Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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
On the Performance of Parallel Processing in Dynamic Resource Sharing Systems
KTH, School of Electrical Engineering and Computer Science (EECS), Network and Systems Engineering.
KTH, School of Electrical Engineering and Computer Science (EECS), Network and Systems Engineering.ORCID iD: 0000-0002-2764-8099
2019 (English)In: Proceedings - 20th International Conference on High Performance Computing and Communications, 16th International Conference on Smart City and 4th International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018, Institute of Electrical and Electronics Engineers Inc. , 2019, p. 30-36Conference paper, Published paper (Refereed)
Abstract [en]

Parallel processing has the potential of significantly decreasing the service time for a single computational task. Meanwhile, as each task occupies more resources, the number of simultaneously supported tasks declines. This tradeoff is interesting when resources are accessed by many users in a dynamic way, like in the case of cloud or fog computing. In this paper, we evaluate how the level of parallelization and the eventual overheads affect the response time in these dynamic resource sharing systems. We show the counterintuitive finding that even when parallelization has no overhead, the allocation of all resources to a task is suboptimal if the service times have large coefficient of variation. Moreover, we evaluate the scalability properties, and provide guidelines for the optimal level of parallelization under different types of overhead.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc. , 2019. p. 30-36
Keywords [en]
Dynamic Resource Sharing, Parallel Processing, Queuing theory, Computation theory, Data communication systems, Fog computing, Queueing theory, Smart city, Time sharing systems, Coefficient of variation, Computational task, Optimal level, Parallelizations, Service time, Parallel processing systems
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-248249DOI: 10.1109/HPCC/SmartCity/DSS.2018.00036ISI: 000468511200005Scopus ID: 2-s2.0-85062549943ISBN: 9781538666142 (print)OAI: oai:DiVA.org:kth-248249DiVA, id: diva2:1304143
Conference
20th International Conference on High Performance Computing and Communications, 16th IEEE International Conference on Smart City and 4th IEEE International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2018, 28 June 2018 through 30 June 2018
Note

QC 20190411

Available from: 2019-04-11 Created: 2019-04-11 Last updated: 2019-06-26Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopusconference

Authority records BETA

Zeng, MingFodor, Viktória

Search in DiVA

By author/editor
Zeng, MingFodor, Viktória
By organisation
Network and Systems Engineering
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 28 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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