Harnessing the Power of LLMs, Informers and Decision Transformers for Intent-driven RAN Management in 6G

2025-05-03

AI Summary

To address challenges in 6G radio access network (RAN) management—including ambiguous intent interpretation, weak dynamic validation, and insufficient closed-loop optimization—this paper proposes a generative AI–driven three-stage RAN management framework. First, a lightweight QLoRA-finetuned large language model (LLM) integrated with retrieval-augmented generation (RAG) enables high-accuracy semantic intent parsing. Second, an Informer model forecasts critical time-series performance metrics to support proactive intent validation. Third, a novel goal-aware hierarchical decision transformer (HDTGA) facilitates dynamic, multi-granularity network application orchestration. This work introduces the first unified LLM-RAG-Informer-HDTGA collaborative architecture, seamlessly integrating intent understanding, validation, and execution. Experimental results demonstrate a 6% improvement in BERTScore, a 9% increase in semantic similarity, and an 88% intent validation accuracy. Compared to baseline methods, the framework achieves a 19.3% throughput gain, a 48.5% reduction in end-to-end latency, and a 54.9% enhancement in energy efficiency.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Intent-driven network management is critical for managing the complexity of 5G and 6G networks. It enables adaptive, on-demand management of the network based on the objectives of the network operators. In this paper, we propose an innovative three-step framework for intent-driven network management based on Generative AI (GenAI) algorithms. First, we fine-tune a Large Language Model (LLM) on a custom dataset using a Quantized Low-Rank Adapter (QLoRA) to enable memory-efficient intent processing within limited computational resources. A Retrieval Augmented Generation (RAG) module is included to support dynamic decision-making. Second, we utilize a transformer architecture for time series forecasting to predict key parameters, such as power consumption, traffic load, and packet drop rate, to facilitate intent validation proactively. Lastly, we introduce a Hierarchical Decision Transformer with Goal Awareness (HDTGA) to optimize the selection and orchestration of network applications and hence, optimize the network. Our intent guidance and processing approach improves BERTScore by 6% and the semantic similarity score by 9% compared to the base LLM model. Again, the proposed predictive intent validation approach can successfully rule out the performance-degrading intents with an average of 88% accuracy. Finally, compared to the baselines, the proposed HDTGA algorithm increases throughput at least by 19.3%, reduces delay by 48.5%, and boosts energy efficiency by 54.9%.

Problem

• Proposes intent-driven RAN management for 6G using GenAI
• Enhances intent processing via LLM fine-tuning and RAG
• Optimizes network performance with predictive validation and HDTGA

Innovation

• Fine-tune LLM with QLoRA for efficient intent processing
• Use transformer for time series forecasting of key parameters
• Apply HDTGA for optimal network application orchestration