Consequence oriented self-healing and hybrid diagnosis integrating decision diagram, fuzzy logic and neural network

Yuan Shun Dai, Michael Hinchey, Qingpei Hu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Computing systems become increasingly large and complex. Their dependability and autonomy are of great concern today, where self-healing is a challenging topic. This paper presented an innovative model and technology to realize the self-healing function under the real-time requirement. This approach, different from the existing technologies, is based on a new concept defined as consequence-oriented diagnosis and healing. Derived from the new concept, a prototype model for proactive self-healing actions is presented. Then, this paper proposes a hybrid tool that combines MDD, Fuzzy Logic and Neural Network, which is efficient, accurate and intelligent. Some examples to help illustrate the concepts are shown across the paper.

Original languageEnglish
Title of host publicationProceedings - Fourth IEEE International Workshop on Engineering of Autonomic and Autonomous Systems, EASe 2007
Pages127-136
Number of pages10
DOIs
Publication statusPublished - 2007
Externally publishedYes
Event4th IEEE International Workshop on Engineering of Autonomic and Autonomous Systems, EASe 2007 - Tucson, AZ, United States
Duration: 26 Mar 200729 Mar 2007

Publication series

NameProceedings - Fourth IEEE International Workshop on Engineering of Autonomic and Autonomous Systems, EASe 2007

Conference

Conference4th IEEE International Workshop on Engineering of Autonomic and Autonomous Systems, EASe 2007
Country/TerritoryUnited States
CityTucson, AZ
Period26/03/0729/03/07

Keywords

  • Autonomic computing
  • Decision diagram
  • Fuzzy logic
  • Neural network
  • Self-healing

Fingerprint

Dive into the research topics of 'Consequence oriented self-healing and hybrid diagnosis integrating decision diagram, fuzzy logic and neural network'. Together they form a unique fingerprint.

Cite this