RAG-Empowered LLM-Driven Dynamic Radio Resource Management in Open 6G RAN

TL;DR

This paper introduces a novel AI-driven framework using Retrieval-Augmented Generation with Large Language Models to dynamically manage radio resources in 6G networks, enhancing efficiency and SLA compliance.

Contribution

It proposes a dual-agent ReLLM framework for adaptive, efficient radio resource management in open 6G RAN, validated on a real testbed.

Findings

Maintains near-zero drop ratio for low-priority slices.

Satisfies latency requirements for high-priority slices.

Reduces computational and energy costs of LLM inference.

Abstract

Implications of the advancements in the area of artificial intelligence to the wireless communications is extremely significant, especially in terms of resource management. In this paper, a Retrieval-Augmented Generation (RAG)-empowered Large Language Model (ReLLM)-driven dynamic radio resource management framework for Open Radio Access Network (O-RAN) inspired 6G networks is proposed. The introduced methodology leverages the ReLLM framework to interpret both historical and real-time network data, enabling adaptive control of network slices. The ReLLM is founded on two specialized agents, one is responsible for proactively detecting service level agreement (SLA) violations by continuously monitoring and estimating slice-specific performance metrics, and the other one is responsible for dynamically reallocating physical resource blocks when the SLA violation probability exceeds a pre-defined threshold. The primary objective of this dual-agent design is to minimize unnecessary LLM inference calls while satisfying the SLA requirements of the slices, thereby improving computational and energy efficiency. The proposed ReLLM framework is implemented and validated on an end-to-end O-RAN testbed built upon open-source OpenAirInterface emulators. The experimental results demonstrate that the LLM approach with its reduced token consumption feature maintains a near-zero drop ratio for the low-priority slice while simultaneously satisfying acceptable latency performance for the high-priority slice. The ReLLM-driven design improves reliability and SLA compliance, confirming its practicality for real-world O-RAN testbeds and its potential applicability to future 6G networks.