Towards Intelligent Resource Allocation in Highly-Distributed Content Delivery Networks Using Graph Neural Networks

We introduce GNN4Alloc, a learning-based frame-work for resource allocation in highly distributed Content De-livery Networks (CDNs). Focusing on the core challenges of content placement and routing, GNN4Alloc leverages Graph Neural Networks (GNNs) to enhance decision-making efficiency in dynamic and...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2025 9th Network Traffic Measurement and Analysis Conference (TMA) s. 1 - 4
Hlavní autoři: Vanerio, Juan, Casas, Pedro, Schmid, Stefan
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IFIP 10.06.2025
Témata:
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract We introduce GNN4Alloc, a learning-based frame-work for resource allocation in highly distributed Content De-livery Networks (CDNs). Focusing on the core challenges of content placement and routing, GNN4Alloc leverages Graph Neural Networks (GNNs) to enhance decision-making efficiency in dynamic and large-scale environments. Building on prior work that employs mathematical optimization and heuristic algorithms, we reformulate these problems using graph representation learning, leveraging the bipartite nature of content-to-node assignment and routing decisions in CDN resource allocation. The framework incorporates GNN-based modules - including neural algorithm executors and constrained optimization layers - to develop adaptive allocation policies that generalize across diverse network topologies and demand profiles. By doing so, GNN4Alloc aims to improve both the scalability and solution quality of content allocation strategies, contributing to the broader goal of advancing GNN-based control in distributed systems.
AbstractList We introduce GNN4Alloc, a learning-based frame-work for resource allocation in highly distributed Content De-livery Networks (CDNs). Focusing on the core challenges of content placement and routing, GNN4Alloc leverages Graph Neural Networks (GNNs) to enhance decision-making efficiency in dynamic and large-scale environments. Building on prior work that employs mathematical optimization and heuristic algorithms, we reformulate these problems using graph representation learning, leveraging the bipartite nature of content-to-node assignment and routing decisions in CDN resource allocation. The framework incorporates GNN-based modules - including neural algorithm executors and constrained optimization layers - to develop adaptive allocation policies that generalize across diverse network topologies and demand profiles. By doing so, GNN4Alloc aims to improve both the scalability and solution quality of content allocation strategies, contributing to the broader goal of advancing GNN-based control in distributed systems.
Author Vanerio, Juan
Casas, Pedro
Schmid, Stefan
Author_xml – sequence: 1
  givenname: Juan
  surname: Vanerio
  fullname: Vanerio, Juan
  organization: University of Vienna
– sequence: 2
  givenname: Pedro
  surname: Casas
  fullname: Casas, Pedro
  organization: AIT Austrian Institute of Technology
– sequence: 3
  givenname: Stefan
  surname: Schmid
  fullname: Schmid, Stefan
  organization: University of Vienna
BookMark eNo9kMtKAzEYhSPoQmvfQDAvMDWXmVyWpdW2UBVkXJdM5k8bjJOSpJa-vQUvqwPf4TuLc4MuhzgAQveUTBjXVD-0z1MhaiYnjLBmQinRklB9gcZaKq4Jp1LIur5GuY1Hk_qMV0OBEPwWhoLfIMdDsoCnIURrio8D9gNe-u0unKq5zyX57lCgx7N41s7GHIL_gnTCL1COMX1k_J79sMWLZPa7MzwkE_67W3TlTMgw_s0Rap8e29myWr8uVrPpuvKal6pXVjnbGdZ3jDLhlJGOGkGYrK3hTDnZAFWCE8kdVV0DxtZKKmGgYc5ayUfo7mfWA8Bmn_ynSafN3xX8G6wSW7U
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.23919/TMA66427.2025.11097019
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Xplore Digital Library
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore Digital Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9783903176744
3903176745
EndPage 4
ExternalDocumentID 11097019
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i93t-d8c8fcba2db2126f8a7f1a60274ca328f75e1863073f18b5eac48786ae52fcc73
IEDL.DBID RIE
IngestDate Wed Aug 06 17:55:18 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i93t-d8c8fcba2db2126f8a7f1a60274ca328f75e1863073f18b5eac48786ae52fcc73
PageCount 4
ParticipantIDs ieee_primary_11097019
PublicationCentury 2000
PublicationDate 2025-June-10
PublicationDateYYYYMMDD 2025-06-10
PublicationDate_xml – month: 06
  year: 2025
  text: 2025-June-10
  day: 10
PublicationDecade 2020
PublicationTitle 2025 9th Network Traffic Measurement and Analysis Conference (TMA)
PublicationTitleAbbrev TMA
PublicationYear 2025
Publisher IFIP
Publisher_xml – name: IFIP
Score 1.9112384
Snippet We introduce GNN4Alloc, a learning-based frame-work for resource allocation in highly distributed Content De-livery Networks (CDNs). Focusing on the core...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Focusing
Graph neural networks
Heuristic algorithms
Network topology
Optimization
Representation learning
Resource management
Routing
Scalability
Telecommunication traffic
Title Towards Intelligent Resource Allocation in Highly-Distributed Content Delivery Networks Using Graph Neural Networks
URI https://ieeexplore.ieee.org/document/11097019
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELagYmACRBFveWB1W9v1I2NFKTBQdcjQrXL8kCpFKWpSpP57fE5bxMDAElmJLUt3su-R775D6MkJ7Ye6EEQKykl0qR0xbOAIj8_CmSFlzKZmE2o61fN5NtsVq6daGO99Ap_5HgzTv3y3shtIlfWBHRPow4_RsVKyLdZqMVuMZzTr5x8jGf1pFcM-Jnr72b_6piSzMTn754bnqPtTgIdnB9NygY58dYnqPEFca_x-oNFs8D79jkclmCUQM15WGOAb5ZaMgRYXOlp5hxMPVVwx9iVgMbZ42iLAa5xgA_gVqKsxkHWY8vCti_LJS_78RnY9E8gy4w1x2upgC8NcEW2SDNqoQI2E2NMaznRQwlMt4WAHGlUUr90YsWhpvGDBWsWvUKdaVf4aYQfJQcqNyTI7ZD46DkFQM-DWWx79BHODuiCwxWfLirHYy-r2j_d36BTUAjArOrhHnWa98Q_oxH41y3r9mHT5DTUTo7Q
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV05T8MwFLagIMEEiCJuPLC6re06ccYKKK1oow4ZulWOD6lSlKImReq_x889EAMDSxTlUKT3ZL8j3_s-hJ6NkLYrc0EiQTnxKbUhinUM4f6YG9WljOkgNhGnqZxOk8l2WD3MwlhrA_jMtuA0_Ms3C72CVlkb2DGBPvwQHYF01nZca4PaYjyhSTsb9yKfUce-8GOitXv-l3JKCBz9s39-8hw1f0bw8GQfXC7QgS0vUZUFkGuFh3sizRrvGvC4V0BgAkPjeYkBwFGsySsQ44KmlTU4MFH5N15tAWiMNU43GPAKB-AAfgfyagx0HarY32uirP-WvQzIVjWBzBNeEyO1dDpXzOQ-KkVOqthRFUH1qRVn0sXCUhnB0nbUO8lvvL5mkZGygjmtY36FGuWitNcIG2gPUq5Ukugusz51cIKqDtdWc58pqBvUBIPNPje8GLOdrW7_uP6ETgbZeDQbDdOPO3QKLgLQFe3co0a9XNkHdKy_6nm1fAx-_QbmzKb9
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2025+9th+Network+Traffic+Measurement+and+Analysis+Conference+%28TMA%29&rft.atitle=Towards+Intelligent+Resource+Allocation+in+Highly-Distributed+Content+Delivery+Networks+Using+Graph+Neural+Networks&rft.au=Vanerio%2C+Juan&rft.au=Casas%2C+Pedro&rft.au=Schmid%2C+Stefan&rft.date=2025-06-10&rft.pub=IFIP&rft.spage=1&rft.epage=4&rft_id=info:doi/10.23919%2FTMA66427.2025.11097019&rft.externalDocID=11097019