Permanent fault-tolerant scheduling in heterogeneous multi-core real-time systems

In a heterogeneous multi-core real-time system, once a permanent error occurs, the task cannot be successfully completed before the deadline, which may cause catastrophic consequences. Therefore, the reliability of the real-time system is critical. In this paper, we consider real-time tasks in a heterogeneous system with previous constraints, and explore how to improve the reliability of the system. We propose a new scheduling algorithm-PFTSA, which uses active replication to back up as many tasks on different processors as possible before the deadline, minimizing communication overhead, ensuring that the maximum number of permanent errors can be accommodated before the deadline and providing maximum system reliability. The experimental results show that the reliability of our proposed scheduling algorithm is higher than the existing related algorithms.