Autors: Gotseva N., Vlahov, A. G., Poulkov, V. K., Manolova, A. H.
Title: ML-Driven Prediction of QoS in C-V2X Scenarios
Keywords: C-V2X, LGBM, Machine Learning, QoS prediction, throughput prediction, vehicular communications

Abstract: This paper explores the efficacy of a Light Gradient Boosting Machine (LGBM) model in predicting downlink throughput within a Cellular Vehicle-to-Everything (C-V2X) environment. Utilizing the Berlin V2X dataset, the model demonstrates high accuracy, achieving an R2 score of 97% and a mean absolute error (MAE) of approximately 3 Mbps. The study underscores the model's utility in enhancing vehicular communication systems by facilitating reliable quality-of-service (QoS) predictions. The model ensures efficient and effective throughput predictions by focusing on a minimal set of impactful network features and employing a simple supervised regression approach.

References

  1. T. Lohmar, A. Zaidi, H. Olofsson, et al., "Driving transformation in the automotive and road transport ecosystem with 5G, " Ericsson Technology Review, Sep. 2019.
  2. G. Fodor, H. Do, S. A. Ashraf, et al., "Supporting enhanced vehicle-T o-everything services by lte release 15 systems, " IEEE Communications Standards Magazine, vol. 3, no. 1, pp. 26-33, Mar. 2019
  3. 3GPP. (2015). Evolved universal terrestrial radio access(EUTRA) overall description. Technical Specification.TS 136300. Version 12.4.0. Sophia Antipolis Cedex-FRANCE
  4. K. Abboud, H. A. Omar, and W. Zhuang, "Interworking of DSRC and cellular network technologies for V2X communications: A survey, " IEEE Trans. Veh. Technol., vol. 65, no. 12, pp. 9457-9470, Dec. 2016.
  5. H. Ye, L. Liang, G. Y. Li, et al., "Machine learning for vehicular networks: Recent advances and application examples, " IEEE Vehicular Technology Magazine, vol. 13, no. 2, pp. 94-101, Jun. 2018.
  6. Reyhanoglu, A., Kar, E., Kumec, F., Kara, Y., Karaagac, S., Turan, B., & Coleri, S., 2023. Machine Learning Aided NR-V2X Quality of Service Predictions. 2023 IEEE Vehicular Networking Conference (VNC), pp. 183-186.
  7. Perdomo, J., Kousaridas, A., Zhou, C., & Monserrat, J., 2021. Deep Learning-based QoS Prediction with Innate Knowledge of the Ra-dio Access Network. 2021 IEEE Global Communications Conference (GLOBECOM), pp. 1-6.
  8. Reyhanoglu, A., Kar, E., Kumec, F., Kara, Y., Karaagac, S., Turan, B., & Coleri, S., 2023. Machine Learning Aided NR-V2X Quality of Service Predictions. 2023 IEEE Vehicular Networking Conference (VNC), pp. 183-186.
  9. R. Hernangómez et al., "Berlin V2X: A Machine Learning Dataset from Multiple Vehicles and Radio Access Technologies, " 2023 IEEE 97th Vehicular Technology Conference (VTC2023-Spring), Florence, Italy, 2023, pp. 1-5, doi: 10.1109/VTC2023-Spring57618.2023.10200750.
  10. Rodrigo Hernangomez, Philipp Geuer, Alexandros Palaios, Daniel Schaüfele, Cara Watermann, Khawla Taleb-Bouhemadi, Mohammad Parvini, Anton Krause, Sanket Partani, Christian Vielhaus, Martin Kas-parick, Daniel F. Külzer, Friedrich Burmeister, Frank H. P. Fitzek, Hans D.Schotten, Gerhard Fettweis, Slawomir Stanczak, December 8, 2022, &;Berlin V2X&, IEEE Dataport, doi: https://dx.doi.org/10.21227/8cj7-q373.
  11. https://towardsdatascience.com/a-quick-guide-T o-lightgbmlibrary-ef5385db8d10
  12. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., & Liu, T.Y. (2017). Lightgbm: A highly efficient gradient-boosting decision tree. Advances in neural information processing systems, 30.
  13. https://lightgbm.readthedocs.io/en/stable/
  14. Guolin Ke; Qi Meng; Thomas Finely; Taifeng Wang; Wei Chen; Weidong Ma; Qiwei Ye; Tie-Yan Liu (2017). "LightGBM: A Highly Efficient Gradient Boosting Decision Tree"

Issue

2024 59th International Scientific Conference on Information, Communication and Energy Systems and Technologies, ICEST 2024 - Proceedings, 2024, , https://doi.org/10.1109/ICEST62335.2024.10639683

Copyright IEEE

Вид: публикация в международен форум, публикация в реферирано издание, индексирана в Scopus и Web of Science