EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Energy and Delay Optimized Task Offloading Framework in Edge Computing Using DDPG with Dual Critic Attention and Uncertainty-Aware Experience Replay

Srinivas Byatarayanpura Venkataswamy, Vinutha Krishnaiah, S. Veena, Manjula H. Nebagiri

Cybernetics and Information Technologies · 01.03.2026 · 26 (1) · 55-71

DOI: 10.2478/cait-2026-0004 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cybernetics and Information Technologies, online erschienen am 21.03.2026. Verfasst von Srinivas Byatarayanpura Venkataswamy und 3 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The increase in Internet of Things (IoT) devices has increased demand for effective and reliable task offloading strategies in edge-computing environments. These systems struggle to balance limited computational resources, varying network conditions, and complex dependencies between subtasks. To address these challenges, this article developed a task offloading framework using the Deep Deterministic Policy Gradient (DDPG) algorithm with Uncertainty-aware Prioritized Experience Replay (UPER) and Dual Critic Attention (DCA) mechanism. The task offloading issue is modeled as a Markov Decision Process (MDP), in which agents learn optimal policies to minimize delay and energy consumption while ensuring high task success rates. The UPER module enhances learning efficacy by sampling transitions with high epistemic uncertainty and temporal difference errors, allowing the DCA component to dynamically balance energy and latency objectives using dual-critic networks. The simulation results show that the proposed model outperforms existing algorithms in terms of offload success rate and minimization of average delay and energy consumption.

Zitieren

APA

Venkataswamy, S. B., Krishnaiah, V., Veena, S., & Nebagiri, M. H. (2026). Energy and Delay Optimized Task Offloading Framework in Edge Computing Using DDPG with Dual Critic Attention and Uncertainty-Aware Experience Replay. Cybernetics and Information Technologies, 26(1), 55-71. https://doi.org/10.2478/cait-2026-0004

Vancouver

Venkataswamy SB, Krishnaiah V, Veena S, Nebagiri MH. Energy and Delay Optimized Task Offloading Framework in Edge Computing Using DDPG with Dual Critic Attention and Uncertainty-Aware Experience Replay. Cybernetics and Information Technologies. 2026;26(1):55-71. doi:10.2478/cait-2026-0004

BibTeX
@article{Venkataswamy2026,
  author = {Venkataswamy, Srinivas Byatarayanpura and Krishnaiah, Vinutha and Veena, S. and Nebagiri, Manjula H.},
  title = {Energy and Delay Optimized Task Offloading Framework in Edge Computing Using DDPG with Dual Critic Attention and Uncertainty-Aware Experience Replay},
  journal = {Cybernetics and Information Technologies},
  year = {2026},
  volume = {26},
  number = {1},
  pages = {55--71},
  doi = {10.2478/cait-2026-0004}
}
Kostenlos starten →