Edge MLOps: An Automation Framework for AIoT Applications

Emmanuel Raj; David Buffoni; Magnus Westerlund; Kimmo Ahola

doi:10.1109/IC2E52221.2021.00034

Edge MLOps: An Automation Framework for AIoT Applications

Emmanuel Raj, David Buffoni, Magnus Westerlund, Kimmo Ahola

BA6402 Future communication networks

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

34 Citations (Scopus)

Abstract

Artificial Intelligence of Things (AIoT) is the combination of artificial intelligence (AI) technologies with the Internet of Things (IoT) infrastructure to achieve more efficient IoT operations and decision making. Edge computing is emerging to enable AIoT applications. In this paper, we develop an Edge MLOps framework for automating Machine Learning at the edge, enabling continuous model training, deployment, delivery and monitoring. To achieve this, we synergize cloud and edge environments. We experimentally validate our framework on a forecasting air quality situation. During validation, the framework showed stability and automatically retrained, integrated, and deployed models for specific environments when their performance deteriorated under a certain threshold.

Original language	English
Title of host publication	2021 IEEE International Conference on Cloud Engineering (IC2E)
Publisher	IEEE Institute of Electrical and Electronic Engineers
Pages	191-200
Number of pages	10
ISBN (Electronic)	978-1-6654-4970-0
ISBN (Print)	978-1-6654-4971-7
DOIs	https://doi.org/10.1109/IC2E52221.2021.00034
Publication status	Published - 8 Oct 2021
MoE publication type	A4 Article in a conference publication
Event	IEEE International Conference on Cloud Engineering, IC2E 2021 - San Francisco, CA, USA Duration: 4 Oct 2021 → 8 Oct 2021

Conference

Conference	IEEE International Conference on Cloud Engineering, IC2E 2021
Period	4/10/21 → 8/10/21

Keywords

Training
Cloud computing
Automation
Atmospheric modeling
Computational modeling
Pipelines
Collaborative work
Edge Computing
AI
Digital Transformation
Machine Learning
IoT
MLOps
5G Networks

Access to Document

10.1109/IC2E52221.2021.00034

Cite this

@inproceedings{075c9f456e394a18b9c1f08fce96b8ce,

title = "Edge MLOps: An Automation Framework for AIoT Applications",

abstract = "Artificial Intelligence of Things (AIoT) is the combination of artificial intelligence (AI) technologies with the Internet of Things (IoT) infrastructure to achieve more efficient IoT operations and decision making. Edge computing is emerging to enable AIoT applications. In this paper, we develop an Edge MLOps framework for automating Machine Learning at the edge, enabling continuous model training, deployment, delivery and monitoring. To achieve this, we synergize cloud and edge environments. We experimentally validate our framework on a forecasting air quality situation. During validation, the framework showed stability and automatically retrained, integrated, and deployed models for specific environments when their performance deteriorated under a certain threshold.",

keywords = "Training, Cloud computing, Automation, Atmospheric modeling, Computational modeling, Pipelines, Collaborative work, Edge Computing, AI, Digital Transformation, Machine Learning, IoT, MLOps, 5G Networks",

author = "Emmanuel Raj and David Buffoni and Magnus Westerlund and Kimmo Ahola",

note = "This work is supported by TietoEVRY and the 5G-FORCE project “6388/31/2018 5G-FORCE” (www.5g-force.org).; IEEE International Conference on Cloud Engineering, IC2E 2021 ; Conference date: 04-10-2021 Through 08-10-2021",

year = "2021",

month = oct,

day = "8",

doi = "10.1109/IC2E52221.2021.00034",

language = "English",

isbn = "978-1-6654-4971-7",

pages = "191--200",

booktitle = "2021 IEEE International Conference on Cloud Engineering (IC2E)",

publisher = "IEEE Institute of Electrical and Electronic Engineers",

address = "United States",

}

Raj, E, Buffoni, D, Westerlund, M & Ahola, K 2021, Edge MLOps: An Automation Framework for AIoT Applications. in 2021 IEEE International Conference on Cloud Engineering (IC2E)., 9610376, IEEE Institute of Electrical and Electronic Engineers, pp. 191-200, IEEE International Conference on Cloud Engineering, IC2E 2021, 4/10/21. https://doi.org/10.1109/IC2E52221.2021.00034

Edge MLOps: An Automation Framework for AIoT Applications. / Raj, Emmanuel; Buffoni, David; Westerlund, Magnus et al.
2021 IEEE International Conference on Cloud Engineering (IC2E). IEEE Institute of Electrical and Electronic Engineers, 2021. p. 191-200 9610376.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Edge MLOps: An Automation Framework for AIoT Applications

AU - Raj, Emmanuel

AU - Buffoni, David

AU - Westerlund, Magnus

AU - Ahola, Kimmo

N1 - This work is supported by TietoEVRY and the 5G-FORCE project “6388/31/2018 5G-FORCE” (www.5g-force.org).

PY - 2021/10/8

Y1 - 2021/10/8

N2 - Artificial Intelligence of Things (AIoT) is the combination of artificial intelligence (AI) technologies with the Internet of Things (IoT) infrastructure to achieve more efficient IoT operations and decision making. Edge computing is emerging to enable AIoT applications. In this paper, we develop an Edge MLOps framework for automating Machine Learning at the edge, enabling continuous model training, deployment, delivery and monitoring. To achieve this, we synergize cloud and edge environments. We experimentally validate our framework on a forecasting air quality situation. During validation, the framework showed stability and automatically retrained, integrated, and deployed models for specific environments when their performance deteriorated under a certain threshold.

AB - Artificial Intelligence of Things (AIoT) is the combination of artificial intelligence (AI) technologies with the Internet of Things (IoT) infrastructure to achieve more efficient IoT operations and decision making. Edge computing is emerging to enable AIoT applications. In this paper, we develop an Edge MLOps framework for automating Machine Learning at the edge, enabling continuous model training, deployment, delivery and monitoring. To achieve this, we synergize cloud and edge environments. We experimentally validate our framework on a forecasting air quality situation. During validation, the framework showed stability and automatically retrained, integrated, and deployed models for specific environments when their performance deteriorated under a certain threshold.

KW - Training

KW - Cloud computing

KW - Automation

KW - Atmospheric modeling

KW - Computational modeling

KW - Pipelines

KW - Collaborative work

KW - Edge Computing

KW - AI

KW - Digital Transformation

KW - Machine Learning

KW - IoT

KW - MLOps

KW - 5G Networks

UR - http://www.scopus.com/inward/record.url?scp=85123212543&partnerID=8YFLogxK

U2 - 10.1109/IC2E52221.2021.00034

DO - 10.1109/IC2E52221.2021.00034

M3 - Conference article in proceedings

SN - 978-1-6654-4971-7

SP - 191

EP - 200

BT - 2021 IEEE International Conference on Cloud Engineering (IC2E)

PB - IEEE Institute of Electrical and Electronic Engineers

T2 - IEEE International Conference on Cloud Engineering, IC2E 2021

Y2 - 4 October 2021 through 8 October 2021

ER -

Edge MLOps: An Automation Framework for AIoT Applications

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this