Show simple item record

dc.contributor.authorBernárdez Gil, Guillermo
dc.contributor.authorSuárez-Varela Maciá, José Rafael
dc.contributor.authorLópez Brescó, Albert
dc.contributor.authorShi, Xiang
dc.contributor.authorXiao, Shihan
dc.contributor.authorCheng, Xiangle
dc.contributor.authorBarlet Ros, Pere
dc.contributor.authorCabellos Aparicio, Alberto
dc.contributor.otherUniversitat Politècnica de Catalunya. Doctorat en Arquitectura de Computadors
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors
dc.date.accessioned2023-10-26T12:39:47Z
dc.date.available2023-10-26T12:39:47Z
dc.date.issued2023-04
dc.identifier.citationBernárdez, G. [et al.]. MAGNNETO: A graph neural network-based multi-agent system for traffic engineering. "IEEE transactions on cognitive communications and networking", Abril 2023, vol. 9, núm. 2, p. 494-506.
dc.identifier.issn2332-7731
dc.identifier.urihttp://hdl.handle.net/2117/395413
dc.description.abstractCurrent trends in networking propose the use of Machine Learning (ML) for a wide variety of network optimization tasks. As such, many efforts have been made to produce ML-based solutions for Traffic Engineering (TE), which is a fundamental problem in Internet Service Provider (ISP) networks. Nowadays, state-of-the-art TE optimizers rely on traditional optimization techniques, such as Local search, Constraint Programming, or Linear programming. In this paper, we present MAGNNETO, a distributed ML-based framework that leverages Multi-Agent Reinforcement Learning and Graph Neural Networks for distributed TE optimization. MAGNNETO deploys a set of agents across the network that learn and communicate in a distributed fashion via message exchanges between neighboring agents. Particularly, we apply this framework to optimize link weights in Open Shortest Path First (OSPF), with the goal of minimizing network congestion. In our evaluation, we compare MAGNNETO against several state-of-the-art TE optimizers in more than 75 topologies (up to 153 nodes and 354 links), including realistic traffic loads. Our experimental results show that, thanks to its distributed nature, MAGNNETO achieves comparable performance to state-of-the-art TE optimizers with significantly lower execution times. Moreover, our ML-based solution demonstrates a strong generalization capability to successfully operate in new networks unseen during training.
dc.description.sponsorshipThis publication is part of the Spanish I+D+i project TRAINER-A (ref. PID2020-118011GBC21), funded by MCIN/AEI/10.13039/501100011033. This work is also partially funded by the Catalan Institution for Research and Advanced Studies (ICREA), the Secretariat for Universities and Research of the Ministry of Business and Knowledge of the Government of Catalonia, and the European Social Fund.
dc.format.extent13 p.
dc.language.isoeng
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
dc.subjectÀrees temàtiques de la UPC::Enginyeria de la telecomunicació::Telemàtica i xarxes d'ordinadors
dc.subject.lcshMachine learning
dc.subject.lcshReinforcement learning
dc.subject.lcshTelecommunication -- Traffic -- Management
dc.subject.otherTraffic engineering
dc.subject.otherRouting optimization
dc.subject.otherMulti-agent reinforcement learning
dc.subject.otherGraph neural networks
dc.titleMAGNNETO: A graph neural network-based multi-agent system for traffic engineering
dc.typeArticle
dc.subject.lemacAprenentatge automàtic
dc.subject.lemacAprenentatge per reforç
dc.subject.lemacTelecomunicació -- Tràfic -- Gestió
dc.contributor.groupUniversitat Politècnica de Catalunya. IDEAI-UPC - Intelligent Data sciEnce and Artificial Intelligence Research Group
dc.identifier.doi10.1109/TCCN.2023.3235719
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://ieeexplore.ieee.org/document/10013773
dc.rights.accessOpen Access
local.identifier.drac37295960
dc.description.versionPostprint (author's final draft)
dc.relation.projectidinfo:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2020-118011GB-C21/ES/INVESTIGACION EN FUTURAS REDES TOTALMENTE OPTIMIZADAS MEDIANTE INTELIGENCIA ARTIFICIAL - A/
local.citation.authorBernárdez, G.; Suarez-varela, J.; Lopez, A.; Shi, X.; Xiao, S.; Cheng, X.; Barlet, P.; Cabellos-Aparicio, A.
local.citation.publicationNameIEEE transactions on cognitive communications and networking
local.citation.volume9
local.citation.number2
local.citation.startingPage494
local.citation.endingPage506


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record