Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Efficient Self-Learning and Model Versioning for AI-native O-RAN Edge

Mounir Bensalem, Fin Gentzen, Tuck-Wai Choong, Yu-Chiao Jhuang, Admela Jukan, Jenq-Shiou Leu

TL;DR

Simulation results show that an efficient RL-driven decision-making can guarantee quality of service, bounded latencies while balancing model accuracy, system stability, and resilience.

Abstract

The AI-native vision of 6G requires Radio Access Networks to train, deploy, and continuously refine thousands of machine learning (ML) models that drive real-time radio network optimization. Although the Open RAN (O-RAN) architecture provides open interfaces and an intelligent control plane, it leaves the life-cycle management of these models unspecified. Consequently, operators still rely on ad-hoc, manual update practices that can neither scale across the heterogeneous, multi-layer stack of Cell-Site, Edge-, Regional-, and Central-Cloud domains, nor across the three O-RAN control loops (real-, near-real-, and non-real-time). We present a self-learning framework that provides an efficient closed-loop version management for an AI-native O-RAN edge. In this framework, training pipelines in the Central/Regional Cloud continuously generate new models, which are cataloged along with their resource footprints, security scores, and accuracy metrics in a shared version repository. An Update Manager consults this repository and applies a self-learning policy to decide when and where each new model version should be promoted into operation. A container orchestrator then realizes these decisions across heterogeneous worker nodes, enabling multiple services (rApps, xApps, and dApps) to obtain improved inference with minimal disruption. Simulation results show that an efficient RL-driven decision-making can guarantee quality of service, bounded latencies while balancing model accuracy, system stability, and resilience.

Efficient Self-Learning and Model Versioning for AI-native O-RAN Edge

TL;DR

Simulation results show that an efficient RL-driven decision-making can guarantee quality of service, bounded latencies while balancing model accuracy, system stability, and resilience.

Abstract

The AI-native vision of 6G requires Radio Access Networks to train, deploy, and continuously refine thousands of machine learning (ML) models that drive real-time radio network optimization. Although the Open RAN (O-RAN) architecture provides open interfaces and an intelligent control plane, it leaves the life-cycle management of these models unspecified. Consequently, operators still rely on ad-hoc, manual update practices that can neither scale across the heterogeneous, multi-layer stack of Cell-Site, Edge-, Regional-, and Central-Cloud domains, nor across the three O-RAN control loops (real-, near-real-, and non-real-time). We present a self-learning framework that provides an efficient closed-loop version management for an AI-native O-RAN edge. In this framework, training pipelines in the Central/Regional Cloud continuously generate new models, which are cataloged along with their resource footprints, security scores, and accuracy metrics in a shared version repository. An Update Manager consults this repository and applies a self-learning policy to decide when and where each new model version should be promoted into operation. A container orchestrator then realizes these decisions across heterogeneous worker nodes, enabling multiple services (rApps, xApps, and dApps) to obtain improved inference with minimal disruption. Simulation results show that an efficient RL-driven decision-making can guarantee quality of service, bounded latencies while balancing model accuracy, system stability, and resilience.
Paper Structure (11 sections, 9 equations, 5 figures, 1 table, 1 algorithm)

This paper contains 11 sections, 9 equations, 5 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Reference Architecture
  4. ML Update Manager
  5. A Sample ML-based workflow in O-RAN
  6. ML Model Versioning with RL
  7. Assumptions
  8. Problem Formulation
  9. RL-Based Update Decision
  10. Numerical Evaluation
  11. Conclusion

Figures (5)

  • Figure 1: O-RAN compliant reference architecture with self-learning and ML model versioning.
  • Figure 2: ML Update Manager
  • Figure 3: A simplified ML versioning flow diagram for massive MIMO beamforming optimization, based on oran_usecases_2025
  • Figure 4: Delay for different O-RAN RIC application workflows
  • Figure 5: Performance metrics for ML Models