ReflexPilot: Startup-Aware Dependent Task Scheduling Based on Deep Reinforcement Learning for Edge-Cloud Collaborative Computing
IEEE Transactions on Cloud Computing · 2025-04 · 13 (2) · 641-654
DOI: 10.1109/tcc.2025.3555231 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Cloud Computing, 2025-04. Verfasst von Wenhao Zou und 4 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Pilot for Major Scientific Research Facility of Jiangsu Province of China.
Abstract (Originalsprache)
With the increasing number of devices, the demand for data computation is growing rapidly. In edge-cloud collaborative computing, tasks can be scheduled to servers as interdependent subtasks, enhancing performance through parallel computing. A task is executed in an executor, which must first initialize the runtime environment in a process called task startup. However, most existing research neglects the reuse of executors, leading to considerable delays during task startup. To address this issue, we model the edge-cloud collaborative task scheduling scenario considering executor reuse, task startup, and dependency relationships. We then formulate the dependent task scheduling problem with task startup. To meet real-time demands in edge-cloud collaborative computing, we propose ReflexPilot, an online task scheduling architecture featuring executor management. Building on this architecture, we introduce OTSA-PPO, a task scheduling algorithm based on Proximal Policy Optimization (PPO), and EMA, an advanced executor allocation algorithm. Under constraints of computational and communication resources, ReflexPilot leverages OTSA-PPO for online scheduling of dependent tasks based on current states, while EMA pre-creates and reuses executors to reduce the average task completion time. Extensive simulations demonstrate that ReflexPilot significantly reduces the average task completion time by 31% to 71% compared with existing baselines.
Förderung
- National Natural Science Foundation of China
- Pilot for Major Scientific Research Facility of Jiangsu Province of China
Zitieren
APA
Zou, W., Zhang, Z., Wang, N., Tian, Y., & Tian, L. (2025). ReflexPilot: Startup-Aware Dependent Task Scheduling Based on Deep Reinforcement Learning for Edge-Cloud Collaborative Computing. IEEE Transactions on Cloud Computing, 13(2), 641-654. https://doi.org/10.1109/tcc.2025.3555231
Vancouver
Zou W, Zhang Z, Wang N, Tian Y, Tian L. ReflexPilot: Startup-Aware Dependent Task Scheduling Based on Deep Reinforcement Learning for Edge-Cloud Collaborative Computing. IEEE Transactions on Cloud Computing. 2025;13(2):641-654. doi:10.1109/tcc.2025.3555231
BibTeX
@article{Zou2025,
author = {Zou, Wenhao and Zhang, Zongshuai and Wang, Nina and Tian, Yu and Tian, Lin},
title = {ReflexPilot: Startup-Aware Dependent Task Scheduling Based on Deep Reinforcement Learning for Edge-Cloud Collaborative Computing},
journal = {IEEE Transactions on Cloud Computing},
year = {2025},
volume = {13},
number = {2},
pages = {641--654},
doi = {10.1109/tcc.2025.3555231}
}
EUVIMED