Downtime Minimization for Real-time AI Service on Intelligent Edge Nodes: Micro-Renewal Method

Seungjun Hong; Seung Jin Lee; Inhun Choi; Eui Nam Huh

doi:10.1109/ICECE54449.2021.9674707

Downtime Minimization for Real-time AI Service on Intelligent Edge Nodes: Micro-Renewal Method

Seungjun Hong
, Seung Jin Lee
, Inhun Choi
, Eui Nam Huh

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

As the innovation of computing infrastructure evolves to edge computing via cloud computing, intelligent devices such as robots, drones, and autonomous vehicles, which are mobile edge nodes, also surged. Since the edge nodes have limited resources, artificial intelligence services are provided based on lightweight containers. In addition, as intelligent edge node users increase and the categories of users become vast, in order to provide artificial intelligence services according to the situations of all users, data on each situation is collected, and it is necessary to continuously update the learning model. However, if the service is being provided, downtime is inevitable for the updated model to be applied to the service. Therefore, in this paper, we propose a micro-renewal method that minimizes the interruption of the service provided to users in real time when the learning model in the service is updated.

Original language	English
Title of host publication	2021 IEEE 4th International Conference on Electronics and Communication Engineering, ICECE 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	347-351
Number of pages	5
ISBN (Electronic)	9781728194226
DOIs	https://doi.org/10.1109/ICECE54449.2021.9674707
Publication status	Published - 2021
Event	4th IEEE International Conference on Electronics and Communication Engineering, ICECE 2021 - Virtual, Xi'an, China Duration: 17 Dec 2021 → 19 Dec 2021

Publication series

Name	2021 IEEE 4th International Conference on Electronics and Communication Engineering, ICECE 2021

Conference

Conference	4th IEEE International Conference on Electronics and Communication Engineering, ICECE 2021
Country/Territory	China
City	Virtual, Xi'an
Period	17/12/21 → 19/12/21

Bibliographical note

Publisher Copyright:
©2021 IEEE

Keywords

Containerservicedowntime
Intelligent edge nodes
Real-timemodelupdate
artificial intelligent services

Access to Document

10.1109/ICECE54449.2021.9674707

Cite this

Hong, S., Lee, S. J., Choi, I., & Huh, E. N. (2021). Downtime Minimization for Real-time AI Service on Intelligent Edge Nodes: Micro-Renewal Method. In 2021 IEEE 4th International Conference on Electronics and Communication Engineering, ICECE 2021 (pp. 347-351). (2021 IEEE 4th International Conference on Electronics and Communication Engineering, ICECE 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICECE54449.2021.9674707

Hong, Seungjun ; Lee, Seung Jin ; Choi, Inhun et al. / Downtime Minimization for Real-time AI Service on Intelligent Edge Nodes : Micro-Renewal Method. 2021 IEEE 4th International Conference on Electronics and Communication Engineering, ICECE 2021. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 347-351 (2021 IEEE 4th International Conference on Electronics and Communication Engineering, ICECE 2021).

@inproceedings{44b5d995405548718d038ae02717fe8c,

title = "Downtime Minimization for Real-time AI Service on Intelligent Edge Nodes: Micro-Renewal Method",

abstract = "As the innovation of computing infrastructure evolves to edge computing via cloud computing, intelligent devices such as robots, drones, and autonomous vehicles, which are mobile edge nodes, also surged. Since the edge nodes have limited resources, artificial intelligence services are provided based on lightweight containers. In addition, as intelligent edge node users increase and the categories of users become vast, in order to provide artificial intelligence services according to the situations of all users, data on each situation is collected, and it is necessary to continuously update the learning model. However, if the service is being provided, downtime is inevitable for the updated model to be applied to the service. Therefore, in this paper, we propose a micro-renewal method that minimizes the interruption of the service provided to users in real time when the learning model in the service is updated.",

keywords = "Containerservicedowntime, Intelligent edge nodes, Real-timemodelupdate, artificial intelligent services",

author = "Seungjun Hong and Lee, \{Seung Jin\} and Inhun Choi and Huh, \{Eui Nam\}",

note = "Publisher Copyright: {\textcopyright}2021 IEEE; 4th IEEE International Conference on Electronics and Communication Engineering, ICECE 2021 ; Conference date: 17-12-2021 Through 19-12-2021",

year = "2021",

doi = "10.1109/ICECE54449.2021.9674707",

language = "English",

series = "2021 IEEE 4th International Conference on Electronics and Communication Engineering, ICECE 2021",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "347--351",

booktitle = "2021 IEEE 4th International Conference on Electronics and Communication Engineering, ICECE 2021",

address = "United States",

}

Hong, S, Lee, SJ, Choi, I & Huh, EN 2021, Downtime Minimization for Real-time AI Service on Intelligent Edge Nodes: Micro-Renewal Method. in 2021 IEEE 4th International Conference on Electronics and Communication Engineering, ICECE 2021. 2021 IEEE 4th International Conference on Electronics and Communication Engineering, ICECE 2021, Institute of Electrical and Electronics Engineers Inc., pp. 347-351, 4th IEEE International Conference on Electronics and Communication Engineering, ICECE 2021, Virtual, Xi'an, China, 17/12/21. https://doi.org/10.1109/ICECE54449.2021.9674707

Downtime Minimization for Real-time AI Service on Intelligent Edge Nodes: Micro-Renewal Method. / Hong, Seungjun; Lee, Seung Jin; Choi, Inhun et al.
2021 IEEE 4th International Conference on Electronics and Communication Engineering, ICECE 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 347-351 (2021 IEEE 4th International Conference on Electronics and Communication Engineering, ICECE 2021).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Downtime Minimization for Real-time AI Service on Intelligent Edge Nodes

T2 - 4th IEEE International Conference on Electronics and Communication Engineering, ICECE 2021

AU - Hong, Seungjun

AU - Lee, Seung Jin

AU - Choi, Inhun

AU - Huh, Eui Nam

PY - 2021

Y1 - 2021

N2 - As the innovation of computing infrastructure evolves to edge computing via cloud computing, intelligent devices such as robots, drones, and autonomous vehicles, which are mobile edge nodes, also surged. Since the edge nodes have limited resources, artificial intelligence services are provided based on lightweight containers. In addition, as intelligent edge node users increase and the categories of users become vast, in order to provide artificial intelligence services according to the situations of all users, data on each situation is collected, and it is necessary to continuously update the learning model. However, if the service is being provided, downtime is inevitable for the updated model to be applied to the service. Therefore, in this paper, we propose a micro-renewal method that minimizes the interruption of the service provided to users in real time when the learning model in the service is updated.

AB - As the innovation of computing infrastructure evolves to edge computing via cloud computing, intelligent devices such as robots, drones, and autonomous vehicles, which are mobile edge nodes, also surged. Since the edge nodes have limited resources, artificial intelligence services are provided based on lightweight containers. In addition, as intelligent edge node users increase and the categories of users become vast, in order to provide artificial intelligence services according to the situations of all users, data on each situation is collected, and it is necessary to continuously update the learning model. However, if the service is being provided, downtime is inevitable for the updated model to be applied to the service. Therefore, in this paper, we propose a micro-renewal method that minimizes the interruption of the service provided to users in real time when the learning model in the service is updated.

KW - Containerservicedowntime

KW - Intelligent edge nodes

KW - Real-timemodelupdate

KW - artificial intelligent services

UR - https://www.scopus.com/pages/publications/85125170812

U2 - 10.1109/ICECE54449.2021.9674707

DO - 10.1109/ICECE54449.2021.9674707

M3 - Conference contribution

AN - SCOPUS:85125170812

T3 - 2021 IEEE 4th International Conference on Electronics and Communication Engineering, ICECE 2021

SP - 347

EP - 351

BT - 2021 IEEE 4th International Conference on Electronics and Communication Engineering, ICECE 2021

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 17 December 2021 through 19 December 2021

ER -

Hong S, Lee SJ, Choi I, Huh EN. Downtime Minimization for Real-time AI Service on Intelligent Edge Nodes: Micro-Renewal Method. In 2021 IEEE 4th International Conference on Electronics and Communication Engineering, ICECE 2021. Institute of Electrical and Electronics Engineers Inc. 2021. p. 347-351. (2021 IEEE 4th International Conference on Electronics and Communication Engineering, ICECE 2021). doi: 10.1109/ICECE54449.2021.9674707

Downtime Minimization for Real-time AI Service on Intelligent Edge Nodes: Micro-Renewal Method

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this