REAL: Reinforcement Learning-Enabled xApps for Experimental Closed-Loop Optimization in O-RAN with OSC RIC and srsRAN

2025-02-02

AI Summary

To address the absence of AI-driven real-time closed-loop optimization and the difficulty in dynamically adapting to multi-slice QoS requirements in O-RAN, this paper proposes the first lightweight real-time network slicing optimization framework integrating the OSC RIC with srsRAN. The framework enables near-real-time radio resource scheduling for eMBB, URLLC, and mMTC slices under a 12-user scenario, and achieves—on an open-source O-RAN platform—the first end-to-end closed-loop control via a reinforcement learning (PPO)-based xApp. Innovatively, it incorporates GNU Radio-based channel modeling—including free-space path loss (FSPL), multipath fading, AWGN, and Doppler effects—to realistically emulate urban mobile environments. Experimental results demonstrate the RL xApp’s capability to dynamically guarantee slice-specific QoS metrics, validating the feasibility of AI-enabled closed-loop optimization on a physical 5G open-source testbed. This work establishes a scalable baseline for PHY-layer digital twin implementation.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Security and Privacy: Security and privacy of machine learning and AI applications

Abstract

Open Radio Access Network (O-RAN) offers an open, programmable architecture for next-generation wireless networks, enabling advanced control through AI-based applications on the near-Real-Time RAN Intelligent Controller (near-RT RIC). However, fully integrated, real-time demonstrations of closed-loop optimization in O-RAN remain scarce. In this paper, we present a complete framework that combines the O-RAN Software Community RIC (OSC RIC) with srsRAN for near-real-time network slicing using Reinforcement Learning (RL). Our system orchestrates resources across diverse slice types (eMBB, URLLC, mMTC) for up to 12 UEs. We incorporate GNU Radio blocks for channel modeling, including Free-Space Path Loss (FSPL), single-tap multipath, AWGN, and Doppler effects, to emulate an urban mobility scenario. Experimental results show that our RL-based xApps dynamically adapt resource allocation and maintain QoS under varying traffic demands, highlighting both the feasibility and challenges of end-to-end AI-driven optimization in a lightweight O-RAN testbed. Our findings establish a baseline for real-time RL-based slicing in a disaggregated 5G framework and underscore the need for further enhancements to support fully simulated PHY digital twins without reliance on commercial software.

Problem

• O-RAN
• real-time optimization
• AI-driven resource allocation

Innovation

• O-RAN Integration
• Reinforcement Learning
• 5G Network Optimization