| Title: |
A Multi-Agent Deep Reinforcement Learning Approach for RAN Resource Allocation in O-RAN |
| Authors: |
Rezazadeh F.; Zanzi L.; Devoti F.; Barrachina-Muñoz S.; Zeydan E.; Costa-Perez X.; Mangues-Bafalluy J. |
| Publisher Information: |
Institute of Electrical and Electronics Engineers Inc. |
| Publication Year: |
2023 |
| Collection: |
Zenodo |
| Subject Terms: |
5G mobile communication systems; Deep learning; Multi agent systems; Reinforcement learning; Resource allocation; Artificial intelligence learning; Learning frameworks; Local monitoring; Machine-learning; Multi agent; Radio resources; Reinforcement learning approach; Reinforcement learnings; Resource management; Resources allocation; Wireless networks |
| Description: |
Artificial intelligence (AI) and Machine Learning (ML) are considered as key enablers for realizing the full potential of fifth-generation (5G) and beyond mobile networks, particularly in the context of resource management and orchestration. In this demonstration, we consider a fully-fledged 5G mobile network and develop a multi-agent deep reinforcement learning (DRL) framework for RAN resource allocation. By leveraging local monitoring information generated by a shared gNodeB instance (gNB), each DRL agent aims to optimally allocate radio resources concerning service-specific traffic demands belonging to heterogeneous running services. We perform experiments on the deployed testbed in real-time, showing that DRL-based agents can allocate radio resources fairly while improving the overall efficiency of resource utilization and minimizing the risk of over provisioning. © 2023 IEEE. ; ACKNOWLEDGMENT The research leading to these results has been partially supported by the H2020 MonB5G Project (grant 871780), the European Union Smart Networks and Services (SNS) under Horizon-JU-SNS-2022 program (project BeGREEN - grant 101097083), and EdgeDT. The work is also partly funded by Program UNICO I+D funded by MCIN/AEI/ 10.13039/501100011033 under Grant TSI-063000-2021-54/55, and in part by the ERDF "A way of making Europe" under Grant PID2021-126431OB-I00, and in part by Generalitat de Catalunya (grant 2021SGR-00770). |
| Document Type: |
conference object |
| Language: |
unknown |
| Relation: |
https://zenodo.org/records/10794230; oai:zenodo.org:10794230; https://doi.org/10.1109/INFOCOMWKSHPS57453.2023.10226154 |
| DOI: |
10.1109/INFOCOMWKSHPS57453.2023.10226154 |
| Availability: |
https://doi.org/10.1109/INFOCOMWKSHPS57453.2023.10226154; https://zenodo.org/records/10794230 |
| Rights: |
Creative Commons Attribution 4.0 International ; cc-by-4.0 ; https://creativecommons.org/licenses/by/4.0/legalcode |
| Accession Number: |
edsbas.E202CD67 |
| Database: |
BASE |