A Q-Learning Approach for Workflow Scheduling in Edge Computing Systems

Elarbi Badidi

doi:10.1007/978-3-031-74470-9_6

A Q-Learning Approach for Workflow Scheduling in Edge Computing Systems

Elarbi Badidi

Department of Computer Science and Software Engineering

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

Abstract

In edge computing applications, it is a common practice to employ cloud resources for data processing. However, latency-sensitive applications encounter hurdles due to limitations in network bandwidth and the latency associated with cloud data processing. Efficient task scheduling algorithms play a crucial role in effectively allocating resources for executing workflows in edge computing environments and tackling associated challenges. This paper aims to evaluate the performance of the Q-learning algorithm in edge computing, with a specific emphasis on the Montage workflow as a case study. Our simulation environment compares the Q-learning algorithm against traditional scheduling approaches using the overall workflow task completion time and energy consumption performance metrics. Our experimental findings offer valuable insights into the efficacy of the Q-learning algorithm within edge computing environments.

Original language	English
Title of host publication	Communication and Information Technologies through the Lens of Innovation - Proceeding of the 5th International Conference on Advanced technologies and Humanity ICATH 2023
Editors	Saliha Assoul, Brahim El Bhiri, Rajaa Saidi, Ebobisse Djene Yves Frederic
Publisher	Springer Nature
Pages	45-52
Number of pages	8
ISBN (Print)	9783031744693
DOIs	https://doi.org/10.1007/978-3-031-74470-9_6
Publication status	Published - 2025
Event	5th International Conference on Advanced technologies and Humanity, ICATH 2023 - Rabat, Morocco Duration: Dec 25 2023 → Dec 26 2023

Publication series

Name	Advances in Science, Technology and Innovation
ISSN (Print)	2522-8714
ISSN (Electronic)	2522-8722

Conference

Conference	5th International Conference on Advanced technologies and Humanity, ICATH 2023
Country/Territory	Morocco
City	Rabat
Period	12/25/23 → 12/26/23

Keywords

Edge computing
Montage workflow
Reinforcement learning
Task scheduling

ASJC Scopus subject areas

Architecture
Environmental Chemistry
Renewable Energy, Sustainability and the Environment

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-031-74470-9_6

Cite this

Badidi, E. (2025). A Q-Learning Approach for Workflow Scheduling in Edge Computing Systems. In S. Assoul, B. El Bhiri, R. Saidi, & E. D. Yves Frederic (Eds.), Communication and Information Technologies through the Lens of Innovation - Proceeding of the 5th International Conference on Advanced technologies and Humanity ICATH 2023 (pp. 45-52). (Advances in Science, Technology and Innovation). Springer Nature. https://doi.org/10.1007/978-3-031-74470-9_6

A Q-Learning Approach for Workflow Scheduling in Edge Computing Systems. / Badidi, Elarbi.
Communication and Information Technologies through the Lens of Innovation - Proceeding of the 5th International Conference on Advanced technologies and Humanity ICATH 2023. ed. / Saliha Assoul; Brahim El Bhiri; Rajaa Saidi; Ebobisse Djene Yves Frederic. Springer Nature, 2025. p. 45-52 (Advances in Science, Technology and Innovation).

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

Badidi, E 2025, A Q-Learning Approach for Workflow Scheduling in Edge Computing Systems. in S Assoul, B El Bhiri, R Saidi & ED Yves Frederic (eds), Communication and Information Technologies through the Lens of Innovation - Proceeding of the 5th International Conference on Advanced technologies and Humanity ICATH 2023. Advances in Science, Technology and Innovation, Springer Nature, pp. 45-52, 5th International Conference on Advanced technologies and Humanity, ICATH 2023, Rabat, Morocco, 12/25/23. https://doi.org/10.1007/978-3-031-74470-9_6

Badidi E. A Q-Learning Approach for Workflow Scheduling in Edge Computing Systems. In Assoul S, El Bhiri B, Saidi R, Yves Frederic ED, editors, Communication and Information Technologies through the Lens of Innovation - Proceeding of the 5th International Conference on Advanced technologies and Humanity ICATH 2023. Springer Nature. 2025. p. 45-52. (Advances in Science, Technology and Innovation). doi: 10.1007/978-3-031-74470-9_6

Badidi, Elarbi. / A Q-Learning Approach for Workflow Scheduling in Edge Computing Systems. Communication and Information Technologies through the Lens of Innovation - Proceeding of the 5th International Conference on Advanced technologies and Humanity ICATH 2023. editor / Saliha Assoul ; Brahim El Bhiri ; Rajaa Saidi ; Ebobisse Djene Yves Frederic. Springer Nature, 2025. pp. 45-52 (Advances in Science, Technology and Innovation).

@inproceedings{58f36b7bb2064e1689668bbeacf30171,

title = "A Q-Learning Approach for Workflow Scheduling in Edge Computing Systems",

abstract = "In edge computing applications, it is a common practice to employ cloud resources for data processing. However, latency-sensitive applications encounter hurdles due to limitations in network bandwidth and the latency associated with cloud data processing. Efficient task scheduling algorithms play a crucial role in effectively allocating resources for executing workflows in edge computing environments and tackling associated challenges. This paper aims to evaluate the performance of the Q-learning algorithm in edge computing, with a specific emphasis on the Montage workflow as a case study. Our simulation environment compares the Q-learning algorithm against traditional scheduling approaches using the overall workflow task completion time and energy consumption performance metrics. Our experimental findings offer valuable insights into the efficacy of the Q-learning algorithm within edge computing environments.",

keywords = "Edge computing, Montage workflow, Reinforcement learning, Task scheduling",

author = "Elarbi Badidi",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.; 5th International Conference on Advanced technologies and Humanity, ICATH 2023 ; Conference date: 25-12-2023 Through 26-12-2023",

year = "2025",

doi = "10.1007/978-3-031-74470-9\_6",

language = "English",

isbn = "9783031744693",

series = "Advances in Science, Technology and Innovation",

publisher = "Springer Nature",

pages = "45--52",

editor = "Saliha Assoul and \{El Bhiri\}, Brahim and Rajaa Saidi and \{Yves Frederic\}, \{Ebobisse Djene\}",

booktitle = "Communication and Information Technologies through the Lens of Innovation - Proceeding of the 5th International Conference on Advanced technologies and Humanity ICATH 2023",

address = "United States",

}

TY - GEN

T1 - A Q-Learning Approach for Workflow Scheduling in Edge Computing Systems

AU - Badidi, Elarbi

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

PY - 2025

Y1 - 2025

N2 - In edge computing applications, it is a common practice to employ cloud resources for data processing. However, latency-sensitive applications encounter hurdles due to limitations in network bandwidth and the latency associated with cloud data processing. Efficient task scheduling algorithms play a crucial role in effectively allocating resources for executing workflows in edge computing environments and tackling associated challenges. This paper aims to evaluate the performance of the Q-learning algorithm in edge computing, with a specific emphasis on the Montage workflow as a case study. Our simulation environment compares the Q-learning algorithm against traditional scheduling approaches using the overall workflow task completion time and energy consumption performance metrics. Our experimental findings offer valuable insights into the efficacy of the Q-learning algorithm within edge computing environments.

AB - In edge computing applications, it is a common practice to employ cloud resources for data processing. However, latency-sensitive applications encounter hurdles due to limitations in network bandwidth and the latency associated with cloud data processing. Efficient task scheduling algorithms play a crucial role in effectively allocating resources for executing workflows in edge computing environments and tackling associated challenges. This paper aims to evaluate the performance of the Q-learning algorithm in edge computing, with a specific emphasis on the Montage workflow as a case study. Our simulation environment compares the Q-learning algorithm against traditional scheduling approaches using the overall workflow task completion time and energy consumption performance metrics. Our experimental findings offer valuable insights into the efficacy of the Q-learning algorithm within edge computing environments.

KW - Edge computing

KW - Montage workflow

KW - Reinforcement learning

KW - Task scheduling

UR - http://www.scopus.com/inward/record.url?scp=105002563652&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=105002563652&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-74470-9_6

DO - 10.1007/978-3-031-74470-9_6

M3 - Conference contribution

AN - SCOPUS:105002563652

SN - 9783031744693

T3 - Advances in Science, Technology and Innovation

SP - 45

EP - 52

BT - Communication and Information Technologies through the Lens of Innovation - Proceeding of the 5th International Conference on Advanced technologies and Humanity ICATH 2023

A2 - Assoul, Saliha

A2 - El Bhiri, Brahim

A2 - Saidi, Rajaa

A2 - Yves Frederic, Ebobisse Djene

PB - Springer Nature

T2 - 5th International Conference on Advanced technologies and Humanity, ICATH 2023

Y2 - 25 December 2023 through 26 December 2023

ER -