5G mobile communication technology can satisfy the needs of network quality of service (QoS) for vehicle-to-everything (V2X) in ideal conditions. However, complex intelligent transportation scenarios may lead to fluctuations in 5G QoS, resulting in passive and lagging degradation of the service level of V2X services. To address the challenge of aligning service requirements with network conditions, it is crucial to explore schemes for predicting and managing QoS fluctuations. This paper proposes a vehicle route planning scheme to improve the quality of experience for V2X services by QoS prediction based on probability distribution detection (PDD). We design a distribution detection algorithm to tackle the issue of improving QoS prediction accuracy by calculating probability confidence weights of the outcome of two different QoS prediction models. Simulation evaluations show that the proposed PDD-based prediction method significantly enhances the accuracy of predictions. We have achieved 0.128 mean absolute error, with 0.189 root mean square error, in predicting the network throughput. Furthermore, in comparison to the routes selected by the length-based route planning scheme, the proposed route planning strategy can enhance the network throughput by at least 5.3 kbps.

1. [1] 3GPP TS 22.186, “Enhancement of 3GPP support for V2X scenarios (Rel. 16),” 2019.
2. [2] China Mobile, “5G Vehicular Networking Demand and Technology White Paper,” 2021.
3. [3] 5GAA, “Making 5G Proactive and Predictive for the Automotive Industry,” 2019.
4. [4] 3GPP TS 23.288, “Architecture Enhancements for 5G System (5GS) to Support Network Data Analytics Services (Rel. 16),” 2020.
5. [5] A. Kousaridas, R. P. Manjunath, J. Perdomo, C. Zhou, E. Zielinski, S. Schmitz, and A. Pfadler, “QoS Prediction for 5G Connected and Automated Driving,” IEEE Communications Magazine, Vol.59, Issue 9, pp. 58-64, 2021. https://doi.org/10.1109/MCOM.110.2100042
6. [6] 3GPP TS 23.287, “Architecture enhancements for 5G System (5GS) to support Vehicle-to-Everything (V2X) services (Rel. 16),” 2019.
7. [7] D. F. Külzer, M. Kasparick, A. Palaios, R. Sattiraju, O. D. Ramos-Cantor, D. Wieruch, H. Tchouankem, F. Göttsch, P. Geuer, J. Schwardmann, G. Fettweis, H. D. Schotten, and S. Stańczak, “AI4Mobile: Use Cases and Challenges of AI-based QoS Prediction for High-Mobility Scenarios,” 2021 IEEE 93rd Vehicular Technology Conf. (VTC2021-Spring), 2021. https://doi.org/10.1109/VTC2021-Spring51267.2021.9449059
8. [8] R. Stevens, M. B. Abboud, M. Drissi, and S. Allio, “Real-time route planning based on network coverage for connected vehicles,” 2023 IEEE 97th Vehicular Technology Conf. (VTC2023-Spring), 2023. https://doi.org/10.1109/VTC2023-Spring57618.2023.10200415
9. [9] D. C. Moreira, I. M. Guerreiro, W. Sun, C. C. Cavalcante, and D. A. Sousa, “QoS Predictability in V2X Communication with Machine Learning,” 2020 IEEE 91st Vehicular Technology Conf. (VTC2020-Spring), 2020. https://doi.org/10.1109/VTC2020-Spring48590.2020.9129490
10. [10] D. Minovski, N. Ögren, K. Mitra, and C. Åhlund, “Throughput Prediction Using Machine Learning in LTE and 5G Networks,” IEEE Trans. on Mobile Computing, Vol.22, Issue 3, pp. 1825-1840, 2023. https://doi.org/10.1109/TMC.2021.3099397
11. [11] M. Saravanan, V. Rajagopalan, and D. Sachdeva, “Understanding Network Nodal Points for Emergency Services,” 2023 15th Int. Conf. on COMmunication Systems & NETworkS (COMSNETS), pp. 847-851, 2023. https://doi.org/10.1109/COMSNETS56262.2023.10041372
12. [12] A. Reyhanoglu, E. Kar, F. E. Kumec, Y. S. C. Kara, S. Karaagac, B. Turan, and S. Coleri, “Machine Learning Aided NR-V2X Quality of Service Predictions,” 2023 IEEE Vehicular Networking Conf. (VNC), pp. 183-186, 2023. https://doi.org/10.1109/VNC57357.2023.10136346
13. [13] P. Bardalai, H. Neog, P. E. Dutta, N. Medhi, and S. K. Deka, “Throughput Prediction in Smart Healthcare Network using Machine Learning Approaches,” 2022 IEEE 19th India Council Int. Conf. (INDICON), 2022. https://doi.org/10.1109/INDICON56171.2022.10040160
14. [14] S. Barmpounakis, L. Magoula, N. Koursioumpas, R. Khalili, J. M. Perdomo, and R. P. Manjunath, “LSTM-based QoS prediction for 5G-enabled Connected and Automated Mobility applications,” 2021 IEEE 4th 5G World Forum (5GWF), pp. 436-440, 2021. https://doi.org/10.1109/5GWF52925.2021.00083
15. [15] Y. Xu, Y. Shi, Y. Ge, S. Chen, and L. Wang, “Informer-based QoS prediction for V2X communication: A method with verification using reality field test data,” Computer Networks, Vol.235, Article No.109958, 2023. https://doi.org/10.1016/j.comnet.2023.109958
16. [16] S. Barmpounakis, N. Maroulis, N. Koursioumpas, A. Kousaridas, A. Kalamari, P. Kontopoulos, and N. Alonistioti, “AI-driven, QoS prediction for V2X communications in beyond 5G systems,” Computer Networks, Vol.217, Article No.109341, 2022. https://doi.org/10.1016/j.comnet.2022.109341
17. [17] M. Mhedhbi, S. Elayoubi, and G. Leconte, “AI-based prediction for ultra reliable low latency service performance in industrial environments,” 2022 18th Int. Conf. on Wireless and Mobile Computing, Networking and Communications (WiMob), pp. 130-135, 2022. https://doi.org/10.1109/WiMob55322.2022.9941706
18. [18] L. Magoula, N. Koursioumpas, S. Barmpounakis, P. Kontopoulos, M. A. Gutierrez-Estevez, R. Khalili, and A. Kousaridas, “A Deep Learning Approach for Distributed QoS Prediction in Beyond 5G Networks,” 2022 IEEE 33rd Annual Int. Symp. on Personal, Indoor and Mobile Radio Communications (PIMRC), pp. 1407-1412, 2022. https://doi.org/10.1109/PIMRC54779.2022.9977782
19. [19] W. Zhang, M. Feng, M. Krunz, and H. Volos, “Latency Prediction for Delay-sensitive V2X Applications in Mobile Cloud/Edge Computing Systems,” GLOBECOM 2020-2020 IEEE Global Communications Conf., 2020. https://doi.org/10.1109/GLOBECOM42002.2020.9348104
20. [20] M. A. Gutierrez-Estevez, Z. Utkovski, A. Kousaridas, and C. Zhou, “A Statistical Learning Framework for QoS Prediction in V2X,” 2021 IEEE 4th 5G World Forum (5GWF), pp. 441-446, 2021. https://doi.org/10.1109/5GWF52925.2021.00084
21. [21] Y. Liu, W. Zhang, J.-W. Wang, Y. Liu, and J. Peng, “Event-Triggered Feedback Control for Nonlinear Parabolic Distributed Parameter Systems with Time-Varying Delays,” IEEE Trans. on Automation Science and Engineering, pp. 1-14, 2024. https://doi.org/10.1109/TASE.2024.3418489
22. [22] Y. Liu, J.-W. Wang, Z. Wu, Z. Ren, and S. Xie, “Robust H_∞ Control for Semilinear Parabolic Distributed Parameter Systems with External Disturbances via Mobile Actuators and Sensors,” IEEE Trans. on Cybernetics, Vol.53, Issue 8, pp. 4880-4893, 2023. https://doi.org/10.1109/TCYB.2022.3150171
23. [23] J. Li and J. Lin, “A probability distribution detection based hybrid ensemble QoS prediction approach,” Information Sciences, Vol.519, pp. 289-305, 2020. https://doi.org/10.1016/j.ins.2020.01.046
24. [24] C. Lin, F. Dong, and K. Hirota, “Fuzzy Inference Based Vehicle to Vehicle Network Connectivity Model to Support Optimization Routing Protocol for Vehicular Ad-Hoc Network (VANET),” J. Adv. Comput. Intell. Intell. Inform., Vol.18, No.1, pp. 9-21, 2014. https://doi.org/10.20965/jaciii.2014.p0009
25. [25] A. Palaios, C. L. Vielhaus, D. F. Külzer, C. Watermann, R. Hernangómez, S. Partani, P. Geuer, A. Krause, R. Sattiraju, M. Kasparick, G. P. Fettweis, F. H. P. Fitzek, H. D. Schotten, and S. Stańczak, “Machine Learning for QoS Prediction in Vehicular Communication: Challenges and Solution Approaches,” IEEE Access, Vol.11, pp. 92459-92477, 2023. https://doi.org/10.1109/ACCESS.2023.3303528
26. [26] G. Nardini, A. Noferi, P. Ducange, and G. Stea, “Exploiting Simu5G for Generating Datasets for Training and Testing AI Models for 5G/6G Network Applications,” SoftwareX, Vol.21, Article No.101320, 2023. https://doi.org/10.1016/j.softx.2023.101320
27. [27] G. Nardini, D. Sabella, G. Stea, P. Thakkar, and A. Virdis, “Simu5GAn OMNeT++ Library for End-to-End Performance Evaluation of 5G Networks,” IEEE Access, Vol.8, pp. 181176-181191, 2020. https://doi.org/10.1109/ACCESS.2020.3028550