Platform-Agnostic MLOps on Edge, Fog and Cloud Platforms in Industrial IoT

Alexander Keusch, Thomas Blumauer-Hiessl, Alireza Furutanpey, Daniel Schall, Schahram Dustdar

2024

Abstract

The proliferation of edge computing systems drives the need for comprehensive frameworks that can seamlessly deploy machine learning models across edge, fog, and cloud layers. This work presents a platform-agnostic Machine Learning Operations (MLOps) framework tailored for industrial applications. A novel framework enables data scientists in an industrial setting to develop and deploy AI solutions across diverse deployment modes while providing a consistent experience. We evaluate our framework on real-world industrial data by collecting performance metrics and energy measurements on training and prediction runs of two ML workflows. Then, we compare edge, fog, and cloud deployments and highlight the advantages and limitations of each deployment mode. Our results emphasize the relevance of the introduced platform-agnostic MLOps frameworks in enabling flexible and efficient AI deployments.

Paper Citation

in Harvard Style

Keusch A., Blumauer-Hiessl T., Furutanpey A., Schall D. and Dustdar S. (2024). Platform-Agnostic MLOps on Edge, Fog and Cloud Platforms in Industrial IoT. In Proceedings of the 20th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST; ISBN 978-989-758-718-4, SciTePress, pages 71-79. DOI: 10.5220/0012977500003825

in Bibtex Style

@conference{webist24,
author={Alexander Keusch and Thomas Blumauer-Hiessl and Alireza Furutanpey and Daniel Schall and Schahram Dustdar},
title={Platform-Agnostic MLOps on Edge, Fog and Cloud Platforms in Industrial IoT},
booktitle={Proceedings of the 20th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST},
year={2024},
pages={71-79},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012977500003825},
isbn={978-989-758-718-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST
TI - Platform-Agnostic MLOps on Edge, Fog and Cloud Platforms in Industrial IoT
SN - 978-989-758-718-4
AU - Keusch A.
AU - Blumauer-Hiessl T.
AU - Furutanpey A.
AU - Schall D.
AU - Dustdar S.
PY - 2024
SP - 71
EP - 79
DO - 10.5220/0012977500003825
PB - SciTePress