Umeå universitets logga

umu.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Energy efficient and QoS-aware model selection for DNN inference in edge intelligence
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.ORCID-id: 0000-0002-2633-6798
2025 (Engelska)Ingår i: Proceedings - 2025 IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2025, Institute of Electrical and Electronics Engineers (IEEE), 2025Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Edge intelligence is about enabling deep learning applications to run on edge platforms, often under strict Quality of Service (QoS) constraints (e.g., deadlines and accuracy). The heterogeneity and limited computational and energy capacities of edge servers necessitate further study on energy-efficient Deep Neural Network (DNN) inference. While availability of DNN model variants enables adaptive selection without compromising accuracy, it increases the complexity of the solution space. Also, existing research on model selection for DNN inference lacks efficient estimation of energy consumption. This paper proposes a polynomial-time joint strategy for QoS-aware model instance provisioning and selection, based on many-to-many stable matching. Our novel formulation uses the number of floating-point operations (FLOPs) of each model along with hardware-level characteristics of edge servers to minimize total energy usage while maximizing successful inference completions. The proposed strategy is evaluated under different preference functions. Experimental results, compared to optimal and evolutionary algorithms, demonstrate the runtime efficiency of our strategy. Furthermore, extensive evaluations against baselines highlights its superior performance and the importance of jointly considering both system- and application-level parameters in the solution.

Ort, förlag, år, upplaga, sidor
Institute of Electrical and Electronics Engineers (IEEE), 2025.
Serie
IEEE International Conference on Cloud Computing Technology and Science (CloudCom), ISSN 2330-2194, E-ISSN 2380-8004
Nyckelord [en]
DNN Inference, Edge Intelligence, Energy Efficiency, Model Se-lection, QoS Requirements, Stable Matching
Nationell ämneskategori
Datavetenskap (datalogi) Datorsystem
Identifikatorer
URN: urn:nbn:se:umu:diva-252671DOI: 10.1109/CloudCom67567.2025.11331487Scopus ID: 2-s2.0-105034656451ISBN: 9798331566340 (digital)ISBN: 9798331566357 (tryckt)OAI: oai:DiVA.org:umu-252671DiVA, id: diva2:2061568
Konferens
2025 IEEE 16th International Conference on Cloud Computing Technology and Science, IEEE CloudCom 2025, Shenzhen, China, 14-16 November 2025
Forskningsfinansiär
Kempestiftelserna, 3161Tillgänglig från: 2026-05-21 Skapad: 2026-05-21 Senast uppdaterad: 2026-05-21Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextScopus

Person

Siar, HajarElmroth, Erik

Sök vidare i DiVA

Av författaren/redaktören
Siar, HajarElmroth, Erik
Av organisationen
Institutionen för datavetenskap
Datavetenskap (datalogi)Datorsystem

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 35 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf