RouteNet: leveraging graph neural networks for network modeling and optimization in SDN

© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.Network modeling is a key enabler to achieve efficient network operation in future self-driving Software-Defined Networks. However, we still lack functional network models able to produce accurate predictions of Key Performance Indicators (KPI) such as delay, jitter or loss at limited cost. In this paper we propose RouteNet, a novel network model based on Graph Neural Network (GNN) that is able to understand the complex relationship between topology, routing, and input traffic to produce accurate estimates of the per-source/destination per-packet delay distribution and loss. RouteNet leverages the ability of GNNs to learn and model graph-structured information and as a result, our model is able to generalize over arbitrary topologies, routing schemes and traffic intensity. In our evaluation, we show that RouteNet is able to predict accurately the delay distribution (mean delay and jitter) and loss even in topologies, routing and traffic unseen in the training (worst case MRE = 15.4%). Also, we present several use cases where we leverage the KPI predictions of our GNN model to achieve efficient routing optimization and network planning.This work was supported in part by the Polish Ministryof Science and Higher Education with the subvention funds of the Facultyof Computer Science, Electronics and Telecommunications, AGH University,in part by the Spanish MINECO under Contract TEC2017-90034-C2-1-R(ALLIANCE), in part by the Catalan Institution for Research and AdvancedStudies (ICREA) and the FI-AGAUR Grant by the Catalan Government, andin part by PL-Grid Infrastructure.Peer ReviewedPostprint (author's final draft