LLM-Guided Open RAN: Empowering Hierarchical RAN Intelligent Control

2025-04-25

AI Summary

To address insufficient coordination, semantic fragmentation, and policy misalignment between non-real-time (nRT) and near-real-time (near-RT) RAN Intelligent Controllers (RICs) in O-RAN, this paper proposes LLM-hRIC—a hierarchical RIC framework. It integrates a large language model (LLM) at the nRT layer for environment-aware strategic reasoning and couples a deep reinforcement learning (DRL) module at the near-RT layer for low-latency resource scheduling. This work pioneers a semantically aligned, dual-timescale architecture that unifies LLM-driven high-level intent understanding with DRL-enabled rapid execution—breaking from conventional isolated RIC decision-making. Evaluated on an integrated access and backhaul (IAB) network simulator, LLM-hRIC achieves a 23% reduction in average latency and an 18% gain in throughput over baseline methods, while significantly improving spectral efficiency and load balancing. Results validate both the effectiveness and scalability of hierarchical intelligent control in O-RAN.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Recent advancements in large language models (LLMs) have led to a significant interest in deploying LLMempowered algorithms for wireless communication networks. Meanwhile, open radio access network (O-RAN) techniques offer unprecedented flexibility, with the non-real-time (non-RT) radio access network (RAN) intelligent controller (RIC) (non-RT RIC) and near-real-time (near-RT) RIC (near-RT RIC) components enabling intelligent resource management across different time scales. In this paper, we propose the LLM empowered hierarchical RIC (LLM-hRIC) framework to improve the collaboration between RICs. This framework integrates LLMs with reinforcement learning (RL) for efficient network resource management. In this framework, LLMs-empowered non-RT RICs provide strategic guidance and high-level policies based on environmental context. Concurrently, RL-empowered near-RT RICs perform low-latency tasks based on strategic guidance and local near-RT observation. We evaluate the LLM-hRIC framework in an integrated access and backhaul (IAB) network setting. Simulation results demonstrate that the proposed framework achieves superior performance. Finally, we discuss the key future challenges in applying LLMs to O-RAN.

Problem

• Enhancing collaboration between RAN intelligent controllers (RICs)
• Integrating LLMs with RL for network resource management
• Improving performance in integrated access and backhaul networks

Innovation

• LLM-hRIC integrates LLMs with reinforcement learning
• LLMs guide non-RT RICs for strategic policies
• RL empowers near-RT RICs for low-latency tasks