Reliability-driven real-time task replication for fault tolerance in hierarchical scheduling multiprocessor systems

摘要

The increasing complexity of systems poses a big challenge to design systems with fault-tolerant capability. The aim of this study was to establish fault-tolerant system for multiprocessor platform with the help of hierarchical scheduling framework. A mathematical fault and reliability model for hierarchical scheduling framework was proposed firstly, and then a heuristic algorithm by exploiting the difference of task resource overhead and the probability of task failures was presented and a task replication scheme was given lastly. The experimental results demonstrated the proposed scheme could effectively guarantee reliability goal and reduce resource consumption simultaneously.