METHOD FOR IMPROVING THE TRANSMISSION EFFICIENCY OF WI-FI AND LTEU NETWORKS USING ML ALGORITHMS

Abstract

The article considers the problem of adaptive LTE access in unlicensed
spectrum, taking into account coexistence with Wi-Fi, regulatory restrictions, and limited resources of edge
devices. A working architecture is proposed that combines lightweight convolutional neural networks for
radio signal classification and detection, recurrent models for short-term channel load prediction, and
reinforcement learning algorithms for channel selection, TXOP, and shutdown patterns. The proposed
approach optimizes LTE throughput while maintaining fairness to Wi-Fi, minimizing overhead and raw
data transmission through lightweight models and federated strategies. Evaluation criteria are provided,
experimental scenarios are described, and advantages over static methods are justified. The proposed
approach combines observation, prediction, and control methods into a single working architecture that
provides a practical opportunity to improve LTE spectral efficiency in the unlicensed band while
maintaining fairness criteria with respect to Wi-Fi.
Keywords: Wi-Fi, LTE, unlicensed spectrum, CNN, machine learning, RL-LSTM, Q-learning

References
1. License assisted access-WiFi coexistence with TXOP backoff for LTE in unlicensed band / S.
Saadat et al. China Communications. 2017. Vol. 14, no. 3. P. 1–14. URL:
https://doi.org/10.1109/cc.2017.7897317.
2. Alhulayil M., Lopez-Benitez M. LTE/Wi-Fi Coexistence in Unlicensed Bands Based on
Dynamic Transmission Opportunity. 2020 IEEE Wireless Communications and Networking
Conference Workshops (WCNCW), Seoul, Korea (South), 6–9 April 2020. 2020. URL:
https://doi.org/10.1109/wcncw48565.2020.9124747.
3. Machine Learning Enabled Spectrum Sharing in Dense LTE-U/Wi-Fi Coexistence Scenarios
/ A. Dziedzic et al. IEEE Open Journal of Vehicular Technology. 2020. Vol. 1. P. 173–189. URL:
https://doi.org/10.1109/ojvt.2020.2981519.
4. An Alytical Study Of Cellular Networks LTE-U and Wi-Fi in 5G Environment. Lahore
Garrison University Research Journal of Computer Science and Information Technology. 2024. P.
17–31. URL: https://doi.org/10.54692/lgurjcsit.2024.083503.
5. Ahmad O., Farooq B. Auxiliary-LSTM based floor-level occupancy prediction using Wi-Fi
access point logs. Journal of Smart Cities and Society. 2022. Vol. 1, no. 3. P. 195–211. URL:
https://doi.org/10.3233/scs-220012.
6. A Q-Learning Scheme for Fair Coexistence Between LTE and Wi-Fi in Unlicensed Spectrum
/ V. Maglogiannis et al. IEEE Access. 2018. Vol. 6. P. 27278–27293. URL:
https://doi.org/10.1109/access.2018.2829492.
7. Dynamic Spectrum Coexistence of NR-V2X and Wi-Fi 6E using Deep Reinforcement
Learning / K. D. Shah et al. IEEE Open Journal of the Computer Society. 2025. P. 1–12. URL:
https://doi.org/10.1109/ojcs.2025.3586664.
8. Wi-Fi Coexistence with Duty Cycled LTE-U / Y. Pang et al. Wireless Communications and
Mobile Computing. 2017. Vol. 2017. P. 1–10. URL: https://doi.org/10.1155/2017/6486380.
9. RL-Based Energy-Efficient Data Transmission Over Hybrid BLE/LTE/Wi-Fi/LoRa UAVAssisted Wireless Network / W. A. Nelson et al. IEEE/ACM Transactions on Networking. 2023. P.
1–16. URL: https://doi.org/10.1109/tnet.2023.3332296.
10. He L., Cheng H., Zhang Y. Centralized and Decentralized Event-Triggered Nash EquilibriumSeeking Strategies for Heterogeneous Multi-Agent Systems. Mathematics. 2025. Vol. 13, no. 3. P.
419. URL: https://doi.org/10.3390/math13030419.
11. Ali R., Almagrabi A. O. Beyond Wi-Fi 7: Enhanced Decentralized Wireless Local Area
Networks with Federated Reinforcement Learning. Computers, Materials & Continua. 2025. P. 1–10.
URL: https://doi.org/10.32604/cmc.2025.070224.
12. Reinforcement Learning for Efficient and Fair Coexistence Between LTE-LAA and Wi-Fi /
M. Han et al. IEEE Transactions on Vehicular Technology. 2020. Vol. 69, no. 8. P. 8764–8776. URL:
https://doi.org/10.1109/tvt.2020.2994525.
13. Basnet M. B. Predicting Channel Quality Indicator (CQI) in LTE Using Ensemble Learning
Approaches. Divya Gyan Journal of Business and Computing. 2026. Vol. 1, no. 1. P. 55–72. URL:
https://doi.org/10.3126/dgjbc.v1i1.91087.
14. Muthirayan D., Kalathil D., Khargonekar P. P. Meta-Learning Online Control for Linear
Dynamical Systems. IEEE Transactions on Automatic Control. 2025. P. 1–7. URL:
https://doi.org/10.1109/tac.2025.3536839.