Umeå University's logo

umu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Cost-aware neural network splitting and dynamic rescheduling for edge intelligence
University of Vienna, Vienna, Austria.
Umeå University, Faculty of Science and Technology, Department of Computing Science. University of Vienna, Vienna, Austria.
Vienna University of Technology, Vienna, Austria.
2023 (English)In: EdgeSys '23: Proceedings of the 6th International Workshop on Edge Systems, Analytics and Networking, ACM Digital Library, 2023, p. 42-47Conference paper, Published paper (Refereed)
Abstract [en]

With the rise of IoT devices and the necessity of intelligent applications, inference tasks are often offloaded to the cloud due to the computation limitation of the end devices. Yet, requests to the cloud are costly in terms of latency, and therefore a shift of the computation from the cloud to the network's edge is unavoidable. This shift is called edge intelligence and promises lower latency, among other advantages. However, some algorithms, like deep neural networks, are computationally intensive, even for local edge servers (ES). To keep latency low, such DNNs can be split into two parts and distributed between the ES and the cloud. We present a dynamic scheduling algorithm that takes real-Time parameters like the clock speed of the ES, bandwidth, and latency into account and predicts the optimal splitting point regarding latency. Furthermore, we estimate the overall costs for the ES and cloud during run-Time and integrate them into our prediction and decision models. We present a cost-Aware prediction of the splitting point, which can be tuned with a parameter toward faster response or lower costs.

Place, publisher, year, edition, pages
ACM Digital Library, 2023. p. 42-47
Keywords [en]
cost-Awareness, DNN splitting, edge computing, edge intelligence
National Category
Computer Sciences Computer Systems
Identifiers
URN: urn:nbn:se:umu:diva-209279DOI: 10.1145/3578354.3592871Scopus ID: 2-s2.0-85159359631ISBN: 9798400700828 (electronic)OAI: oai:DiVA.org:umu-209279DiVA, id: diva2:1764377
Conference
6th International Workshop on Edge Systems, Analytics and Networking, EdgeSys 2023, in conjunction with ACM EuroSys 2023, Rome, Italy, May 8, 2023
Available from: 2023-06-08 Created: 2023-06-08 Last updated: 2023-06-08Bibliographically approved

Open Access in DiVA

fulltext(1120 kB)39 downloads
File information
File name FULLTEXT01.pdfFile size 1120 kBChecksum SHA-512
90c4bcc31868d2a8732b43aec856d86e017f0314a44df286a6194b64f0bf14cf7b134127c233aeb992281a9c7a9be855d21c3fb2a9018e780928d77d7f69b5a9
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Aral, Atakan

Search in DiVA

By author/editor
Aral, Atakan
By organisation
Department of Computing Science
Computer SciencesComputer Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 39 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 213 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf