Real-Time Adaptive Workflow Scheduling With Graph Learning and Transformer-Driven Reinforcement in Heterogeneous Clouds
IEEE Transactions on Cloud Computing · 2026-01 · 14 (1) · 376-390
DOI: 10.1109/tcc.2025.3642240 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Cloud Computing, 2026-01. Verfasst von Fan Ding und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 46 Literaturangaben.
Abstract (Originalsprache)
Scheduling workflows with complex dependencies under dynamic resource availability in heterogeneous clouds remains highly challenging. Static and heuristic methods often fail to adapt to workload and resource changes, resulting in higher makespan, lower utilization, and increased cost. We propose GDST-PPO, a graph-based dynamic scheduling framework that encodes workflow DAGs with a GNN, models temporal and resource contexts via a Transformer with sparse attention, and optimizes decisions using PPO with a multi-objective reward. We perform extensive experiments on five benchmark workflows under realistic heterogeneous cloud settings. Across six baselines, GDST-PPO achieves up to 10.3% lower makespan, 18.1% higher resource utilization, and an 11.4% gain in overall score. In absolute terms, it attains a makespan of 7,168,820 s, resource utilization of 39.55%, and an overall score of 6.62 on our benchmark, demonstrating efficient, flexible, and cost-effective cloud workflow management.
Zitieren
APA
Ding, F., & Wang, H. (2026). Real-Time Adaptive Workflow Scheduling With Graph Learning and Transformer-Driven Reinforcement in Heterogeneous Clouds. IEEE Transactions on Cloud Computing, 14(1), 376-390. https://doi.org/10.1109/tcc.2025.3642240
Vancouver
Ding F, Wang H. Real-Time Adaptive Workflow Scheduling With Graph Learning and Transformer-Driven Reinforcement in Heterogeneous Clouds. IEEE Transactions on Cloud Computing. 2026;14(1):376-390. doi:10.1109/tcc.2025.3642240
BibTeX
@article{Ding2026,
author = {Ding, Fan and Wang, Houxiang},
title = {Real-Time Adaptive Workflow Scheduling With Graph Learning and Transformer-Driven Reinforcement in Heterogeneous Clouds},
journal = {IEEE Transactions on Cloud Computing},
year = {2026},
volume = {14},
number = {1},
pages = {376--390},
doi = {10.1109/tcc.2025.3642240}
}
EUVIMED