Learning to route

Asaf Valadarsky, Michael Schapira, Dafna Shahaf, Aviv Tamar

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

145 Scopus citations

Abstract

Recently, much attention has been devoted to the question of whether/when traditional network protocol design, which relies on the application of algorithmic insights by human experts, can be replaced by a data-driven (i.e., machine learning) approach. We explore this question in the context of the arguably most fundamental networking task: routing. Can ideas and techniques from machine learning (ML) be leveraged to automatically generate "good" routing configurations? We focus on the classical setting of intradomain traffic engineering. We observe that this context poses significant challenges for data-driven protocol design. Our preliminary results regarding the power of data-driven routing suggest that applying ML (specifically, deep reinforcement learning) to this context yields high performance and is a promising direction for further research. We outline a research agenda for ML-guided routing.

Original languageAmerican English
Title of host publicationHotNets 2017 - Proceedings of the 16th ACM Workshop on Hot Topics in Networks
PublisherAssociation for Computing Machinery, Inc
Pages185-191
Number of pages7
ISBN (Electronic)9781450355698
DOIs
StatePublished - 30 Nov 2017
Event16th ACM Workshop on Hot Topics in Networks, HotNets 2017 - Palo Alto, United States
Duration: 30 Nov 20171 Dec 2017

Publication series

NameHotNets 2017 - Proceedings of the 16th ACM Workshop on Hot Topics in Networks

Conference

Conference16th ACM Workshop on Hot Topics in Networks, HotNets 2017
Country/TerritoryUnited States
CityPalo Alto
Period30/11/171/12/17

Bibliographical note

Publisher Copyright:
© 2017 Copyright held by the owner/author(s).

Fingerprint

Dive into the research topics of 'Learning to route'. Together they form a unique fingerprint.

Cite this