A Balanced Cost Fault-Tolerant Scheduling Algorithm in Heterogeneous Real-Time Systems

摘要

High reliability is required for many safety-critical and real-time applications. It is difficult to avoid permanent faults during the executing process of tasks. Once such faults are not processed in time, real-time tasks cannot be completed within the specified time, which may lead to catastrophic consequences. In order to deal with the problem of permanent fault tolerance in heterogeneous real-time systems, in this paper, we propose a balanced cost fault-tolerant scheduling algorithm. First, the algorithm uses the task computation time and the average communication time of its successor nodes as the ranking factors when calculating task priority, so that the priority of the task with larger average communication time improved; second, a task cost table is established, and tasks are allocated to appropriate processors according to the values in the task cost table in processor allocation stage. Experimental results show that the proposed algorithm can effectively improve the system reliability and reduce the completion time.