Malmö University Publications
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
Analyzing Distributed Deep Neural Network Deployment on Edge and Cloud Nodes in IoT Systems
Malmö University, Faculty of Technology and Society (TS), Department of Computer Science and Media Technology (DVMT). Malmö University, Internet of Things and People (IOTAP).
Malmö University, Faculty of Technology and Society (TS), Department of Computer Science and Media Technology (DVMT). Malmö University, Internet of Things and People (IOTAP).ORCID iD: 0000-0002-8209-0921
Malmö University, Faculty of Technology and Society (TS), Department of Computer Science and Media Technology (DVMT). Malmö University, Internet of Things and People (IOTAP).ORCID iD: 0000-0003-0998-6585
Malmö University, Faculty of Technology and Society (TS), Department of Computer Science and Media Technology (DVMT). Malmö University, Internet of Things and People (IOTAP).ORCID iD: 0000-0003-0326-0556
Show others and affiliations
2020 (English)In: IEEE International Conference on Edge Computing (EDGE), Virtual conference, October 18–24, 2020., 2020, p. 59-66Conference paper, Published paper (Refereed)
Abstract [en]

For the efficient execution of Deep Neural Networks (DNN) in the Internet of Things, computation tasks can be distributed and deployed on edge nodes. In contrast to deploying all computation to the cloud, the use of Distributed DNN (DDNN) often results in a reduced amount of data that is sent through the network and thus might increase the overall performance of the system. However, finding an appropriate deployment scenario is often a complex task and requires considering several criteria. In this paper, we introduce a multi-criteria decision-making method based on the Analytical Hierarchy Process for the comparison and selection of deployment alternatives. We use the RECAP simulation framework to model and simulate DDNN deployments on different scales to provide a comprehensive assessment of deployments to system designers. In a case study, we apply the method to a smart city scenario where different distributions and deployments of a DNN are analyzed and compared.

Place, publisher, year, edition, pages
2020. p. 59-66
Keywords [en]
Edge Computing, Internet of Things, Distributed Deep Neural Networks, Simulation, Smart Cities
National Category
Computer Systems Communication Systems
Identifiers
URN: urn:nbn:se:mau:diva-37023DOI: 10.1109/EDGE50951.2020.00017ISI: 000659316400010Scopus ID: 2-s2.0-85100251401ISBN: 978-1-7281-8254-4 (electronic)ISBN: 978-1-7281-8255-1 (print)OAI: oai:DiVA.org:mau-37023DiVA, id: diva2:1504498
Conference
IEEE International Conference on Edge Computing (EDGE) 2020. 19-23 Oct. 2020. Beijing, China
Available from: 2020-11-27 Created: 2020-11-27 Last updated: 2024-02-05Bibliographically approved
In thesis
1. Towards Supporting IoT System Designers in Edge Computing Deployment Decisions
Open this publication in new window or tab >>Towards Supporting IoT System Designers in Edge Computing Deployment Decisions
2021 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

The rapidly evolving Internet of Things (IoT) systems demands addressing new requirements. This particularly needs efficient deployment of IoT systems to meet the quality requirements such as latency, energy consumption, privacy, and bandwidth utilization. The increasing availability of computational resources close to the edge has prompted the idea of using these for distributed computing and storage, known as edge computing. Edge computing may help and complement cloud computing to facilitate deployment of IoT systems and improve their quality. However, deciding where to deploy the various application components is not a straightforward task, and IoT system designer should be supported for the decision.

To support the designers, in this thesis we focused on the system qualities, and aimed for three main contributions. First, by reviewing the literature, we identified the relevant and most used qualities and metrics. Moreover, to analyse how computer simulation can be used as a supporting tool, we investigated the edge computing simulators, and in particular the metrics they provide for modeling and analyzing IoT systems in edge computing. Finally, we introduced a method to represent how multiple qualities can be considered in the decision. In particular, we considered distributing Deep Neural Network layers as a use case and raked the deployment options by measuring the relevant metrics via simulation.

Place, publisher, year, edition, pages
Malmö: Malmö universitet, 2021. p. 141
Series
Studies in Computer Science ; 13
Keywords
Internet of Things, Edge computing, Decision Support, Quality Attrib-utes, Metrics, Simulation
National Category
Communication Systems Other Electrical Engineering, Electronic Engineering, Information Engineering Computer Systems
Identifiers
urn:nbn:se:mau:diva-37068 (URN)10.24834/isbn.9789178771592 (DOI)978-91-7877-158-5 (ISBN)978-91-7877-159-2 (ISBN)
Supervisors
Available from: 2020-12-03 Created: 2020-12-02 Last updated: 2024-02-23Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopusConference homepage

Authority records

Ashouri, MajidLorig, FabianDavidsson, PaulSpalazzese, Romina

Search in DiVA

By author/editor
Ashouri, MajidLorig, FabianDavidsson, PaulSpalazzese, Romina
By organisation
Department of Computer Science and Media Technology (DVMT)Internet of Things and People (IOTAP)
Computer SystemsCommunication Systems

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 151 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