A new performance measure for scheduling independent real-time tasks
Journal of Parallel and Distributed Computing
Scheduling Algorithms for Multiprogramming in a Hard-Real-Time Environment
Journal of the ACM (JACM)
Improved Response-Time Analysis Calculations
RTSS '98 Proceedings of the IEEE Real-Time Systems Symposium
Schedulability Analysis and Utilization Bounds for Highly Scalable Real-Time Services
RTAS '01 Proceedings of the Seventh Real-Time Technology and Applications Symposium (RTAS '01)
Rate Monotonic Analysis: The Hyperbolic Bound
IEEE Transactions on Computers
A Utilization Bound for Aperiodic Tasks and Priority Driven Scheduling
IEEE Transactions on Computers
Schedulability Analysis of Periodic Fixed Priority Systems
IEEE Transactions on Computers
Rate monotonic vs. EDF: judgment day
Real-Time Systems
Measuring the Performance of Schedulability Tests
Real-Time Systems
Journal of Embedded Computing - Best Papers of RTS' 2005
Service scheduling and rescheduling in an applications integration framework
Advances in Engineering Software
Constant-time admission control for deadline monotonic tasks
Proceedings of the Conference on Design, Automation and Test in Europe
SimMapReduce: A Simulator for Modeling MapReduce Framework
MUE '11 Proceedings of the 2011 Fifth FTRA International Conference on Multimedia and Ubiquitous Engineering
IEEE Transactions on Computers
| Hi-index | 0.00 |
The development of ubiquitous intelligent has increased the real-time requirements for computing system. If one real-time computation does not complete before its deadline, it is as worse as that the computation is never executed at all. Ineffective computation not only wastes computational resources, but also might bring system overload and collapse. Hence, a schedulability test is necessary to ensure the stability of ubiquitous system. The schedulability test is concerned with determining whether a set of tasks is schedulable on a cluster. Although a number of schedulability tests have been developed, they can not be compared due to distinct test principles. In this paper, we propose a reliability indicator, through which the probability that a random task set succeeds in schedulability test can be evaluated. The larger the probability is, the better the test is. The reliability of two sufficient deadline monotonic tests are compared, and the comparison result is further validated by detailed experiments. Both analysis and experimental results show that the performance discrepancy of schedulability test is determined by a prerequisite pattern. Since this pattern can be deduce by reliability indicator, it may help system designers choose a good schedulability test in advance.