본문 바로가기
KERD
논문KCI 등재

A deferring strategy to improve schedulability for the imprecise convergence on-line tasks

1

조회

0

다운로드

0

인용

0

참고문헌

키워드

주제분류학제간연구

초록

The imprecise real-time scheduling can be used for minimizing the bad effects of timing faults by leaving less important tasks unfinished if necessary when a transient overload occured. In the imprecise scheduling, every time-critical task can be logically decomposed into two tasks : a mandatory task and an optional task. Recently, some studies in this field showed good schedulability performance and minimum total error by deferring the optional tasks. But the schedulability performance of the studies can be shown only when the execution time of each optional task was less than or equal to the execution time of its corresponding mandatory task. Therefore, in this paper, a new deferring strategy is proposed under the reverse execution time restriction to the previous studies. Nevertheless, the strategy produces comparable or superior schedulability performance to the previous studies and can minimize the total error also.

Abstract

The imprecise real-time scheduling can be used for minimizing the bad effects of timing faults by leaving less important tasks unfinished if necessary when a transient overload occured. In the imprecise scheduling, every time-critical task can be logically decomposed into two tasks : a mandatory task and an optional task. Recently, some studies in this field showed good schedulability performance and minimum total error by deferring the optional tasks. But the schedulability performance of the studies can be shown only when the execution time of each optional task was less than or equal to the execution time of its corresponding mandatory task. Therefore, in this paper, a new deferring strategy is proposed under the reverse execution time restriction to the previous studies. Nevertheless, the strategy produces comparable or superior schedulability performance to the previous studies and can minimize the total error also.

참고문헌 (15)

  1. 송기현, "An On-line Algorithm to Search Minimum Total Error for Imprecise Real-time Tasks with 0", 1 Constraint, 2005, pp.8(12), 1589~1596[DOI]
  2. J. Y. Chung, "Scheduling imprecise computations to minimize total error", Microprocessing and Microprogramming, 27, pp.767~774 (1989)
  3. J. W. S. Liu, "Imprecise computations", IEEE Special Issue on Real-Time Systems, pp.83~94 (1994)
  4. W. K. Shih, "Fast algorithms for scheduling imprecise computaions", SIAM Journal on Computing, 20, pp.537~552 (1991)
  5. 최환필, "불확정 계산을 위한 EDF 기반의 실시간 스케줄링 알고리즘", 정보처리학회논문지. 컴퓨터 및 통신시스템, 18(4), pp.143~150 (2011), 한국정보처리학회
  6. 송기현, "비정밀 실시간 스케쥴링에서 선택적 태스크들의 지연 방법에 관한 연구", 한국지식정보기술학회 논문지, 9(1), pp.95~104 (2014), 한국지식정보기술학회
  7. 송기현, "A Study on New Defering Method for Optional Tasks to Improve Schedulability", 한국지식정보기술학회 논문지, 10(3), pp.337~346 (2015), 한국지식정보기술학회
  8. G. H. Song., "An efficient algorithm to minimize total error of the imprecise real time tasks with 0", 1constraint, 2006, pp.7(4), 309~320
  9. Gi-Hyeon Song, "Scheduling Algorithm to Minimize Total Error for Imprecise On-Line Tasks", 멀티미디어학회논문지, 10(12), pp.1741~1751 (2007), 한국멀티미디어학회
  10. 송기현, "0", 1 제약조건을 갖는 부정확한 태스크들의 총오류를 최소화시키기 위한 개선된 온라인 알고리즘, 2007, pp.34(10), 493~501[DOI]
  11. W. K. Shih, "On-line algorithms for scheduling imprecise computations", SIAM Journal on Computing, 25, pp.1105~1121 (1996)
  12. J. M. Chen, "Imprecise computations with deferred optional tasks", Journal of Information Science and Engineering, 25, pp.185~200 (2009)
  13. S. K. Baruah, "Competitive on-line scheduling of imprecise computations", IEEE Transactions on Computers, 47, pp.1027~1032 (1998)
  14. J. H. Kim, "Performance evaluation of on-line scheduling algorithms for imprecise computation", Proceedings of the 5th IEEE International Conference on Real-Time Computing Systems and Applications, pp.217~222 (1998)
  15. Riccardo Bettati, "On-line scheduling for checkpointing imprecise computation", Proceeding of the Fifth Euromicro Workshop on Real-Time Systems (1993)

관련 논문AI추천

이 간행물의 다른 논문 (40건)