A novel energy aware resource allocation algorithm for fog nodes using clipped double deep Q-learning
PeerJ Computer Science · 27.05.2026 · 12 · e3903
DOI: 10.7717/peerj-cs.3903 ↗Kurz gefasst
Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 27.05.2026. Verfasst von C. Anitha und 1 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Fog computing offers low latency for sensitive applications by deploying fog nodes near the edge, thus supporting computation close to Internet of Things (IoT) devices. In this article, we allocate resources by ensuring minimal energy consumption of the fog nodes, which helps to overcome latency and transmission challenges in fog computing while achieving minimal completion time for job requests. The resource manager grants rewards for actions taken, allowing the fog resources to be allocated to tasks using the clipped double deep Q-learning algorithm. However, the latency of the tasks leads to the use of a penalty. This algorithm will move towards a greener environment. Simulation results demonstrate that the proposed allocation algorithm could achieve a considerable performance improvement compared to algorithms in the literature. This algorithm performs better by reducing average energy consumption by 43% compared to other existing methods.
Zitieren
APA
Anitha, C., & Revathy, C. (2026). A novel energy aware resource allocation algorithm for fog nodes using clipped double deep Q-learning. PeerJ Computer Science, 12, e3903. https://doi.org/10.7717/peerj-cs.3903
Vancouver
Anitha C, Revathy C. A novel energy aware resource allocation algorithm for fog nodes using clipped double deep Q-learning. PeerJ Computer Science. 2026;12:e3903. doi:10.7717/peerj-cs.3903
BibTeX
@article{Anitha2026,
author = {Anitha, C. and Revathy, C.},
title = {A novel energy aware resource allocation algorithm for fog nodes using clipped double deep Q-learning},
journal = {PeerJ Computer Science},
year = {2026},
volume = {12},
pages = {e3903},
doi = {10.7717/peerj-cs.3903}
}
EUVIMED