A Reinforcement Q-Learning-based Resource Sharing Mechanism for V2X slicing Networks

DOI

10.2991/978-94-6463-496-9_23How to use a DOI?

Keywords

Deep reinforcement leaning; Resource sharing; V2X; Networks slicing; 5G

Abstract

Network slicing has emerged as a transformative technology, offering the possibility of coexisting with multiple services with different Quality of Service (QoS) requirements within the same infrastructure. The main challenge of vehicle-to-everything (V2X) network slicing lies in developing an effective resource management approach. This approach should provide an adequate balance between optimizing the use of resources and maintaining isolation between slices. One of the benchmark approaches used in the network slicing environment is strict slicing, which allocates a fixed proportion of the whole resource pool to each slice throughout its lifetime. However, one of the limitations of this approach is the inefficiency of resource utilization, as each slice may not utilize its resources 100% during its lifetime. In this paper, we propose a flexible resource sharing mechanism based on deep reinforcement Qlearning (QDRL-based resource sharing). This mechanism triggers sharing between slices when there is an overloaded slice in the system while maintaining high isolation. Experimental results show that our solution is effective in terms of improving resource utilization and minimizing the blocking probability of new calls and the handover dropping probability.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Anas Nawfel Saidi
AU  - Mohamed Lehsaini
PY  - 2024
DA  - 2024/08/31
TI  - A Reinforcement Q-Learning-based Resource Sharing Mechanism for V2X slicing Networks
BT  - Proceedings of the International Conference on Emerging Intelligent Systems for Sustainable Development (ICEIS 2024)
PB  - Atlantis Press
SP  - 298
EP  - 312
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-496-9_23
DO  - 10.2991/978-94-6463-496-9_23
ID  - Saidi2024
ER  -