conference on Distributed Computing and Networking.

Aydin, Y., Kurt, G. K., Ozdemir, E., and Yanikomeroglu, H. (2021). Group handover for drone base stations. IEEE Internet of Things Journal, 8(18):13876–13887.

Derhab, A., Cheikhrouhou, O., Allouch, A., Koubaa, A., Qureshi, B., Ferrag, M. A., Maglaras, L., and Khan, F. A. (2023). Internet of drones security: Taxonomies, open issues, and future directions. in Vehicular Communications.

Gangula, R., Esrafilian, O., Gesbert, D., Roux, C., Kaltenberger, F., and Knopp, R. (2018). Flying rebots: First results on an autonomous uav-based lte relay using open airinterface. IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications.

Hasselt, H. v., Guez, A., and Silver, D. (2016). Deep reinforcement learning with double q-learning. In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, AAAI’16, page 2094–2100. AAAI Press.

Hu, H., Yang, L., and Wang, S. (2019). A trajectory prediction based intelligent handover control method in UAV cellular networks. China Communications, 16(1):1–14.

Jang, Y., Raza, S. M., Kim, M., and Choo, H. (2022). Proactive handover decision for uavs with deep reinforcement learning. Sensors, 22(3).

Lin, X. (2022). An overview of 5g advanced evolution in 3gpp release 18. IEEE Communications Standards Magazine, 6(3):77–83.

Mishra, D. and Natalizio, E. (2020). A survey on cellular-connected uavs: Design challenges, enabling 5g/b5g innovations, and experimental advancements. Computer Networks.

Muruganathan, S. D., Lin, X., Määttänen, H.-L., Sedin, J., Zou, Z., Hapsari, W. A., and Yasukawa, S. (2021). An overview of 3gpp release-15 study on enhanced lte support for connected drones. IEEE Communications Standards Magazine, 5(4):140–146.

Queiroz, A., Barbosa, M. K., and Dias, K. (2023). Aero5gbs—deep learning-empowered ground users handover in aerial 5g and beyond systems. IEEE Access.

Tafintsev, N., Chiumento, A., Vikhrova, O., Valkama, M., and Andreev, S. (2023). Utilization of uavs as flying base stations in urban environments. In 2023 15th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops.

Yang, H., Hu, B., and Wang, L. (2017). A deep learning based handover mechanism for UAV networks. In 2017 20th International Symposium on Wireless Personal Multimedia Communications (WPMC). IEEE.