Fuzzy-Grey Prediction Based Dynamic Failure Detector for Distributed Systems

  • Dong Tian
  • Shuyu Chen
  • Taiping Mao
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4494)


Fuzzy logic and grey theory, combined with adaptive heartbeat mechanism, are integrated to implement an adaptive failure detector for distributed systems. A GM(1,1) unified-dimensional new message model, which only needs a small volume of sample data, is used to predict heartbeat arrival time dynamically. Since prediction error is inevitable, a two-input (residual ratio and message loss rate), one-output (compensation value) fuzzy controller is designed to learn how to compensate for the output from the grey model, and the roughly determined fuzzy rule base is tuned by a reward-punishment learning principle. Experimental results show the availability and validity of the failure detector in detail.


Fuzzy Rule Fuzzy Controller Fuzzy Rule Base Adaptive Fuzzy Controller Fuzzy Control Rule 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Sugeno, M.: An introductory survey of fuzzy control. Inform. Sci. 36, 59–83 (1985)zbMATHCrossRefMathSciNetGoogle Scholar
  2. 2.
    Zimmermann, H.Z.: Fuzzy set theory and its applications, 2nd edn. Kluwer Academic Publishers, Dordrecht (1991)zbMATHGoogle Scholar
  3. 3.
    Deng, J.: Control problems of grey system. Systems Control Lett. 5, 288–294 (1982)Google Scholar
  4. 4.
    Deng, J. L.: Grey Prediction and Decision, Huazhong University of Science and Technology (in Chinese) (1986)Google Scholar
  5. 5.
    Chen, W., Toueg, S., Aguilera, M.K.: On the quality of service of failure detectors. IEEE Transactions on Computers 51(2), 13–32 (2002)CrossRefMathSciNetGoogle Scholar
  6. 6.
    Bertier, M., Marin, O., Sens, P.: Implementation and performance evaluation of an adaptable failure detector. In: Proc. IEEE Intl. Conf. On Dependable Systems and Networks (DSN 2002), pp. 354–363 (June 2002)Google Scholar
  7. 7.
    Hayashibara, N., Défago, X., Yared, R., Katayama, T.: The φ accrual failure detector, In: Proc. 23nd IEEE Intl. Symp. On Reliable Distributed Systems (SRDS 2004), pp. 66–78 (October 2004)Google Scholar
  8. 8.
    Hayashibara, N., Défago, X., Katayama, T.: Flexible failure detection with κ-fd. Research Report IS-RR-2004-006, Japan Advanced Institute of Science and Technology, Ishikawa, Japan (February 2004)Google Scholar
  9. 9.
    Hayashibara, N., Défago, X., Katayama, T.: Implementation and performance analysis of the φ-failure detector. Research Report IS-RR-2003-013, Japan Advanced Institute of Science and Technology, Ishikawa, Japan (October 2003)Google Scholar
  10. 10.
    Hayashibara, N., Défago, X., Katayama, T.: Two-ways adaptive failure detection with the φ-failure detector. In: Proc. Workshop on Adaptive Distributed Systems (WADiS 2003), pp. 22–27, Sorrento, Italy (October 2003)Google Scholar
  11. 11.
    Kaidar, I., Sussman, J., Marzullo, K., Dolev, D.: Moshe: A group membership service for WANs. ACM Trans. Comput. Systems 20(2), 1–48 (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Dong Tian
    • 1
    • 2
  • Shuyu Chen
    • 2
  • Taiping Mao
    • 1
  1. 1.GuiZhou Electronic Computer Software Development Center, GuiZhouChina
  2. 2.College of Computer Science, ChongQing University, ChongQingChina

Personalised recommendations