Hybrid FSO/RF Networks with Neural Prediction of RSSI and Weather

Zuzana Liščinská; L’uboš Ovseník; Jakub Oravec

doi:10.2478/aei-2025-0015

Abstract

This paper investigates neural network models for predicting weather parameters and received signal strength indicator (RSSI) to enable adaptive handover in hybrid free space optics (FSO)/radio frequency (RF) systems. The most correlated parameters were visibility, temperature (measured from three independent sensors), and particle concentration. The work was exclusively focused on predicting correlated atmospheric effects and subsequently predicting RSSI parameter derived from them using a long short-term memory (LSTM) model, minute by minute over 24 hours. The predicted values can in the future serve as input for initiating handover decisions – for example, through visualization in Simulink. The threshold value of -30 dBm was taken from peer-reviewed articles and is used as a reference limit for link quality.

References

SONG, S. – LIU, Y. – XU, T. – GUO, L.: Hybrid FSO/RF System Using Intelligent Power Control and Link Switching, IEEE Photonics Technology Letters 33 (2021) DOI: 10.1109/LPT.2021.3076467
Search in Google Scholar Back to article
PASSANT, H. M. – EL-SHIMY, M. A. – SHALABY, H. M. H. – KHEIRALLAH, H. N.: Hybrid FSO/RF system over proposed random dust attenuation model based on real-time data combined with G – G atmospheric turbulence, Optics Communications 549 (2023) DOI: 10.1016/j.optcom.2023.129891
Search in Google Scholar Back to article
KHALID, H. – SAJID, S. M. – NISTAZAKIS, H. E. – TOMBRAS, G. S.: Performance Analysis of Hard-Switching Based Hybrid FSO/RF System over Turbulence Channels, Computation 7, No.28 (2019) DOI: 10.3390/computation7020028
Search in Google Scholar Back to article
MOHSAN, S. A. H. – KHAN, M. A. – AMJAD, H.: Hybrid FSO/RF networks: A review of practical constraints, applications and challenges, Optical Switching and Networking 47 (2023) DOI: 10.1016/j.osn.2022.100697
Search in Google Scholar Back to article
LAPČAK, M. – OVSENÍK, L. – ORAVEC, J. – ZDRAVECKÝ, N.: Design of hard switching for FSO/RF hybrid system based on prediction of RSSI parameter and environmental conditions, 2022 32nd International Conference Radioelektronika (RADIOELEKTRONIKA (2022) DOI: 10.1109/RADIOELEKTRONIKA54537.2022.9764908
Search in Google Scholar Back to article
SHAO, J. – LIU, Y. – DU, X. – XIE, T.: Adaptive Modulation Scheme for Soft-Switching Hybrid FSO/RF Links Based on Machine Learning, Photonics 11, No.404 (2024) DOI: 10.3390/photonics11050404
Search in Google Scholar Back to article
SEDGWICK, P.: Pearson ’ s correlation coefficient, BMJ 345 (2012) DOI: 10.1136/bmj.e4483
Search in Google Scholar Back to article
LIŠČINSKÁ, Z.: Use of neural networks for line switching in hybrid FSO/RF systems, Electrical Engineering and Informatics 15 (2024) https://eei.fei.tuke.sk/wp-content/uploads/2024/07/EEI_15.pdf accessed: June 15, 2025
Search in Google Scholar Back to article
SMITH, E. M. – SMITH, J. – LEGG, P. – FRANCIS, S.: Predicting the Occurrence of World News Events Using Recurrent Neural Networks and Auto-Regressive Moving Average Models, Advances in Computational Intelligence Systems 650 (2018) DOI: 10.1007/978-3-319-66939-7_16
Search in Google Scholar Back to article
ISTIAKE SUNNY, Md. A. – MASWOOD, M. M. S. – ALHARBI, A. G.: Deep Learning-Based Stock Price Prediction Using LSTM and Bi-Directional LSTM Model, Medium (2020) DOI: 10.1109/NILES50944.2020.9257950
Search in Google Scholar Back to article

Hybrid FSO/RF Networks with Neural Prediction of RSSI and Weather

Abstract

Paradigm

My account