Enhancing Channel Selection in 5G with Decentralized Federated Multi-Agent Deep Reinforcement Learning
The increasing popularity of vehicular communication systems necessitates efficient and autonomous decision-making to address the challenges of vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications. In this paper, we present a comprehensive study on channelization in Cellular V...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ferdowsi University of Mashhad
2024-12-01
|
| Series: | Computer and Knowledge Engineering |
| Subjects: | |
| Online Access: | https://cke.um.ac.ir/article_45826_5014363e0f68262f4593f908220dec1b.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595442137825280 |
|---|---|
| author | Taghi Shahgholi Keyhan Khamforoosh Amir Sheikhahmadi Sadoon Azizi |
| author_facet | Taghi Shahgholi Keyhan Khamforoosh Amir Sheikhahmadi Sadoon Azizi |
| author_sort | Taghi Shahgholi |
| collection | DOAJ |
| description | The increasing popularity of vehicular communication systems necessitates efficient and autonomous decision-making to address the challenges of vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications. In this paper, we present a comprehensive study on channelization in Cellular Vehicle-to-Everything (C-V2X) communication and propose a novel two-layer multi-agent approach that integrates deep reinforcement learning (DRL) and federated learning (FL) to enhance the decision-making process in channel utilization.Our approach leverages the autonomy of each vehicle, treating it as an independent agent capable of making channel selection decisions based on its local observations in its own cluster. Simultaneously, a centralized architecture coordinates nearby vehicles to optimize overall system performance. The DRL-based decision-making model considers crucial factors, such as instantaneous channel state information and historical link selections, to dynamically allocate channels and transmission power, leading to improved system efficiency.By incorporating federated learning, we enable knowledge sharing and synchronization among the decentralized vehicular agents. This collaborative approach harnesses the collective intelligence of the network, empowering each agent to gain insights into the broader network dynamics beyond its limited observations. The results of our extensive simulations demonstrate the superiority of the proposed approach over existing methods, as it achieves higher data rates, success rates, and superior interference mitigation. |
| format | Article |
| id | doaj-art-0541c59c96ed4e97b91f75ca642542ef |
| institution | Kabale University |
| issn | 2538-5453 2717-4123 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Ferdowsi University of Mashhad |
| record_format | Article |
| series | Computer and Knowledge Engineering |
| spelling | doaj-art-0541c59c96ed4e97b91f75ca642542ef2025-01-19T04:04:23ZengFerdowsi University of MashhadComputer and Knowledge Engineering2538-54532717-41232024-12-017211610.22067/cke.2024.88900.111945826Enhancing Channel Selection in 5G with Decentralized Federated Multi-Agent Deep Reinforcement LearningTaghi Shahgholi0Keyhan Khamforoosh1Amir Sheikhahmadi2Sadoon Azizi3Department of Computer Engineering, Sanandaj Branch, Islamic Azad University ,Sanandaj, IranDepartment of Computer Engineering, Sanandaj Branch, Islamic Azad University,Sanandaj, IranDepartment of Computer Engineering, Sanandaj Branch, Islamic Azad University,Sanandaj, IranDepartment of Computer Engineering and IT, University of Kurdistan,Sanandaj,IranThe increasing popularity of vehicular communication systems necessitates efficient and autonomous decision-making to address the challenges of vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications. In this paper, we present a comprehensive study on channelization in Cellular Vehicle-to-Everything (C-V2X) communication and propose a novel two-layer multi-agent approach that integrates deep reinforcement learning (DRL) and federated learning (FL) to enhance the decision-making process in channel utilization.Our approach leverages the autonomy of each vehicle, treating it as an independent agent capable of making channel selection decisions based on its local observations in its own cluster. Simultaneously, a centralized architecture coordinates nearby vehicles to optimize overall system performance. The DRL-based decision-making model considers crucial factors, such as instantaneous channel state information and historical link selections, to dynamically allocate channels and transmission power, leading to improved system efficiency.By incorporating federated learning, we enable knowledge sharing and synchronization among the decentralized vehicular agents. This collaborative approach harnesses the collective intelligence of the network, empowering each agent to gain insights into the broader network dynamics beyond its limited observations. The results of our extensive simulations demonstrate the superiority of the proposed approach over existing methods, as it achieves higher data rates, success rates, and superior interference mitigation.https://cke.um.ac.ir/article_45826_5014363e0f68262f4593f908220dec1b.pdfc-v2x optimizationmulti-agent learningdrl-based channel accessfederated learning integration |
| spellingShingle | Taghi Shahgholi Keyhan Khamforoosh Amir Sheikhahmadi Sadoon Azizi Enhancing Channel Selection in 5G with Decentralized Federated Multi-Agent Deep Reinforcement Learning Computer and Knowledge Engineering c-v2x optimization multi-agent learning drl-based channel access federated learning integration |
| title | Enhancing Channel Selection in 5G with Decentralized Federated Multi-Agent Deep Reinforcement Learning |
| title_full | Enhancing Channel Selection in 5G with Decentralized Federated Multi-Agent Deep Reinforcement Learning |
| title_fullStr | Enhancing Channel Selection in 5G with Decentralized Federated Multi-Agent Deep Reinforcement Learning |
| title_full_unstemmed | Enhancing Channel Selection in 5G with Decentralized Federated Multi-Agent Deep Reinforcement Learning |
| title_short | Enhancing Channel Selection in 5G with Decentralized Federated Multi-Agent Deep Reinforcement Learning |
| title_sort | enhancing channel selection in 5g with decentralized federated multi agent deep reinforcement learning |
| topic | c-v2x optimization multi-agent learning drl-based channel access federated learning integration |
| url | https://cke.um.ac.ir/article_45826_5014363e0f68262f4593f908220dec1b.pdf |
| work_keys_str_mv | AT taghishahgholi enhancingchannelselectionin5gwithdecentralizedfederatedmultiagentdeepreinforcementlearning AT keyhankhamforoosh enhancingchannelselectionin5gwithdecentralizedfederatedmultiagentdeepreinforcementlearning AT amirsheikhahmadi enhancingchannelselectionin5gwithdecentralizedfederatedmultiagentdeepreinforcementlearning AT sadoonazizi enhancingchannelselectionin5gwithdecentralizedfederatedmultiagentdeepreinforcementlearning |