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.orcid | 0000-0003-4824-1199 | |
| cris.virtual.orcid | 0000-0002-6276-2057 | |
| cris.virtualsource.department | 505a9fa2-2261-4859-8c77-73c2ba21244c | |
| cris.virtualsource.department | 5fc1041b-34c9-4bdb-ba41-1a986f0c4c25 | |
| cris.virtualsource.orcid | 505a9fa2-2261-4859-8c77-73c2ba21244c | |
| cris.virtualsource.orcid | 5fc1041b-34c9-4bdb-ba41-1a986f0c4c25 | |
| dc.contributor.author | Zaccarini, Mattia | |
| dc.contributor.author | Pereira dos Santos, José Pedro | |
| dc.contributor.author | Poltronieri, Filippo | |
| dc.contributor.author | Di Cicco, Nicola | |
| dc.contributor.author | Tortonesi, Mauro | |
| dc.contributor.author | Stefanelli, Cesare | |
| dc.contributor.author | de Turck, Filip | |
| dc.date.accessioned | 2026-11-16T15:05:34Z | |
| dc.date.available | 2026-11-16T15:05:34Z | |
| dc.date.createdwos | 2026 | |
| dc.date.issued | 2026 | |
| dc.description.abstract | The 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.wosFundingText | This 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.doi | 10.1109/noms69089.2026.11668312 | |
| dc.identifier.isbn | 979-8-3315-9269-1 | |
| dc.identifier.issn | 1542-1201 | |
| dc.identifier.uri | https://imec-publications.be/handle/20.500.12860/60821 | |
| dc.language.iso | eng | |
| dc.provenance.editstepuser | greet.vanhoof@imec.be | |
| dc.publisher | IEEE | |
| dc.relation.ispartofseries | IEEE IFIP Network Operations and Management Symposium | |
| dc.source.beginpage | 1 | |
| dc.source.conference | IEEE Network Operations and Management Symposium - NOMS | |
| dc.source.conferencedate | 2026-05-18 | |
| dc.source.conferencelocation | Rome, Italy | |
| dc.source.endpage | 12 | |
| dc.source.journal | NOMS 2026-2026 IEEE NETWORK OPERATIONS AND MANAGEMENT SYMPOSIUM | |
| dc.source.numberofpages | 12 | |
| dc.subject.keywords | VIRTUAL RESOURCES | |
| dc.subject.keywords | ORCHESTRATION | |
| dc.title | GaiaRL: Multi-Objective RL for Sustainable VNF Placement in the Compute Continuum | |
| dc.type | Proceedings paper | |
| dspace.entity.type | Publication | |
| imec.internal.crawledAt | 2026-09-03 | |
| imec.internal.source | crawler | |
| imec.internal.wosCreatedAt | 2026-11-11 | |
| Files | Original bundle
| |
| Publication available in collections: |