Consequence Oriented Self-Healing and Hybrid Diagnosis Integrating Decision Diagram, Fuzzy Logic and Neural Network

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