A Multi-Agent RL Algorithm for Dynamic Task Offloading in D2D-MEC Network with Energy Harvesting
Sensors · 26.04.2024 · 24 (9) · 2779
DOI: 10.3390/s24092779 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 26.04.2024. Verfasst von Xin Mi und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer, Zhongshan Institute, University of Electronic Science and Technology of China, Zhognshan 528400, China. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Foundation of Guangdong Province, China, Science and Technology Foundation of Guangdong Province.
Abstract (Originalsprache)
Delay-sensitive task offloading in a device-to-device assisted mobile edge computing (D2D-MEC) system with energy harvesting devices is a critical challenge due to the dynamic load level at edge nodes and the variability in harvested energy. In this paper, we propose a joint dynamic task offloading and CPU frequency control scheme for delay-sensitive tasks in a D2D-MEC system, taking into account the intricacies of multi-slot tasks, characterized by diverse processing speeds and data transmission rates. Our methodology involves meticulous modeling of task arrival and service processes using queuing systems, coupled with the strategic utilization of D2D communication to alleviate edge server load and prevent network congestion effectively. Central to our solution is the formulation of average task delay optimization as a challenging nonlinear integer programming problem, requiring intelligent decision making regarding task offloading for each generated task at active mobile devices and CPU frequency adjustments at discrete time slots. To navigate the intricate landscape of the extensive discrete action space, we design an efficient multi-agent DRL learning algorithm named MAOC, which is based on MAPPO, to minimize the average task delay by dynamically determining task-offloading decisions and CPU frequencies. MAOC operates within a centralized training with decentralized execution (CTDE) framework, empowering individual mobile devices to make decisions autonomously based on their unique system states. Experimental results demonstrate its swift convergence and operational efficiency, and it outperforms other baseline algorithms.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Computer, Zhongshan Institute, University of Electronic Science and Technology of China, Zhognshan 528400, China.
- Engineering and Technology, Central Queensland University, Brisbane 4000, Australia.
ORCID-Profile: Huaiwen He
Förderung
- Science and Technology Foundation of Guangdong Province, China
- Science and Technology Foundation of Guangdong Province
Zitieren
APA
Mi, X., He, H., & Shen, H. (2024). A Multi-Agent RL Algorithm for Dynamic Task Offloading in D2D-MEC Network with Energy Harvesting. Sensors, 24(9), 2779. https://doi.org/10.3390/s24092779
Vancouver
Mi X, He H, Shen H. A Multi-Agent RL Algorithm for Dynamic Task Offloading in D2D-MEC Network with Energy Harvesting. Sensors. 2024;24(9):2779. doi:10.3390/s24092779
BibTeX
@article{Mi2024,
author = {Mi, Xin and He, Huaiwen and Shen, Hong},
title = {A Multi-Agent RL Algorithm for Dynamic Task Offloading in D2D-MEC Network with Energy Harvesting},
journal = {Sensors},
year = {2024},
volume = {24},
number = {9},
pages = {2779},
doi = {10.3390/s24092779}
}
EUVIMED