RAG-Enabled Intent Reasoning for Application-Network Interaction

TL;DR

This paper introduces a context-aware AI framework combining RAG, MR, and generative AI to interpret diverse application intents for network management, surpassing existing LLM-based methods.

Contribution

It presents a novel intent-RAG framework that enhances intent translation in intent-based networks without requiring complex semantic language creation.

Findings

The intent-RAG framework outperforms LLM and vanilla-RAG in intent translation accuracy.

The framework enables generalized, domain-specific intent expression.

Experimental results validate the effectiveness of the proposed approach.

Abstract

Intent-based network (IBN) is a promising solution to automate network operation and management. IBN aims to offer human-tailored network interaction, allowing the network to communicate in a way that aligns with the network users' language, rather than requiring the network users to understand the technical language of the network/devices. Nowadays, different applications interact with the network, each with its own specialized needs and domain language. Creating semantic languages (i.e., ontology-based languages) and associating them with each application to facilitate intent translation lacks technical expertise and is neither practical nor scalable. To tackle the aforementioned problem, we propose a context-aware AI framework that utilizes machine reasoning (MR), retrieval augmented generation (RAG), and generative AI technologies to interpret intents from different applications and generate structured network intents. The proposed framework allows for generalized/domain-specific intent expression and overcomes the drawbacks of large language models (LLMs) and vanilla-RAG framework. The experimental results show that our proposed intent-RAG framework outperforms the LLM and vanilla-RAG framework in intent translation.