Reinforcement Learning for Multi-Objective Task Placement on Heterogeneous Architectures with Real-Time Constraints

Bakhta Haouari, Bakhta Haouari, Bakhta Haouari, Rania Mzid, Rania Mzid, Olfa Mosbahi

2024

Abstract

This paper introduces a novel approach for multi-objective task placement on heterogeneous architectures in real-time embedded systems. The primary objective of task placement is to identify optimal deployment models that assign each task to a processor while considering multiple optimization criteria. Given the NP-hard nature of the task placement problem, various techniques, including Mixed Integer Linear Programming and genetic algorithms, have been traditionally employed for efficient resolution. In this paper, we explore the use of reinforcement learning to solve the task placement problem. We initially modeled this problem as a Markov Decision Process. Then, we leverage the Pareto Q-learning algorithm to approximate Pareto front solutions, balancing system extensibility and energy efficiency. The application of the proposed method to real-world case studies showcases its effectiveness in task placement problem resolution, enabling rapid adaptation to designer adjustments compared to related works.

Paper Citation

in Harvard Style

Haouari B., Mzid R. and Mosbahi O. (2024). Reinforcement Learning for Multi-Objective Task Placement on Heterogeneous Architectures with Real-Time Constraints. In Proceedings of the 19th International Conference on Evaluation of Novel Approaches to Software Engineering - Volume 1: ENASE; ISBN 978-989-758-696-5, SciTePress, pages 179-189. DOI: 10.5220/0012721500003687

in Bibtex Style

@conference{enase24,
author={Bakhta Haouari and Rania Mzid and Olfa Mosbahi},
title={Reinforcement Learning for Multi-Objective Task Placement on Heterogeneous Architectures with Real-Time Constraints},
booktitle={Proceedings of the 19th International Conference on Evaluation of Novel Approaches to Software Engineering - Volume 1: ENASE},
year={2024},
pages={179-189},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012721500003687},
isbn={978-989-758-696-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Conference on Evaluation of Novel Approaches to Software Engineering - Volume 1: ENASE
TI - Reinforcement Learning for Multi-Objective Task Placement on Heterogeneous Architectures with Real-Time Constraints
SN - 978-989-758-696-5
AU - Haouari B.
AU - Mzid R.
AU - Mosbahi O.
PY - 2024
SP - 179
EP - 189
DO - 10.5220/0012721500003687
PB - SciTePress