Open RAN and AI: Standardization Gaps and Research Directions
Dr. Michele Polese, Prof. Tommaso Melodia
Northeastern University
Abstract
This paper identifies and analyzes the standardization gaps at the intersection of Open RAN and AI in the O-RAN Alliance specifications. We evaluate the current RIC (RAN Intelligent Controller) architecture against the requirements of advanced AI workloads including deep reinforcement learning and federated learning. Seven critical gaps are identified, including model lifecycle management, real-time inference latency bounds, and multi-vendor AI interoperability. We propose solutions for each gap and prioritize them for standardization.
AI Summary
- Identifies seven standardization gaps at the intersection of Open RAN and AI.
- Evaluates current O-RAN RIC architecture against advanced AI requirements.
- Proposes solutions for model lifecycle management and multi-vendor AI interoperability.
- Prioritizes gaps for O-RAN Alliance standardization roadmap.
Key Findings
- 1Current O-RAN specs lack sufficient support for real-time DRL inference.
- 2Multi-vendor AI model interoperability is the most critical gap.
- 3Model lifecycle management needs standardized APIs for training, deployment, and monitoring.
Industry Implications
O-RAN Alliance should prioritize AI-related specifications in upcoming releases.
Vendors need to collaborate on common AI model formats and interfaces.
Closing these gaps is essential for AI-RAN to achieve its full potential.
Read the Original Paper
Access the full paper on arXiv for complete methodology, results, and references.
Open on arXivRelated Papers
3GPP 6G Vision and Requirements: Technical Report Summary and Analysis
3GPP / Ericsson — 56 citations
Standards/Policy PapersInteroperability Testing Framework for AI-RAN Multi-Vendor Deployments
AI-RAN Alliance — 16 citations
Standards/Policy PapersSpectrum Policy for 6G: Upper Mid-Band and Sub-THz Allocation Strategies
London School of Economics — 18 citations