Verifying Autonomic Fault Mitigation Strategies in Large Scale Real-Time Systems

When hardware failures occur in large-scale embedded systems, manual reconfiguration is infeasible and systems must autonomously adapt their task allocations to maintain operation despite diminished resources. The innovation of GHOST lies in providing a systematic optimization process for finding appropriate healing actions that satisfy both system designer and user requirements. This enables autonomous systems to make intelligent recovery decisions rather than simply failing or restarting.

This paper presents the GHOST (Guided Healing and Optimization Search Technique) algorithm for automated healing of large-scale embedded system structures. When a resource fault is detected, GHOST applies iterative transformation criteria to find alternative system models that can continue operation with reduced resources. The approach defines performance criteria including throughput, robustness, and similarity to the original system, and uses weighted optimization to balance competing objectives during the healing process.

GHOST successfully handles both resource reduction cases (where available resources are reduced) and resource failure cases (where persistent faults block certain resources). The algorithm demonstrates healing transformations on hierarchical system structures, showing how it can redistribute tasks and management responsibilities to maintain system functionality. Examples illustrate how the optimization process balances throughput maximization against maintaining structural similarity to the original design.