Energy-Efficient Task Scheduling in Edge–Cloud Environments using Reinforcement Learning
International Journal of Scientific Research in Science, Engineering and Technology · 10.06.2026 · 13 (3) · 392-399
DOI: 10.32628/ijsrset2613351 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Scientific Research in Science, Engineering and Technology, online erschienen am 10.06.2026. Verfasst von Kuruva Vasu und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The rapid proliferation of Internet of Things (IoT) devices has necessitated the development of efficient computation offloading strategies to satisfy the requirements of latency-sensitive applications. While Cloud computing offers immense processing power, the transmission latency often violates strict deadlines. Conversely, Edge computing reduces latency but is constrained by limited energy and computational resources. This paper proposes an intelligent task scheduling framework utilizing Deep Q-Networks (DQN) to optimize the trade-off between energy consumption and service delay. By modeling the offloading decision process as a Markov Decision Process (MDP), the proposed system dynamically adapts to fluctuating network conditions and task arrival rates. Simulation results demonstrate that the proposed RL-based scheduler significantly outperforms traditional heuristic approaches, achieving optimal load balancing and energy efficiency in heterogeneous Edge–Cloud environments.
Zitieren
APA
Vasu, K., Srinivasulu, K., Kumar, K. Y., Raqeeb, S. A., & Hussain, S. A. (2026). Energy-Efficient Task Scheduling in Edge–Cloud Environments using Reinforcement Learning. International Journal of Scientific Research in Science, Engineering and Technology, 13(3), 392-399. https://doi.org/10.32628/ijsrset2613351
Vancouver
Vasu K, Srinivasulu K, Kumar KY, Raqeeb SA, Hussain SA. Energy-Efficient Task Scheduling in Edge–Cloud Environments using Reinforcement Learning. International Journal of Scientific Research in Science, Engineering and Technology. 2026;13(3):392-399. doi:10.32628/ijsrset2613351
BibTeX
@article{Vasu2026,
author = {Vasu, Kuruva and Srinivasulu, Kamarthi and Kumar, Kendole Yaswanth and Raqeeb, Shaik Abdul and Hussain, Shaik Altaf},
title = {Energy-Efficient Task Scheduling in Edge–Cloud Environments using Reinforcement Learning},
journal = {International Journal of Scientific Research in Science, Engineering and Technology},
year = {2026},
volume = {13},
number = {3},
pages = {392--399},
doi = {10.32628/ijsrset2613351}
}
EUVIMED