Identifying Key Enablers in Edge Intelligence (Dagstuhl Seminar 21342)

Authors Aaron Ding, Ella Peltonen, Sasu Tarkoma, Lars Wolf and all authors of the abstracts in this report



PDF
Thumbnail PDF

File

DagRep.11.7.76.pdf
  • Filesize: 3.2 MB
  • 13 pages

Document Identifiers

Author Details

Aaron Ding
  • TU Delft, NL
Ella Peltonen
  • University of Oulu, FI
Sasu Tarkoma
  • University of Helsinki, FI
Lars Wolf
  • TU Braunschweig, DE
and all authors of the abstracts in this report

Cite AsGet BibTex

Aaron Ding, Ella Peltonen, Sasu Tarkoma, and Lars Wolf. Identifying Key Enablers in Edge Intelligence (Dagstuhl Seminar 21342). In Dagstuhl Reports, Volume 11, Issue 7, pp. 76-88, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2021)
https://doi.org/10.4230/DagRep.11.7.76

Abstract

Edge computing, a key part of the 5G networks and beyond, promises to decentralize cloud applications while providing more bandwidth and reducing latencies. The promises are delivered by moving application-specific computations between the cloud, the data-producing devices, and the network infrastructure components at the edges of wireless and fixed networks. However, the current AI/ML methods assume computations are conducted in a powerful computational infrastructure, such as a homogeneous cloud with ample computing and data storage resources available. In this seminar, we discussed and developed presumptions for a comprehensive view of AI methods and capabilities in the context of edge computing, and provided a roadmap to bring together enablers and key aspects for edge computing and applied AI/ML fields.

Subject Classification

ACM Subject Classification
  • Computer systems organization → Distributed architectures
  • Computing methodologies → Artificial intelligence
  • Networks
Keywords
  • artificial intelligence
  • communication networks
  • edge computing
  • intelligent networking

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail