Joint Admission Control and Resource Provisioning for URLLC Traffic in O-RAN: A Constrained Multi-Agent Reinforcement Learning Approach

Achieving ultra-reliable low-latency communication (URLLC) in next-generation radio access networks (RAN) is crucial for mission-critical applications, such as industrial robotics and remote healthcare. However, high traffic loads in RAN environments may lead to resource contention and overload, jeopardizing latency and reliability requirements. To address this, Open RAN (O-RAN) architecture provides a flexible, softwaredefined framework that can manage admission control and resource allocation strategies. This paper introduces a joint admission control and resource provisioning framework tailored for O-RAN environments, using a constrained reinforcement learning model to dynamically balance user admissions and allocate resources to those admitted. By selectively granting service requests and efficiently managing resources, our approach mitigates latency violations and improves energy efficiency under high traffic conditions. Simulation results indicate substantial performance gains over traditional methods, demonstrating the potential of reinforcement learning to optimize URLLC performance in resource-constrained NextG networks.