基于深度学习的动态优先级任务调度算法
作者:

Dynamic Priority Task Scheduling Algorithm Based on Deep Learning
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [15]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    工业互联网中设备任务的处理需要大量计算资源, 有低时延需求的任务显著增多. 边缘计算将算力等资源放置到靠近需求一侧, 为任务处理提供有效支撑. 但由于边缘计算资源有限, 无法同时满足设备任务的低时延和高完成率需求. 如何确定合理的卸载决策与任务调度, 仍然存在巨大挑战. 针对以上问题, 本文提出了一种基于深度学习的动态优先级任务调度算法DPTSA, 首先根据动态优先级选择待处理任务, 通过神经网络产生任务调度决策, 然后通过交叉变异等操作产生一组可行解, 再筛选最优解存储到经验缓冲区, 最后通过经验缓冲区样本优化神经网络参数. 基于Google的Brog任务调度数据集的实验结果表明, 相比于4种基准算法, DPTSA在任务等待时间和任务完成率方面都有出色表现.

    Abstract:

    The processing of device tasks in the industrial Internet requires a large amount of computing resources, and the tasks with low latency requirements have increased significantly. Edge computing places computing power and other resources on the side close to the demand to provide effective support for task processing. However, due to the limited edge computing resources, the requirements of low latency and high completion rate of the device tasks cannot be satisfied at the same time. It is still a great challenge to determine a reasonable offloading decision and task scheduling. Given the above problem, a deep learning-based dynamic priority task scheduling algorithm DPTSA is proposed in this study. Firstly, the tasks to be processed are selected according to dynamic priority and task scheduling decisions are generated through neural networks. Then, a set of feasible solutions are generated through cross-variance and other operations, and the optimal solutions are screened out and stored in the empirical buffer area. Finally, the neural network parameters are optimized through the empirical buffer samples. The experimental results based on Google’s Brog task scheduling dataset show that DPTSA is superior to the four benchmark algorithms in terms of task waiting time and task completion rate.

    参考文献
    [1] Mantravadi S, Møller C, Li C, et al. Design choices for next-generation IIoT-connected MES/MOM: An empirical study on smart factories. Robotics and Computer-integrated Manufacturing, 2022, 73: 102225. [doi: 10.1016/j.rcim.2021.102225
    [2] Luo QY, Hu SH, Li CL, et al. Resource scheduling in edge computing: A survey. IEEE Communications Surveys & Tutorials, 2021, 23(4): 2131–2165
    [3] Deng SG, Zhao HL, Fang WJ, et al. Edge intelligence: The confluence of edge computing and artificial intelligence. IEEE Internet of Things Journal, 2020, 7(8): 7457–7469. [doi: 10.1109/JIOT.2020.2984887
    [4] Qiu T, Chi JC, Zhou XB, et al. Edge computing in industrial Internet of Things: Architecture, advances and challenges. IEEE Communications Surveys & Tutorials, 2020, 22(4): 2462–2488
    [5] Vitturi S, Zunino C, Sauter T. Industrial communication systems and their future challenges: Next-generation Ethernet, IIoT, and 5G. Proceedings of the IEEE, 2019, 107(6): 944–961. [doi: 10.1109/JPROC.2019.2913443
    [6] Chen X, Cheng L, Liu C, et al. A WOA-based optimization approach for task scheduling in cloud computing systems. IEEE Systems Journal, 2020, 14(3): 3117–3128. [doi: 10.1109/JSYST.2019.2960088
    [7] Khan WZ, Rehman MH, Zangoti HM, et al. Industrial Internet of Things: Recent advances, enabling technologies and open challenges. Computers & Electrical Engineering, 2020, 81: 106522
    [8] Hazra A, Adhikari M, Amgoth T, et al. A comprehensive survey on interoperability for IIoT: Taxonomy, standards, and future directions. ACM Computing Surveys, 2023, 55(1): 9
    [9] Ullah I, Khan MS, St-Hilaire M, et al. Task priority-based cached-data prefetching and eviction mechanisms for performance optimization of edge computing clusters. Security and Communication Networks, 2021, 2021: 5541974
    [10] Sharma R, Nitin N, AlShehri MAR, et al. Priority-based joint EDF-RM scheduling algorithm for individual real-time task on distributed systems. The Journal of Supercomputing, 2021, 77(1): 890–908. [doi: 10.1007/s11227-020-03306-x
    [11] Xiong X, Zheng K, Lei L, et al. Resource allocation based on deep reinforcement learning in IoT edge computing. IEEE Journal on Selected Areas in Communications, 2020, 38(6): 1133–1146. [doi: 10.1109/JSAC.2020.2986615
    [12] Liao HL, Li XY, Guo DK, et al. Dependency-aware application assigning and scheduling in edge computing. IEEE Internet of Things Journal, 2022, 9(6): 4451–4463. [doi: 10.1109/JIOT.2021.3104015
    [13] Liang J, Li KL, Liu CB, et al. Joint offloading and scheduling decisions for DAG applications in mobile edge computing. Neurocomputing, 2021, 424: 160–171. [doi: 10.1016/j.neucom.2019.11.081
    [14] Ajmal MS, Iqbal Z, Khan FZ, et al. Hybrid ant genetic algorithm for efficient task scheduling in cloud data centers. Computers and Electrical Engineering, 2021, 95: 107419. [doi: 10.1016/j.compeleceng.2021.107419
    [15] Bi SZ, Huang L, Wang H, et al. Lyapunov-guided deep reinforcement learning for stable online computation offloading in mobile-edge computing networks. IEEE Transactions on Wireless Communications, 2021, 20(11): 7519–7537. [doi: 10.1109/TWC.2021.3085319
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

齐玉峰,贺晓.基于深度学习的动态优先级任务调度算法.计算机系统应用,2023,32(7):195-201

复制
分享
文章指标
  • 点击次数:730
  • 下载次数: 2235
  • HTML阅读次数: 1799
  • 引用次数: 0
历史
  • 收稿日期:2022-12-03
  • 最后修改日期:2023-01-17
  • 在线发布日期: 2023-05-19
文章二维码
您是第11274712位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号