Attention-Driven Graph Convolutional Networks for Deadline-Constrained Virtual Machine Task Allocation in Edge Computing
IEEE Transactions on Consumer Electronics · 2025-05 · 71 (2) · 5595-5605
DOI: 10.1109/tce.2025.3571035 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Consumer Electronics, 2025-05. Verfasst von Ahmad Ali und 5 weiteren Autor:innen. Die Arbeit wurde bisher 63-mal zitiert (Crossref) und nennt 39 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Guangdong Province, Shenzhen Natural Science Fund through the Stable Support Plan Program.
Abstract (Originalsprache)
Effective load balancing is critical in contemporary mobile computing environments to ensure optimal resource utilization and adherence to strict deadlines. This study presents a novel framework for deadline-constrained load balancing, termed DCLD-net, which leverages the integration of Graph Convolutional Networks (GCN) and an attention-based Bidirectional Gated Recurrent Unit (BiGRU). The proposed framework utilizes the spatial modeling capabilities of GCNs to capture intricate network topologies, while the temporal dynamics and attention mechanisms of BiGRU enable the identification of critical patterns in traffic flow data. By incorporating key factors such as sticky sessions, load distribution, content-based factors such as videos or file downloads, instance health checks, and other relevant parameters, the DCLD-net model achieves high accuracy in predicting task schedules. These schedules allocate tasks to virtual machines (VMs), enabling dynamic traffic routing through a load balancer that efficiently assigns tasks. Extensive experimental evaluations demonstrate that the proposed attention-based BiGRU-GCN model significantly outperforms traditional methods in both deadline compliance and load balancing efficiency, offering a robust solution to the challenges of modern cloud computing. Experimental results demonstrate that DCLD-net outperforms traditional methods by 27% in deadline compliance and 29.3% in load balancing efficiency.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Guangdong Province
- Shenzhen Natural Science Fund through the Stable Support Plan Program
- Open Fund of National Engineering Laboratory for Big Data System Computing Technology
Zitieren
APA
Ali, A., Ullah, I., Singh, S. K., Jiang, W., Alturise, F., & Bai, X. (2025). Attention-Driven Graph Convolutional Networks for Deadline-Constrained Virtual Machine Task Allocation in Edge Computing. IEEE Transactions on Consumer Electronics, 71(2), 5595-5605. https://doi.org/10.1109/tce.2025.3571035
Vancouver
Ali A, Ullah I, Singh SK, Jiang W, Alturise F, Bai X. Attention-Driven Graph Convolutional Networks for Deadline-Constrained Virtual Machine Task Allocation in Edge Computing. IEEE Transactions on Consumer Electronics. 2025;71(2):5595-5605. doi:10.1109/tce.2025.3571035
BibTeX
@article{Ali2025,
author = {Ali, Ahmad and Ullah, Inam and Singh, Sushil Kumar and Jiang, Weiwei and Alturise, Fahad and Bai, Xiaoshan},
title = {Attention-Driven Graph Convolutional Networks for Deadline-Constrained Virtual Machine Task Allocation in Edge Computing},
journal = {IEEE Transactions on Consumer Electronics},
year = {2025},
volume = {71},
number = {2},
pages = {5595--5605},
doi = {10.1109/tce.2025.3571035}
}
EUVIMED