<div class="csl-bib-body">
<div class="csl-entry">Gravara, M., Marcelino, C., Stanisic, A., & Nastic, S. (2026). PLAIground: SLO-Driven Runtime Model Selection for Compound AI Systems in the Edge-Cloud-Space Continuum. In <i>2026 IEEE International Conference on Smart Computing Workshops and Other Affiliated events (SmartComp Companion)</i> (pp. 261–266). IEEE. https://doi.org/10.1109/SmartComp-Companion70724.2026.00061</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/230698
-
dc.description.abstract
Applications in the 3D Computing Continuum, which unifies edge, cloud, and space, require combining multiple AI tasks such as object detection, time-series analytics, and natural language processing into Compound AI systems. These systems must satisfy stringent Service Level Objectives (SLOs) on accuracy, latency, and cost. A key mechanism for maintaining SLO compliance of Compound AI systems is runtime model selection, where AI models are dynamically switched for each workflow task. However, existing distributed and compound AI frameworks do not natively support runtime model selection. We present PLAIground, a framework that enables runtime model selection for Compound AI systems. PLAIground introduces Compoundable AI Model (CAIM) abstraction, which decouples task semantics from AI model implementations via Task and Data Contracts, enabling model switching without workflow changes. Additionally, PLAIground introduces Pixie, an SLO-driven runtime model selection algorithm, which dynamically selects the most suitable model for each task during execution. Our evaluation on two realistic Compound AI workflows demonstrates that Pixie achieves up to 91.3% accuracy while maintaining SLO compliance where fixed-model strategies either violate cost and latency budgets up to 21x or miss accuracy targets by 4%.
en
dc.description.sponsorship
European Commission
-
dc.language.iso
en
-
dc.subject
3D Continuum
en
dc.subject
Compound AI
en
dc.subject
Edge-Cloud-Space Continuum
en
dc.subject
Model Selection
en
dc.subject
Programming Models
en
dc.title
PLAIground: SLO-Driven Runtime Model Selection for Compound AI Systems in the Edge-Cloud-Space Continuum
en
dc.type
Inproceedings
en
dc.type
Konferenzbeitrag
de
dc.relation.isbn
979-8-3195-4416-2
-
dc.description.startpage
261
-
dc.description.endpage
266
-
dc.relation.grantno
101192912
-
dc.type.category
Full-Paper Contribution
-
tuw.booktitle
2026 IEEE International Conference on Smart Computing Workshops and Other Affiliated events (SmartComp Companion)
-
tuw.peerreviewed
true
-
tuw.relation.publisher
IEEE
-
tuw.project.title
NexaSphere: NexGen 3D Networks Spin Harmonies across 6G, AI, and unified TN/NTN
-
tuw.researchTopic.id
I4
-
tuw.researchTopic.name
Information Systems Engineering
-
tuw.researchTopic.value
100
-
tuw.publication.orgunit
E194-02 - Forschungsbereich Distributed Systems
-
tuw.publisher.doi
10.1109/SmartComp-Companion70724.2026.00061
-
dc.description.numberOfPages
6
-
tuw.author.orcid
0009-0006-7986-5243
-
tuw.author.orcid
0000-0003-1707-3014
-
tuw.author.orcid
0009-0007-2120-1142
-
tuw.author.orcid
0000-0003-0410-6315
-
tuw.event.name
11th IEEE International Workshop on Smart Service Systems (SmartSys 2026) co-located with IEEE SMARTCOMP 2026
en
tuw.event.startdate
22-06-2026
-
tuw.event.enddate
25-06-2026
-
tuw.event.online
On Site
-
tuw.event.type
Event for scientific audience
-
tuw.event.place
Messina
-
tuw.event.country
IT
-
tuw.event.presenter
Gravara, Milos
-
wb.sciencebranch
Informatik
-
wb.sciencebranch.oefos
1020
-
wb.sciencebranch.value
100
-
item.cerifentitytype
Publications
-
item.languageiso639-1
en
-
item.openairecristype
http://purl.org/coar/resource_type/c_5794
-
item.openairetype
conference paper
-
item.fulltext
no Fulltext
-
item.grantfulltext
none
-
crisitem.author.dept
E194-02 - Forschungsbereich Distributed Systems
-
crisitem.author.dept
E194-02 - Forschungsbereich Distributed Systems
-
crisitem.author.dept
E194-02 - Forschungsbereich Distributed Systems
-
crisitem.author.dept
E194-02 - Forschungsbereich Distributed Systems
-
crisitem.author.orcid
0009-0006-7986-5243
-
crisitem.author.orcid
0000-0003-1707-3014
-
crisitem.author.orcid
0009-0007-2120-1142
-
crisitem.author.orcid
0000-0003-0410-6315
-
crisitem.author.parentorg
E194 - Institut für Information Systems Engineering
-
crisitem.author.parentorg
E194 - Institut für Information Systems Engineering
-
crisitem.author.parentorg
E194 - Institut für Information Systems Engineering
-
crisitem.author.parentorg
E194 - Institut für Information Systems Engineering