Publication:

<i>GaiaRL</i>: Multi-Objective RL for Sustainable VNF Placement in the Compute Continuum

 
cris.virtual.department#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.department#PLACEHOLDER_PARENT_METADATA_VALUE#
cris.virtual.orcid0000-0003-4824-1199
cris.virtual.orcid0000-0002-6276-2057
cris.virtualsource.department505a9fa2-2261-4859-8c77-73c2ba21244c
cris.virtualsource.department5fc1041b-34c9-4bdb-ba41-1a986f0c4c25
cris.virtualsource.orcid505a9fa2-2261-4859-8c77-73c2ba21244c
cris.virtualsource.orcid5fc1041b-34c9-4bdb-ba41-1a986f0c4c25
dc.contributor.authorZaccarini, Mattia
dc.contributor.authorPereira dos Santos, José Pedro
dc.contributor.authorPoltronieri, Filippo
dc.contributor.authorDi Cicco, Nicola
dc.contributor.authorTortonesi, Mauro
dc.contributor.authorStefanelli, Cesare
dc.contributor.authorde Turck, Filip
dc.date.accessioned2026-11-16T15:05:34Z
dc.date.available2026-11-16T15:05:34Z
dc.date.createdwos2026
dc.date.issued2026
dc.description.abstractThe increasing deployment of Virtual Network Functions (VNFs) across the Compute Continuum (CC)-spanning cloud, fog, and edge environments- has introduced new challenges in orchestrating network services efficiently and sustainably. As network infrastructures scale to support latency-sensitive and resource-intensive applications, such as eXtended Reality (XR) and Generative Artificial Intelligence (GenAI) applications, existing orchestration strategies often prioritize performance while overlooking energy consumption and carbon footprint, leading to environmentally costly outcomes. Motivated by the urgent need for greener network management solutions, this work proposes GaiaRL, a Multi-Objective Reinforcement Learning (MORL) framework for sustainable VNF placement in distributed edge-to-cloud environments. GaiaRL formulates the orchestration problem as a sequential decision-making problem, balancing conflicting objectives such as deployment cost, latency, energy consumption, and fair resource utilization. We implement and evaluate multiple MORL algorithms-alongside a novel Geometric Pareto Q-Learning (GeoPQL) method-and compare them against single-objective baselines from previous work. Experiments using realistic 5G deployments across compute continuum scenarios show that MORL algorithms better balance the trade-offs between different objectives and drive energy-aware orchestration in modern computing scenarios, paving the way toward sustainable network management in 6G and beyond.
dc.description.wosFundingTextThis work has been partially supported by the Spoke 1 "FutureHPC & BigData" of the Italian Research Center on High-Performance Computing, Big Data and Quantum Computing (ICSC) funded by MUR Missione 4 - Next Generation EU (NGEU). Jose Santos is funded by the Research Foundation Flanders (FWO), grant number 1253226N.
dc.identifier.doi10.1109/noms69089.2026.11668312
dc.identifier.isbn979-8-3315-9269-1
dc.identifier.issn1542-1201
dc.identifier.urihttps://imec-publications.be/handle/20.500.12860/60821
dc.language.isoeng
dc.provenance.editstepusergreet.vanhoof@imec.be
dc.publisherIEEE
dc.relation.ispartofseriesIEEE IFIP Network Operations and Management Symposium
dc.source.beginpage1
dc.source.conferenceIEEE Network Operations and Management Symposium - NOMS
dc.source.conferencedate2026-05-18
dc.source.conferencelocationRome, Italy
dc.source.endpage12
dc.source.journalNOMS 2026-2026 IEEE NETWORK OPERATIONS AND MANAGEMENT SYMPOSIUM
dc.source.numberofpages12
dc.subject.keywordsVIRTUAL RESOURCES
dc.subject.keywordsORCHESTRATION
dc.title

GaiaRL: Multi-Objective RL for Sustainable VNF Placement in the Compute Continuum

dc.typeProceedings paper
dspace.entity.typePublication
imec.internal.crawledAt2026-09-03
imec.internal.sourcecrawler
imec.internal.wosCreatedAt2026-11-11
Files

Original bundle

Name:
9086.pdf
Size:
1.59 MB
Format:
Adobe Portable Document Format
Description:
Accepted
Publication available in collections: