liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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
Artificial Intelligence-Driven Mechanism for Edge Computing-Based Industrial Applications
Linköping University, Department of Computer and Information Science, Database and information techniques. Linköping University, Faculty of Science & Engineering.
Chinese Acad Sci, Peoples R China.
Univ Fortaleza, Brazil.
2019 (English)In: IEEE Transactions on Industrial Informatics, ISSN 1551-3203, E-ISSN 1941-0050, Vol. 15, no 7, p. 4235-4243Article in journal (Refereed) Published
Abstract [en]

Due to various challenging issues such as, computational complexity and more delay in cloud computing, edge computing has overtaken the conventional process by efficiently and fairly allocating the resources i.e., power and battery lifetime in Internet of things (IoT)-based industrial applications. In the meantime, intelligent and accurate resource management by artificial intelligence (AI) has become the center of attention especially in industrial applications. With the coordination of AI at the edge will remarkably enhance the range and computational speed of IoT-based devices in industries. But the challenging issue in these power hungry, short battery lifetime, and delay-intolerant portable devices is inappropriate and inefficient classical trends of fair resource allotment. Also, it is interpreted through extensive industrial datasets that dynamic wireless channel could not be supported by the typical power saving and battery lifetime techniques, for example, predictive transmission power control (TPC) and baseline. Thus, this paper proposes 1) a forward central dynamic and available approach (FCDAA) by adapting the running time of sensing and transmission processes in IoT-based portable devices; 2) a system-level battery model by evaluating the energy dissipation in IoT devices; and 3) a data reliability model for edge AI-based IoT devices over hybrid TPC and duty-cycle network. Two important cases, for instance, static (i. e., product processing) and dynamic (i. e., vibration and fault diagnosis) are introduced for proper monitoring of industrial platform. Experimental testbed reveals that the proposed FCDAA enhances energy efficiency and battery lifetime at acceptable reliability (similar to 0.95) by appropriately tuning duty cycle and TPC unlike conventional methods.

Place, publisher, year, edition, pages
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC , 2019. Vol. 15, no 7, p. 4235-4243
Keywords [en]
Artificial intelligence (AI); battery model; duty cycle; edge computing; forward central dynamic and available approach (FCDAA); industrial Internet of things (IIoT); mobile devices; predictive transmission power control (PTPC)
National Category
Communication Systems
Identifiers
URN: urn:nbn:se:liu:diva-159156DOI: 10.1109/TII.2019.2902878ISI: 000474628100045OAI: oai:DiVA.org:liu-159156DiVA, id: diva2:1339650
Note

Funding Agencies|CENIIT project [17.01]

Available from: 2019-07-30 Created: 2019-07-30 Last updated: 2019-07-30

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full text

Search in DiVA

By author/editor
Sodhro, Ali Hassan
By organisation
Database and information techniquesFaculty of Science & Engineering
In the same journal
IEEE Transactions on Industrial Informatics
Communication Systems

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 17 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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