Near-Real-Time Resource Slicing for QoS Optimization in 5G O-RAN using Deep Reinforcement Learning

2025-09-17

AI Summary

To address QoS assurance challenges in 5G O-RAN arising from dynamic channels, user mobility, and traffic fluctuations, this paper proposes xSlice—a near-real-time radio resource slicing framework. Methodologically, it formulates multi-service QoS optimization as a regret minimization problem; designs a graph convolutional network (GCN) for topology-aware graph embedding of variable-size sessions; and integrates an Actor-Critic deep reinforcement learning architecture to enable fine-grained, online adaptive resource scheduling at the MAC layer. Strictly compliant with O-RAN specifications, xSlice is deployed on a real-world testbed comprising ten smartphones. Experimental results demonstrate that xSlice reduces performance regret by 67% compared to baseline approaches, while achieving significant and stable improvements across throughput, latency, and reliability—without compromising standard conformance or practical deployability.

Technology Category

• Planning, Routing, and Scheduling: Scheduling
• Machine Learning: Online Learning & Bandits
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Open-Radio Access Network (O-RAN) has become an important paradigm for 5G and beyond radio access networks. This paper presents an xApp called xSlice for the Near-Real-Time (Near-RT) RAN Intelligent Controller (RIC) of 5G O-RANs. xSlice is an online learning algorithm that adaptively adjusts MAC-layer resource allocation in response to dynamic network states, including time-varying wireless channel conditions, user mobility, traffic fluctuations, and changes in user demand. To address these network dynamics, we first formulate the Quality-of-Service (QoS) optimization problem as a regret minimization problem by quantifying the QoS demands of all traffic sessions through weighting their throughput, latency, and reliability. We then develop a deep reinforcement learning (DRL) framework that utilizes an actor-critic model to combine the advantages of both value-based and policy-based updating methods. A graph convolutional network (GCN) is incorporated as a component of the DRL framework for graph embedding of RAN data, enabling xSlice to handle a dynamic number of traffic sessions. We have implemented xSlice on an O-RAN testbed with 10 smartphones and conducted extensive experiments to evaluate its performance in realistic scenarios. Experimental results show that xSlice can reduce performance regret by 67% compared to the state-of-the-art solutions. Source code is available on GitHub [1].

Problem

• Optimizing QoS in 5G O-RAN through dynamic resource allocation
• Addressing network dynamics like channel conditions and user mobility
• Minimizing performance regret using deep reinforcement learning

Innovation

• Deep reinforcement learning for QoS optimization
• Graph convolutional network for dynamic sessions
• Actor-critic model combining value-policy methods