Using Machine Learning for Intent-based provisioning in High-Speed Science Networks

Abstract

Smart and rapid provisioning of network resources that are easy to configure, monitor, and maintain is essential for high-speed network infrastructures. There is a need to allow users to interface directly with networks to easily navigate their use-cases, while not compromising network policies. This paper introduces EVIAN, a system designed to bridge the gap between user and network requirements. EVIAN is an intent rendering platform, that uses natural language processing to interact with users, gathers network requirements in an easy-to-talk English conversation, and translates these to network API calls.