Authors: Kristina Dzeparoska, Ali Tizghadam, Alberto Leon-Garcia

Published on: February 01, 2024

Impact Score: 8.22

Arxiv code: Arxiv:2402.00715

Summary

• What is new: The paper introduces an assurance framework leveraging AI-driven policies from Large Language Models (LLMs) to handle intent drift in Intent-Based Networking (IBN).
• Why this is important: IBN faces challenges in processing intents and ensuring intent conformance in dynamic networks.
• What the research proposes: An assurance framework that uses AI-driven policies to detect and act upon intent drift, ensuring alignment between operational and target network states.
• Results: The framework effectively detects intent drift and takes necessary actions to maintain alignment with business objectives, utilizing LLMs for rapid learning of in-context requirements.

Technical Details

Technological frameworks used: Assurance framework for IBN

Models used: Large Language Models (LLMs)

Data used: Network operational and target states data

Potential Impact

The framework has implications for network management software providers, telecom companies, and businesses relying on complex network operations.

Want to implement this idea in a business?

We have generated a startup concept here: IntentGuard AI.