Priority-Aware Multi-Agent Deep Reinforcement Learning for Resource Scheduling in C-V2X Mode 4 Communication
The need for vehicular networks with exceptional levels of reliability and negligible delay in communication, especially with the ongoing 5G and the upcoming generation of 6G systems, has given rise to Cellular-Vehicle-to-Anything C-V2X systems. This paper proposes a novel framework of Priority-Awar...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11072434/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839614762864869376 |
|---|---|
| author | Ahmed Thair Shakir Barbara M. Masini Nemer Radhwan Khudhair Rosdiadee Nordin Angela Amphawan |
| author_facet | Ahmed Thair Shakir Barbara M. Masini Nemer Radhwan Khudhair Rosdiadee Nordin Angela Amphawan |
| author_sort | Ahmed Thair Shakir |
| collection | DOAJ |
| description | The need for vehicular networks with exceptional levels of reliability and negligible delay in communication, especially with the ongoing 5G and the upcoming generation of 6G systems, has given rise to Cellular-Vehicle-to-Anything C-V2X systems. This paper proposes a novel framework of Priority-Aware Multi-Agent Deep Reinforcement Learning (PA-MADRL) to address with issues such as high interference, dynamic allocation of critical signals, resource contention in density traffic, dynamic fading, and safety-critical message ratio. This approach is aimed at the development of an effective and adaptive resource allocation mechanism that will improve the likelihood of transmission of safety critical signals and improve overall network performance in metropolitan areas. PA-MADRL allows autonomous vehicles to efficiently allocate resources despite varied congestion along with interference conditions by combining centralized training for global optimization and decentralized execution for scalable decision-making. PA-MADRL is derived from the concept of optimal global allocation of resources in central training and intelligent instantaneous distribution in decentralized setting. Several tests carried out at different levels of interference and traffic densities demonstrate that PA-MADRL improves throughput by 35%, lowers latency by 40% and increases Packet Delivery Ratio (PDR) by nearly 50%, especially when the traffic density increases. These results show that PA-MADRL has the capability to adaptively work in dense vehicular networks with low communication overhead. Ultimately, the framework enhances safety in autonomous transportation by facilitating the timely delivery of critical messages, thus contributing to sustainable and intelligent transportation systems as part of next-generation smart cities. |
| format | Article |
| id | doaj-art-dcd02a0e98f8497b8dcb7f6e9c859b39 |
| institution | Matheson Library |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-dcd02a0e98f8497b8dcb7f6e9c859b392025-07-25T23:00:59ZengIEEEIEEE Access2169-35362025-01-011312902412903910.1109/ACCESS.2025.358680411072434Priority-Aware Multi-Agent Deep Reinforcement Learning for Resource Scheduling in C-V2X Mode 4 CommunicationAhmed Thair Shakir0https://orcid.org/0000-0002-6636-0194Barbara M. Masini1https://orcid.org/0000-0002-1094-1985Nemer Radhwan Khudhair2https://orcid.org/0009-0008-7486-4633Rosdiadee Nordin3https://orcid.org/0000-0001-9254-2023Angela Amphawan4https://orcid.org/0000-0003-2838-8679Department of Medical Physics, College of Applied Sciences, University of Anbar, Ramadi, IraqNational Research Council (CNR), Institute of Electronics, Computer and Telecommunication Engineering (IEIIT), Bologna, ItalyDepartment of Chemical Engineering, College of Engineering, University of Baghdad, Baghdad, IraqDepartment of Computing and Information Systems, School of Engineering, Sunway University, Petaling Jaya, MalaysiaSmart Photonics Research Laboratory, Faculty of Engineering and Technology, Sunway University, Petaling Jaya, MalaysiaThe need for vehicular networks with exceptional levels of reliability and negligible delay in communication, especially with the ongoing 5G and the upcoming generation of 6G systems, has given rise to Cellular-Vehicle-to-Anything C-V2X systems. This paper proposes a novel framework of Priority-Aware Multi-Agent Deep Reinforcement Learning (PA-MADRL) to address with issues such as high interference, dynamic allocation of critical signals, resource contention in density traffic, dynamic fading, and safety-critical message ratio. This approach is aimed at the development of an effective and adaptive resource allocation mechanism that will improve the likelihood of transmission of safety critical signals and improve overall network performance in metropolitan areas. PA-MADRL allows autonomous vehicles to efficiently allocate resources despite varied congestion along with interference conditions by combining centralized training for global optimization and decentralized execution for scalable decision-making. PA-MADRL is derived from the concept of optimal global allocation of resources in central training and intelligent instantaneous distribution in decentralized setting. Several tests carried out at different levels of interference and traffic densities demonstrate that PA-MADRL improves throughput by 35%, lowers latency by 40% and increases Packet Delivery Ratio (PDR) by nearly 50%, especially when the traffic density increases. These results show that PA-MADRL has the capability to adaptively work in dense vehicular networks with low communication overhead. Ultimately, the framework enhances safety in autonomous transportation by facilitating the timely delivery of critical messages, thus contributing to sustainable and intelligent transportation systems as part of next-generation smart cities.https://ieeexplore.ieee.org/document/11072434/VANETsC-V2XPA-MADRLintelligent transportation systemsautonomous driving |
| spellingShingle | Ahmed Thair Shakir Barbara M. Masini Nemer Radhwan Khudhair Rosdiadee Nordin Angela Amphawan Priority-Aware Multi-Agent Deep Reinforcement Learning for Resource Scheduling in C-V2X Mode 4 Communication IEEE Access VANETs C-V2X PA-MADRL intelligent transportation systems autonomous driving |
| title | Priority-Aware Multi-Agent Deep Reinforcement Learning for Resource Scheduling in C-V2X Mode 4 Communication |
| title_full | Priority-Aware Multi-Agent Deep Reinforcement Learning for Resource Scheduling in C-V2X Mode 4 Communication |
| title_fullStr | Priority-Aware Multi-Agent Deep Reinforcement Learning for Resource Scheduling in C-V2X Mode 4 Communication |
| title_full_unstemmed | Priority-Aware Multi-Agent Deep Reinforcement Learning for Resource Scheduling in C-V2X Mode 4 Communication |
| title_short | Priority-Aware Multi-Agent Deep Reinforcement Learning for Resource Scheduling in C-V2X Mode 4 Communication |
| title_sort | priority aware multi agent deep reinforcement learning for resource scheduling in c v2x mode 4 communication |
| topic | VANETs C-V2X PA-MADRL intelligent transportation systems autonomous driving |
| url | https://ieeexplore.ieee.org/document/11072434/ |
| work_keys_str_mv | AT ahmedthairshakir priorityawaremultiagentdeepreinforcementlearningforresourceschedulingincv2xmode4communication AT barbarammasini priorityawaremultiagentdeepreinforcementlearningforresourceschedulingincv2xmode4communication AT nemerradhwankhudhair priorityawaremultiagentdeepreinforcementlearningforresourceschedulingincv2xmode4communication AT rosdiadeenordin priorityawaremultiagentdeepreinforcementlearningforresourceschedulingincv2xmode4communication AT angelaamphawan priorityawaremultiagentdeepreinforcementlearningforresourceschedulingincv2xmode4communication |