Litcius/Paper detail

A Multi-Agent Deep Reinforcement Learning Approach for RAN Resource Allocation in O-RAN

Farhad Rezazadeh, Lanfranco Zanzi, Francesco Devoti, Sergio Barrachina‐Muñoz, Engin Zeydan, Xavier Costa‐Pérez, Josep Mangues‐Bafalluy

202314 citationsDOIOpen Access PDF

Abstract

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.

Topics & Concepts

Reinforcement learningC-RANTestbedComputer scienceOrchestrationProvisioningResource allocationRadio access networkContext (archaeology)Resource management (computing)Distributed computingRanCellular networkComputer networkRadio resource managementKey (lock)Artificial intelligenceWireless networkBase stationWirelessTelecommunicationsComputer securityMusicalVisual artsPaleontologyBiologyArtMobile stationSoftware-Defined Networks and 5GAdvanced MIMO Systems OptimizationAdvanced Photonic Communication Systems
A Multi-Agent Deep Reinforcement Learning Approach for RAN Resource Allocation in O-RAN | Litcius