Towards Intent-Based Network Management: Large Language Models for Intent Extraction in 5G Core Networks
Dimitrios Michael Manias, Ali Chouman, Abdallah Shami
TL;DR
This work tackles the challenge of achieving end-to-end autonomous network management in 5G/B5G by extracting user intents and converting them into network policies. It introduces a customized LLM-based pipeline for intent extraction within the 5G core context, using a prompting architecture to ensure correct interpretation and policy formation. Key contributions include the architectural framework for intent extraction, a preliminary demonstration with GPT-3.5, and a roadmap toward full end-to-end autonomous networking with future moves to open-source LLMs and data-augmentation techniques. The study aims to enable zero-touch network management by integrating with NWDAF within ZSM, reducing human intervention and enhancing network automation.
Abstract
The integration of Machine Learning and Artificial Intelligence (ML/AI) into fifth-generation (5G) networks has made evident the limitations of network intelligence with ever-increasing, strenuous requirements for current and next-generation devices. This transition to ubiquitous intelligence demands high connectivity, synchronicity, and end-to-end communication between users and network operators, and will pave the way towards full network automation without human intervention. Intent-based networking is a key factor in the reduction of human actions, roles, and responsibilities while shifting towards novel extraction and interpretation of automated network management. This paper presents the development of a custom Large Language Model (LLM) for 5G and next-generation intent-based networking and provides insights into future LLM developments and integrations to realize end-to-end intent-based networking for fully automated network intelligence.