GP4P4: Enabling Self-Programming Networks

Abstract

Recent advances in programmable switches have enabled network operators to build high-speed customized network functions. Although this is an important step towards self-* networks, operators are now faced with the burden of learning a new language and maintaining a repository of network function code. Inspired by the Intent-Based Networking paradigm, we propose a new framework, GP4P4: a genetic programming approach able to autonomously generate programs for P4-programmable switches directly from network intents. We demonstrate that GP4P4 is able to generate various small network functions in up to a few minutes; an important first step towards realizing the vision of `Self-Driving' networks.