GHOST: Guided Healing and Optimization Search Technique for Healing Large-Scale Embedded Systems

Abstract

Reflex and healing architectures have been shown to provide adequate user-defined initial failure mitigation behaviors in the presence of system faults. What is lacking, however, is a user-guided means of healing the system after the initial reflexes have been enacted. This process should be autonomic in the sense that new system configurations can be achieved by defining a priori only a small set of criteria to which the healed system should conform. What follows is an explanation of this technique for guided healing which allows system designers to direct the healing process from a higher level in such a way that the resulting system configurations satisfy their particular needs. A brief example outlining the application of this approach is given