Abstract
Aim. Past scheduling algorithms are, in our opinion, too conservative in that they are based on WCET (worst-case execution time). We now propose what we believe to be a new and effective one. Section 2 of the full paper designs our effective scheduling algorithm; it, by adjusting the task sets of processors dynamically, keeps the CPU utilization of each processor around its reference value and guarantees not missing the deadline of each task. Section 3 analyzes the stability of the scheduling algorithm, its steady-state performance and transient performance. Section 4 did experiments on the scheduling algorithm; the experimental results, given in Figs. 4 and 5, prove preliminarily the correctness of our theoretical analysis and the effectiveness of our scheduling algorithm.
| Original language | English |
|---|---|
| Pages (from-to) | 416-420 |
| Number of pages | 5 |
| Journal | Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University |
| Volume | 27 |
| Issue number | 3 |
| State | Published - Jun 2009 |
Keywords
- Algorithms
- Feedback control
- Multiprocessing systems
- Scheduling
Fingerprint
Dive into the research topics of 'Proposing an effective scheduling algorithm based on feedback control for multiprocessing systems'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver