LLM-Based Net Analyzer rApp for Explainable and Safe Automation in O-RAN Non-RT RIC

2026-03-14

AI Summary

This work addresses the operational complexity of 5G/6G O-RAN networks arising from their decoupled architecture and fine-grained control, which hinder the correlation of heterogeneous events and safe generation of configuration actions. The authors propose Net Analyzer rApp, the first framework to integrate a large language model (LLM) as a reasoning collaborator within the O-RAN non-real-time RIC, establishing an event-driven batch inference pipeline for mobility event parsing, anomaly validation, and configuration auditing. By incorporating tool gating, log-directed verification, and human-in-the-loop approval mechanisms, the system strictly decouples reasoning from execution, ensuring auditability and operational safety. Evaluated on a real-world O-RAN testbed under a ping-pong handover scenario, the approach successfully transforms raw telemetry into structured explanations and controlled remediation recommendations, demonstrating both efficacy and security.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Natural Language Processing: Safety and Robustness
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Modern 5G/6G radio access networks are increasingly programmable through O-RAN, yet their operational complexity has grown with disaggregation, open interfaces, and fine-grained control parameters. While RAN-side analytics and telemetry mechanisms, such as KPI-based monitoring and mobility event reporting, provide visibility into network behavior, operators still face challenges in correlating heterogeneous events and safely translating observations into actionable configuration changes. This paper presents an LLM-based Net Analyzer rApp for the O-RAN Non-RT RIC that enables explainable and safe, human-in-the-loop automation for RAN operations. The proposed rApp adopts an event-informed, batch-triggered reasoning framework in which mobility events are first interpreted, anomalies are confirmed through targeted log inspection, configurations are inspected via tool-gated access, and minimal configuration changes are proposed only after explicit operator approval. The architecture enforces a strict separation between reasoning and actuation, ensuring auditability and operational safety. The system is implemented and demonstrated on a real O-RAN testbed using a reproducible ping-pong handover scenario, illustrating how large language models can function as reasoning co-pilots that transform raw RAN telemetry into structured explanations and controlled remediation workflows, complementing existing analytics-only approaches in the NonRT RIC.

Problem

• O-RAN
• RAN automation
• explainable AI
• network operations
• LLM

Innovation

• LLM-based reasoning
• O-RAN Non-RT RIC
• explainable automation
• human-in-the-loop
• safe actuation