Quality Metrics for Reinforcement Learning for Edge Cloud and Internet-of-Things Systems

Claus Pahl, Hamid Barzegar

2023

Abstract

Computation at the edge or within the Internet-of-Things (IoT) requires the use of controllers to make the management of resources in this setting self-adaptive. Controllers are software that observe a system, analyse its quality and recommend and enact decisions to maintain or improve quality. Today, often reinforcement learning (RL) that operates on a notion of reward is used to construct these controllers. Here, we investigate quality metrics and quality management processes for RL-constructed controllers for edge and IoT settings. We introduce RL and control principles and define a quality-oriented controller reference architecture. This forms the based for the central contribution, a quality analysis metrics framework, embedded into a quality management process.

Paper Citation

in Harvard Style

Pahl C. and Barzegar H. (2023). Quality Metrics for Reinforcement Learning for Edge Cloud and Internet-of-Things Systems. In Proceedings of the 19th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST; ISBN 978-989-758-672-9, SciTePress, pages 355-364. DOI: 10.5220/0012194800003584

in Bibtex Style

@conference{webist23,
author={Claus Pahl and Hamid Barzegar},
title={Quality Metrics for Reinforcement Learning for Edge Cloud and Internet-of-Things Systems},
booktitle={Proceedings of the 19th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST},
year={2023},
pages={355-364},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012194800003584},
isbn={978-989-758-672-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Conference on Web Information Systems and Technologies - Volume 1: WEBIST
TI - Quality Metrics for Reinforcement Learning for Edge Cloud and Internet-of-Things Systems
SN - 978-989-758-672-9
AU - Pahl C.
AU - Barzegar H.
PY - 2023
SP - 355
EP - 364
DO - 10.5220/0012194800003584
PB - SciTePress