Roadmap for edge AI: A Dagstuhl Perspective

Aaron Yi Ding; Ella Peltonen; Tobias Meuser; Atakan Aral; Christian Becker; Schahram Dustdar; Thomas Hiessl; Dieter Kranzlmüller; Madhusanka Liyanage; Setareh Maghsudi; Nitinder Mohan; Jörg Ott; Jan S. Rellermeyer; Stefan Schulte; Henning Schulzrinne; Gürkan Solmaz; Sasu Tarkoma; Blesson Varghese; Lars Wolf

doi:10.1145/3523230.3523235

Roadmap for edge AI: A Dagstuhl Perspective

Aaron Yi Ding, Ella Peltonen, Tobias Meuser, Atakan Aral, Christian Becker, Schahram Dustdar, Thomas Hiessl, Dieter Kranzlmüller, Madhusanka Liyanage, Setareh Maghsudi, Nitinder Mohan, Jörg Ott, Jan S. Rellermeyer, Stefan Schulte, Henning Schulzrinne, Gürkan Solmaz, Sasu Tarkoma, Blesson Varghese, Lars Wolf

Informatics 11 - Chair of Connected Mobility

Research output: Contribution to journal › Article › peer-review

38 Scopus citations

Abstract

Based on the collective input of Dagstuhl Seminar (21342), this paper presents a comprehensive discussion on AI methods and capabilities in the context of edge computing, referred as Edge AI. In a nutshell, we envision Edge AI to provide adaptation for data-driven applications, enhance network and radio access, and allow the creation, optimisation, and deployment of distributed AI/ML pipelines with given quality of experience, trust, security and privacy targets. The Edge AI community investigates novel ML methods for the edge computing environment, spanning multiple sub-fields of computer science, engineering and ICT. The goal is to share an envisioned roadmap that can bring together key actors and enablers to further advance the domain of Edge AI.

Original language	English
Pages (from-to)	28-33
Number of pages	6
Journal	Computer Communication Review
Volume	52
Issue number	1
DOIs	https://doi.org/10.1145/3523230.3523235
State	Published - Jan 2022

Keywords

5G Beyond
Edge AI
Edge Computing
Future Cloud
Roadmap

Access to Document

10.1145/3523230.3523235

Cite this

Ding, A. Y., Peltonen, E., Meuser, T., Aral, A., Becker, C., Dustdar, S., Hiessl, T., Kranzlmüller, D., Liyanage, M., Maghsudi, S., Mohan, N., Ott, J., Rellermeyer, J. S., Schulte, S., Schulzrinne, H., Solmaz, G., Tarkoma, S., Varghese, B., & Wolf, L. (2022). Roadmap for edge AI: A Dagstuhl Perspective. Computer Communication Review, 52(1), 28-33. https://doi.org/10.1145/3523230.3523235

@article{21046c4a67b94805acf40f91e9cb74d5,

title = "Roadmap for edge AI: A Dagstuhl Perspective",

abstract = "Based on the collective input of Dagstuhl Seminar (21342), this paper presents a comprehensive discussion on AI methods and capabilities in the context of edge computing, referred as Edge AI. In a nutshell, we envision Edge AI to provide adaptation for data-driven applications, enhance network and radio access, and allow the creation, optimisation, and deployment of distributed AI/ML pipelines with given quality of experience, trust, security and privacy targets. The Edge AI community investigates novel ML methods for the edge computing environment, spanning multiple sub-fields of computer science, engineering and ICT. The goal is to share an envisioned roadmap that can bring together key actors and enablers to further advance the domain of Edge AI.",

keywords = "5G Beyond, Edge AI, Edge Computing, Future Cloud, Roadmap",

author = "Ding, {Aaron Yi} and Ella Peltonen and Tobias Meuser and Atakan Aral and Christian Becker and Schahram Dustdar and Thomas Hiessl and Dieter Kranzlm{\"u}ller and Madhusanka Liyanage and Setareh Maghsudi and Nitinder Mohan and J{\"o}rg Ott and Rellermeyer, {Jan S.} and Stefan Schulte and Henning Schulzrinne and G{\"u}rkan Solmaz and Sasu Tarkoma and Blesson Varghese and Lars Wolf",

note = "Publisher Copyright: {\textcopyright} 2022 Copyright is held by the owner/author(s).",

year = "2022",

month = jan,

doi = "10.1145/3523230.3523235",

language = "English",

volume = "52",

pages = "28--33",

journal = "Computer Communication Review",

issn = "0146-4833",

publisher = "Association for Computing Machinery (ACM)",

number = "1",

}

Ding, AY, Peltonen, E, Meuser, T, Aral, A, Becker, C, Dustdar, S, Hiessl, T, Kranzlmüller, D, Liyanage, M, Maghsudi, S, Mohan, N, Ott, J, Rellermeyer, JS, Schulte, S, Schulzrinne, H, Solmaz, G, Tarkoma, S, Varghese, B & Wolf, L 2022, 'Roadmap for edge AI: A Dagstuhl Perspective', Computer Communication Review, vol. 52, no. 1, pp. 28-33. https://doi.org/10.1145/3523230.3523235

TY - JOUR

T1 - Roadmap for edge AI

T2 - A Dagstuhl Perspective

AU - Ding, Aaron Yi

AU - Peltonen, Ella

AU - Meuser, Tobias

AU - Aral, Atakan

AU - Becker, Christian

AU - Dustdar, Schahram

AU - Hiessl, Thomas

AU - Kranzlmüller, Dieter

AU - Liyanage, Madhusanka

AU - Maghsudi, Setareh

AU - Mohan, Nitinder

AU - Ott, Jörg

AU - Rellermeyer, Jan S.

AU - Schulte, Stefan

AU - Schulzrinne, Henning

AU - Solmaz, Gürkan

AU - Tarkoma, Sasu

AU - Varghese, Blesson

AU - Wolf, Lars

PY - 2022/1

Y1 - 2022/1

N2 - Based on the collective input of Dagstuhl Seminar (21342), this paper presents a comprehensive discussion on AI methods and capabilities in the context of edge computing, referred as Edge AI. In a nutshell, we envision Edge AI to provide adaptation for data-driven applications, enhance network and radio access, and allow the creation, optimisation, and deployment of distributed AI/ML pipelines with given quality of experience, trust, security and privacy targets. The Edge AI community investigates novel ML methods for the edge computing environment, spanning multiple sub-fields of computer science, engineering and ICT. The goal is to share an envisioned roadmap that can bring together key actors and enablers to further advance the domain of Edge AI.

AB - Based on the collective input of Dagstuhl Seminar (21342), this paper presents a comprehensive discussion on AI methods and capabilities in the context of edge computing, referred as Edge AI. In a nutshell, we envision Edge AI to provide adaptation for data-driven applications, enhance network and radio access, and allow the creation, optimisation, and deployment of distributed AI/ML pipelines with given quality of experience, trust, security and privacy targets. The Edge AI community investigates novel ML methods for the edge computing environment, spanning multiple sub-fields of computer science, engineering and ICT. The goal is to share an envisioned roadmap that can bring together key actors and enablers to further advance the domain of Edge AI.

KW - 5G Beyond

KW - Edge AI

KW - Edge Computing

KW - Future Cloud

KW - Roadmap

UR - http://www.scopus.com/inward/record.url?scp=85125850007&partnerID=8YFLogxK

U2 - 10.1145/3523230.3523235

DO - 10.1145/3523230.3523235

M3 - Article

AN - SCOPUS:85125850007

SN - 0146-4833

VL - 52

SP - 28

EP - 33

JO - Computer Communication Review

JF - Computer Communication Review

IS - 1

ER -

Roadmap for edge AI: A Dagstuhl Perspective

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this