期刊文献+

一种基于标准化QoS公平的反馈控制实时调度算法 被引量:2

A Feedback Control Real-time Scheduling Algorithm Based on Normalized QoS Fairness
下载PDF
导出
摘要 任务间的QoS公平性是多QoS级别的可调节动态实时调度系统中的一个重要问题.本文引入了标准化QoS公平的概念,在公平性中加入了任务的重要性因素,并构造了具有PID反馈控制环节的实时调度算法NF-QoS来达到标准化QoS公平.利用NF-QoS对系统截止期错失率进行实时采样,定期反馈给PID控制器,根据PID控制器计算的结果对各任务QoS级别进行调整,以保证各任务公平地得到处理器资源.实验结果表明,NF-QoS不仅合理地协调了系统利用率和截止期错失率,并且有效地提高了系统的QoS公平性. QoS fairness is an important problem in multi-QoS-level adjustable dynamic real-time scheduling systems. In this paper, a concept named normalized QoS fairness is presented to add task importance factor to fairness. The NF-QoS (Normalized Fair QoS) real-time scheduling algorithm is constructed, which incorporates a PID feedback controller to achieve the normalized QoS fairness purpose. NF-QoS samples DMR (Deadline Miss Ratio) as the system runs which is fed back to PID controller periodically. Then QoS levels of tasks are adjusted according to feedback computing results so that all tasks could get CPU resources fairly. The experimental results show that NF-QoS can balance system utilization and DMR reasonably, and effectively enhance the system QoS fairness.
出处 《小型微型计算机系统》 CSCD 北大核心 2007年第4期748-752,共5页 Journal of Chinese Computer Systems
基金 国家自然科学基金项目(60273042)资助 安徽省自然科学基金项目(03042203)资助.
关键词 实时调度 标准化QoS公平 PID反馈控制 real-time scheduling normalized QoS fairness PID feedback control
  • 相关文献

参考文献2

二级参考文献14

  • 1[1]Liu JWS, Shih WK, Lin KJ, Bettati R, Chung JY. Imprecise computations. Proc. of the IEEE, 1994,82(1):83~94.
  • 2[2]Choi KH, Jung GY, Kim T, Jung SH. Real-Time scheduling algorithm for minimizing maximum weighted error with O(NlogN+cN) complexity. Information Processing Letters, 1998,67(6):311~315.
  • 3[3]Mittal A, Manimaran G, Murthy CSR. Integrated dynamic scheduling of hard and QoS degradable real-time tasks in multiprocessor systems. Journal of Systems Architecture, 2000,46(9):793~807.
  • 4[4]Castorino A, Ciccarella G. Algorithms for real-time scheduling of error-cumulative tasks based on the imprecise computation approach. Journal of Systems Architecture, 2000,46(7):587~600.
  • 5[5]Baruah SK, Hickey ME. Competitive on-line scheduling of imprecise computations. IEEE Trans. on Computers, 1998,47(9):1027 ~1032.
  • 6[6]Ho KIJ, Leung JYT, Wei WD. Scheduling imprecise computation tasks with 0/1-constraint. Discrete Applied Mathematics, 1997, 78(1,3):117~132.
  • 7[7]Manimaran G, Murthy CSR. A new scheduling approach supporting different fault-tolerant techniques for real-time multiprocessor systems. Journal of Microprocessors and Microsystems, 1997,21(3):163~173.
  • 8[8]Dey JK, Kurose J, Towsley D. On-Line scheduling policies for a class of IRIS (increasing reward with increasing service) real-time tasks. IEEE Trans. on Computers, 1996,45(7):802~813.
  • 9[9]Chantrapornchai C, Tongsima S, Sha EHM. Imprecise task schedule optimization. In: Proc. of the 6th IEEE Int'l Conf. on Fuzzy Systems. 1997. 1265~1270.
  • 10[10]McVey CB, Atkins EM, Durfee EH. Development of iterative real-time scheduler to planner feedback. In: Proc. of the 15th Int'l Joint Conf. on Artificial Intelligence. August 1997. 1267~1272.

共引文献25

同被引文献3

引证文献2

二级引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部