Hangjie Zheng
GCP NetInfra, Google, Inc., Sunnyvale, CA 94089, USA.
*Corresponding author: Hangjie Zheng
Abstract
Edge computing systems often suffer from elevated task response delays under high-concurrency conditions. Conventional scheduling approaches struggle to accommodate both task urgency and the dynamic nature of node resources, frequently resulting in delayed migration decisions and system bottlenecks. To address these challenges, this paper proposes a delay-aware task migration scheduling algorithm. This approach proposes a multi-dimensional latency evaluation function. By incorporating both real-time task urgency and node load status, it dynamically assesses the potential gains of task migration and determines the optimal execution timing. Simulation results demonstrate the algorithm’s advantages in reducing average response time, minimizing ineffective migrations, and improving scheduling stability, making it suitable for heterogeneous, high-density edge computing scenarios.
References
[1] Moghaddasi K, Jurdak R. An energy-aware distributed federated soft actor-critic framework for intelligent task offloading in vehicular mobile edge computing networks. Ad Hoc Netw. 180:104043.
[2] Wang Y, Yu Z, Yao X, et al. A novel real-time data stream transfer system in edge computing of smart logistics. Electronics. 2025;14(18):3599.
[3] Zheng W, Wang C, Xu W, et al. A new delay-aware distributed cloud–edge scheduling framework and algorithm in dynamic network environments. Sustainability. 2025;17(11):4887.
[4] Tabrizi DM, Roudgar A, Maleki ER, et al. Distributed deep reinforcement learning for independent task offloading in Mobile Edge Computing. J Netw Comput Appl. 2025;240:104211.
[5] Abuthahir SS, Peter PSJ. A hybrid meta-heuristic algorithm for task offloading in vehicular edge computing network. Wirel Pers Commun. 2025;141(1):1-24.
[6] Daghayeghi A, Nickray M. Delay-aware and energy-efficient task scheduling using strength Pareto evolutionary algorithm II in fog-cloud computing paradigm. Wirel Pers Commun. 2024;[preprint]:1-49.
[7] Chenghou J, Jiajie X, Yusen H, et al. Efficient delay-aware task scheduling for IoT devices in mobile cloud computing. Mob Inf Syst. 2022;2022:Article ID 1234567.
[8] Li J, Shi W, Zhang N, et al. Delay-aware VNF scheduling: a reinforcement learning approach with variable action set. IEEE Trans Cogn Commun Netw. 2020; [early access].
How to cite this paper
Research on Delay-aware Scheduling Algorithms for Edge Task Migration in High-concurrency Environments
How to cite this paper: Hangjie Zheng. (2025). Research on Delay-aware Scheduling Algorithms for Edge Task Migration in High-concurrency Environments. Engineering Advances, 5(4), 219-225.
DOI: http://dx.doi.org/10.26855/ea.2025.10.015