A Deep Learning Assisted Heuristic Algorithm to Solve Handover Problem in Heterogeneous RF-VLC Network

Alizadeh Ghazijahani, Hamed; Mofarreh, Mohammad

doi:10.30473/jphys.2025.74713.1242

Document Type : Research

Authors

¹ Assistant Professor, Department of Electrical Engineering, Azarbaijan Shahid Madani University, Tabriz, Iran.

² Assistant Professor, Department of Electrical Engineering, University of Bonab, Bonab, Iran

https://doi.org/10.30473/jphys.2025.74713.1242

Abstract

In heterogeneous networks that Radio Frequency (RF) communication technologies and Visible Light Communication (VLC) operate integrately, the handover process is critical for maintaining connectivity and Quality-of-Service (QoS) in dynamic indoor environments. This paper proposes a novel deep learning assisted heuristic algorithm (DLHA) that predicts, optimizes, and executes handover decisions in an RF-VLC integrated network. By leveraging a gated recurrent unit (GRU)-based deep neural network (DNN) to forecast channel conditions and user mobility, and coupling these predictions with a heuristic decision framework. The algorithm aims to minimize handover latency, reduces packet loss, and balances network load. The problem is further refined using optimization principles and Markov decision processes (MDPs). Simulation results, validated on realistic indoor channel models and mobility scenarios, demonstrate that the proposed DLHA significantly outperforms conventional threshold-based methods.

Keywords

References

[1] Bravo Alvarez, L., Montejo-Sánchez, S., Rodríguez-López, L., Azurdia-Meza, C., & Saavedra, G. (2023). A review of hybrid vlc/rf networks: Features, applications, and future directions. Sensors, 23(17), 7545.

[2] Abuella, H., Elamassie, M., Uysal, M., Xu, Z., Serpedin, E., Qaraqe, K. A., & Ekin, S. (2021). Hybrid RF/VLC systems: A comprehensive survey on network topologies, performance analyses, applications, and future directions. IEEE Access, 9, 160402-160436.

[3] Ciftler, B. S., Alwarafy, A., & Abdallah, M. (2021). Distributed DRL-based downlink power allocation for hybrid RF/VLC networks. IEEE Photonics Journal, 14(3), 1-10.

[4] Ghazijahani, H. A., Abdollahzadeh, M., Seyedarabi, H., & Niya, M. J. M. (2016, September). Adaptive CSK modulation guaranteeing HEVC video quality over visible light communication network. In 2016 8th International symposium on telecommunications (IST) (pp. 789-794). IEEE.

[5] Arshad, R., & Lampe, L. (2021). Stochastic geometry analysis of user mobility in RF/VLC hybrid networks. IEEE Transactions on Wireless Communications, 20(11), 7404-7419.

[6] Kong, J., Ismail, M., Serpedin, E., & Qaraqe, K. A. (2019). Energy efficient optimization of base station intensities for hybrid RF/VLC networks. IEEE Transactions on Wireless Communications, 18(8), 4171-4183.

[7] Abuella, H., Elamassie, M., Uysal, M., Xu, Z., Serpedin, E., Qaraqe, K. A., & Ekin, S. (2021). Hybrid RF/VLC systems: A comprehensive survey on network topologies, performance analyses, applications, and future directions. IEEE Access, 9, 160402-160436.

[8] Mofarreh-Bonab, M., Seyedarabi, H., Mozaffari Tazehkand, B., & Kasaei, S. (2022). 3D hand pose estimation using RGBD images and hybrid deep learning networks. The Visual Computer, 1-10.

[9] Shao, S., Khan, Z., Liu, G., Khreishah, A., Ayyash, M., Elgala, H., ... & Rahaim, M. (2019, April). Optimizing handover parameters by Q-learning for heterogeneous RF-VLC networks. In IEEE INFOCOM 2019-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) (pp. 1069-1070). IEEE.

[10] Ghazijahani, H. A., Seyedarabi, H., Niya, J. M., & Cheung, N. M. (2019). Deep learning-assisted adaptive modulation level assignment for video communication over an elastic optical network. Optical Fiber Technology, 52, 101987.

[11] Hu, Q., Gan, C., Liu, X., Gong, G., & Zhu, Y. (2023). Dynamic handover cost modeling in hybrid VLC/RF networks. Ad Hoc Networks, 146, 103174.

[12] Feng, R., Guo, Y., Zain Yousaf, M., Khan, B., & Luo, L. (2025). Coverage analysis and handover strategy in RF/VLC heterogeneous networks. Applied Optics, 64(15), 4160-4173.

[13] Maimaiti, S., Huang, S., Zhang, K., Liu, X., Xu, Z., & Mi, J. (2025). Collaborative Online Learning-Based Distributed Handover Scheme in Hybrid VLC/RF 5G Systems. Electronics, 14(6), 1142.

[14] Sathisha, R. N., Ahmed, F., & Raghunathan, V. (2023, January). Demonstration of RF-VLC hand-over using receiver side channel selection. In 2023 15th International Conference on COMmunication Systems & NETworkS (COMSNETS) (pp. 382-386). IEEE.

[15] Zeshan, A., & Baykas, T. (2021). Location aware vertical handover in a VLC/WLAN hybrid network. IEEE Access, 9, 129810-129819.

[16] Guler, N. (2024). Vertical Handover-Based Hybrid Radio Frequency/Visible Light Communication Scheme for e-Health Applications (VHO-HeA). Engineered Science, 33, 1252.

[17] Narmanlioglu, O., & Uysal, M. (2021). Event-triggered adaptive handover for centralized hybrid VLC/MMW networks. IEEE Transactions on Communications, 70(1), 455-468.

Quarterly Journal of Optoelectronic

A Deep Learning Assisted Heuristic Algorithm to Solve Handover Problem in Heterogeneous RF-VLC Network

References

References

Volume 8, Issue 1 - Serial Number 22
September 2025
Pages 39-48

A Deep Learning Assisted Heuristic Algorithm to Solve Handover Problem in Heterogeneous RF-VLC Network

References

References

Volume 8, Issue 1 - Serial Number 22September 2025Pages 39-48

Volume 8, Issue 1 - Serial Number 22
September 2025
Pages 39-48