摘要
实时系统要求每个任务必须在其截止时间内产生逻辑正确的结果,然而,由于故障的存在使得系统无法保证所有任务都能满足这一条件,因此,适当降低实时任务的精确度以及提供优化有效的容错方法变得至关重要.文章基于非精确计算理论提出了一种检查点设置策略IC-CPS,该策略面向多任务的实时系统,可以提供容错能力和确定性实时保证.数值测试证明IC-CPS不仅提高了系统的容错能力,扩大了检查点策略的应用范围,使得实时任务能够在按时完成的前提下容忍更多的错误,而且还降低了系统因为设置检查点所产生的开销.
In a real-time system, each task must complete and produce correct output by the specified deadline. However, it is not possible to meet each deadline because of system faults. So, it is very important to decrease precision of real-time task and provide a fault-tolerant optimal scheduling to assure timeliness and reliability. This paper provides a checkpoint placement scheme based on imprecise computation. This scheme can provide fault tolerance and real-time guarantees for multi-task real-time system. Numerical examples proves that IC-CPS can increase the performance of system fault-tolerant, and real-time tasks can tolerate more faults under the premise that tasks are completed on time. Moreover, IC-CPS also reduces the system costs checkpoint placement.
出处
《哈尔滨工程大学学报》
EI
CAS
CSCD
北大核心
2007年第2期203-206,共4页
Journal of Harbin Engineering University
基金
国家863计划基金资助项目(2002AA1Z2306
2004AA1Z2351)
电子信息产业发展基金资助项目(XD-JZ-0412-03)
关键词
容错
检查点间隔
非精确计算
实时系统
fault tolerant
checkpoint interval
imprecise computation
real-time system
