Abstract
In the control of continuous and physical systems, the controlled system is sampled sufficiently fast to capture the dynamics of the system. In general, this property cannot be applied to the control of computer systems as the measured variables are often computed over a data set, e.g., deadline miss ratio. In this paper we quantify the disturbance present in the measured variable as a function of the data set size and the sampling period, and we propose a feedback control structure that suppresses the measurement disturbance. The experiments we have carried out show that a controller using the proposed control structure outperforms a traditional control structure with regard to performance reliability.
| Original language | English |
|---|---|
| Pages (from-to) | 44-76 |
| Number of pages | 33 |
| Journal | Real-Time Systems |
| Volume | 40 |
| Issue number | 1 |
| DOIs | |
| State | Published - Oct 2008 |
Bibliographical note
Funding Information:This work was funded, in part by CUGS (the National Graduate School in Computer Science, Sweden), CENIIT (Center for Industrial Information Technology) under contract 01.07, ISIS (Information Systems for Industrial Control and Supervision), and NSF grants IIS-0208578 and CCR-0329609. This work was partly performed when J. Hansson was with Linköping University.
Keywords
- Adaptive scheduling
- Feedback control
- Measurement disturbance
- System disturbance