On task schedulability in real-time control systems

Danbing Seto, John P. Lehoczky, Lui Sha, Kang G. Shin

Research output: Contribution to conferencePaper

Abstract

Most real-time computer-controlled systems are built in two separate steps, each in isolation: controller design and its digital implementation. Computational tasks that realize the control algorithms are usually scheduled by treating their execution times and periods as unchangeable parameters. Task scheduling therefore depends only on the limited computing resources available. On the other hand, controller design is primarily based on the continuous-time dynamics of the physical system being controlled. The set of tasks resulting from this controller design may not be schedulable with the limited computing resources available. Even if the given set of tasks is schedulable, the overall control performance may not be optimal in the sense that they do not make a full use of the computing resource. In this paper, we propose an integrated approach to controller design and task scheduling. Specifically, task frequencies (or periods) are allowed to vary within a certain range as long as such a change doesn't affect critical control functions such as maintenance of system stability. We present an algorithm that optimizes task frequencies and then schedules the resulting tasks with the limited computing resources available. The proposed approach is also applicable to failure recovery and reconfiguration in real-time control systems.

Original languageEnglish (US)
Pages13-21
Number of pages9
StatePublished - Dec 1 1996
Externally publishedYes
EventProceedings of the 1996 17th IEEE Real-Time Systems Symposium - Washington, DC, USA
Duration: Dec 4 1996Dec 6 1996

Other

OtherProceedings of the 1996 17th IEEE Real-Time Systems Symposium
CityWashington, DC, USA
Period12/4/9612/6/96

Fingerprint

Real time control
Control systems
Controllers
Scheduling
System stability
Computer systems
Recovery

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

Seto, D., Lehoczky, J. P., Sha, L., & Shin, K. G. (1996). On task schedulability in real-time control systems. 13-21. Paper presented at Proceedings of the 1996 17th IEEE Real-Time Systems Symposium, Washington, DC, USA, .

On task schedulability in real-time control systems. / Seto, Danbing; Lehoczky, John P.; Sha, Lui; Shin, Kang G.

1996. 13-21 Paper presented at Proceedings of the 1996 17th IEEE Real-Time Systems Symposium, Washington, DC, USA, .

Research output: Contribution to conferencePaper

Seto, D, Lehoczky, JP, Sha, L & Shin, KG 1996, 'On task schedulability in real-time control systems' Paper presented at Proceedings of the 1996 17th IEEE Real-Time Systems Symposium, Washington, DC, USA, 12/4/96 - 12/6/96, pp. 13-21.
Seto D, Lehoczky JP, Sha L, Shin KG. On task schedulability in real-time control systems. 1996. Paper presented at Proceedings of the 1996 17th IEEE Real-Time Systems Symposium, Washington, DC, USA, .
Seto, Danbing ; Lehoczky, John P. ; Sha, Lui ; Shin, Kang G. / On task schedulability in real-time control systems. Paper presented at Proceedings of the 1996 17th IEEE Real-Time Systems Symposium, Washington, DC, USA, .9 p.
@conference{12ebd602924547039ea67cc505956584,
title = "On task schedulability in real-time control systems",
abstract = "Most real-time computer-controlled systems are built in two separate steps, each in isolation: controller design and its digital implementation. Computational tasks that realize the control algorithms are usually scheduled by treating their execution times and periods as unchangeable parameters. Task scheduling therefore depends only on the limited computing resources available. On the other hand, controller design is primarily based on the continuous-time dynamics of the physical system being controlled. The set of tasks resulting from this controller design may not be schedulable with the limited computing resources available. Even if the given set of tasks is schedulable, the overall control performance may not be optimal in the sense that they do not make a full use of the computing resource. In this paper, we propose an integrated approach to controller design and task scheduling. Specifically, task frequencies (or periods) are allowed to vary within a certain range as long as such a change doesn't affect critical control functions such as maintenance of system stability. We present an algorithm that optimizes task frequencies and then schedules the resulting tasks with the limited computing resources available. The proposed approach is also applicable to failure recovery and reconfiguration in real-time control systems.",
author = "Danbing Seto and Lehoczky, {John P.} and Lui Sha and Shin, {Kang G.}",
year = "1996",
month = "12",
day = "1",
language = "English (US)",
pages = "13--21",
note = "Proceedings of the 1996 17th IEEE Real-Time Systems Symposium ; Conference date: 04-12-1996 Through 06-12-1996",

}

TY - CONF

T1 - On task schedulability in real-time control systems

AU - Seto, Danbing

AU - Lehoczky, John P.

AU - Sha, Lui

AU - Shin, Kang G.

PY - 1996/12/1

Y1 - 1996/12/1

N2 - Most real-time computer-controlled systems are built in two separate steps, each in isolation: controller design and its digital implementation. Computational tasks that realize the control algorithms are usually scheduled by treating their execution times and periods as unchangeable parameters. Task scheduling therefore depends only on the limited computing resources available. On the other hand, controller design is primarily based on the continuous-time dynamics of the physical system being controlled. The set of tasks resulting from this controller design may not be schedulable with the limited computing resources available. Even if the given set of tasks is schedulable, the overall control performance may not be optimal in the sense that they do not make a full use of the computing resource. In this paper, we propose an integrated approach to controller design and task scheduling. Specifically, task frequencies (or periods) are allowed to vary within a certain range as long as such a change doesn't affect critical control functions such as maintenance of system stability. We present an algorithm that optimizes task frequencies and then schedules the resulting tasks with the limited computing resources available. The proposed approach is also applicable to failure recovery and reconfiguration in real-time control systems.

AB - Most real-time computer-controlled systems are built in two separate steps, each in isolation: controller design and its digital implementation. Computational tasks that realize the control algorithms are usually scheduled by treating their execution times and periods as unchangeable parameters. Task scheduling therefore depends only on the limited computing resources available. On the other hand, controller design is primarily based on the continuous-time dynamics of the physical system being controlled. The set of tasks resulting from this controller design may not be schedulable with the limited computing resources available. Even if the given set of tasks is schedulable, the overall control performance may not be optimal in the sense that they do not make a full use of the computing resource. In this paper, we propose an integrated approach to controller design and task scheduling. Specifically, task frequencies (or periods) are allowed to vary within a certain range as long as such a change doesn't affect critical control functions such as maintenance of system stability. We present an algorithm that optimizes task frequencies and then schedules the resulting tasks with the limited computing resources available. The proposed approach is also applicable to failure recovery and reconfiguration in real-time control systems.

UR - http://www.scopus.com/inward/record.url?scp=0030410148&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030410148&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0030410148

SP - 13

EP - 21

ER -