Advanced

Resource-Constrained Embedded Control and Computing Systems

Henriksson, Dan LU (2006) In PhD Thesis TFRT-1074
Abstract
This thesis deals with methods for handling resource constraints in embedded control systems and real-time computing systems. By dynamic feedback-based resource scheduling it is possible to achieve adaptability andincreased performance for these systems.



A feedback scheduling strategy is presented, which uses feedback from plant states to distribute computing resources optimally among a set of controller tasks. Linear-quadratic controllers are analyzed, and expressions relating the expected cost to the sampling period and the plant state are derived and used for on-line sample-rate adjustments.



A flexible implementation of model predictive control (MPC) tasks is described. A termination criterion is... (More)
This thesis deals with methods for handling resource constraints in embedded control systems and real-time computing systems. By dynamic feedback-based resource scheduling it is possible to achieve adaptability andincreased performance for these systems.



A feedback scheduling strategy is presented, which uses feedback from plant states to distribute computing resources optimally among a set of controller tasks. Linear-quadratic controllers are analyzed, and expressions relating the expected cost to the sampling period and the plant state are derived and used for on-line sample-rate adjustments.



A flexible implementation of model predictive control (MPC) tasks is described. A termination criterion is derived that, unlike traditional MPC, takes the effects of computational delay into account in the optimization. A scheduling scheme is also described, where the MPC cost functions being minimized are used as dynamic task priorities for a set of MPC tasks.



A method for optimizing the use of computational resources in a multi-camera-based positioning system is studied. The covariance of the estimation error is minimized, while meeting computation time constraints.



A novel predictor for delay control in server systems is introduced. The predictor uses instantaneous measurements of queue length and arrival times and is continuously updated as new requests arrive according to a receding horizon principle. The predictor is evaluated in simulation and by experiments on an Apache web server.



The MATLAB/Simulink-based simulator TrueTime is presented. TrueTime is a codesign tool that facilitates simulation of distributed real-time control systems. TrueTime also supports simulation of wireless communication and resource constraints associated with wireless sensor/actuator networks. (Less)
Abstract (Swedish)
Popular Abstract in Swedish

Inbyggda styrsystem finns idag överallt omkring oss. Moderna bilar, cd-spelare och mobiltelefoner är bara några exempel på produkter som inte skulle fungera utan datorbaserade reglersystem. Dock karaktäriseras dessa system ofta av begränsade beräkningsresurser, till följd av tillverkarnas behov att minimera produktionskostnaden. Samtidigt vill man införa mer och mer funktionalitet i de datorbaserade reglersystemen.



Den första delen av avhandlingen behandlar metoder för att hantera resursbegränsningar i inbyggda reglersystem. Huvudiden är att använda den reglertekniska principen om återkoppling för att dynamiskt fördela beräkningsresurser mellan olika styralgoritmer.

... (More)
Popular Abstract in Swedish

Inbyggda styrsystem finns idag överallt omkring oss. Moderna bilar, cd-spelare och mobiltelefoner är bara några exempel på produkter som inte skulle fungera utan datorbaserade reglersystem. Dock karaktäriseras dessa system ofta av begränsade beräkningsresurser, till följd av tillverkarnas behov att minimera produktionskostnaden. Samtidigt vill man införa mer och mer funktionalitet i de datorbaserade reglersystemen.



Den första delen av avhandlingen behandlar metoder för att hantera resursbegränsningar i inbyggda reglersystem. Huvudiden är att använda den reglertekniska principen om återkoppling för att dynamiskt fördela beräkningsresurser mellan olika styralgoritmer.



Resursbegränsningar förekommer också i stora komplexa system, som Internet. Som en andra del av avhandlingen beskrivs en metod för att reglera fördröjningar i moderna web-servrar. Metoden bygger på prediktion av framtida fördröjningar i kombination med återkoppling.



Den avslutande delen av avhandlingen beskriver ett simuleringsverktyg för datorbaserade reglersystem. Simulatorn gör det möjligt att simulera datorer och kommunikationsnätverk som används för att implementera styralgoritmer, och deras inverkan på de fysikaliska processer som regleras. Simulatorn har använts för att utvärdera de metoder som beskrivs i de två första delarna av avhandlingen. (Less)
Please use this url to cite or link to this publication:
author
supervisor
opponent
  • Professor Tilbury, Dawn, Mechanical Engineering Dept, University of Michigan
organization
publishing date
type
Thesis
publication status
published
subject
keywords
robotteknik, reglerteknik, kontroll, Automation, robotics, control engineering, Automatiska system, numerisk analys, system, Datalogi, control, numerical analysis, systems, Computer science, Server control, Simulation tools, Feedback scheduling, Real-time control systems, Resource constraints
in
PhD Thesis TFRT-1074
pages
194 pages
publisher
Department of Automatic Control, Lund Institute of Technology, Lund University
defense location
Room M:B, M-building, Ole Römers v 1, Lund Institute of Technology
defense date
2006-01-13 10:15:00
ISSN
0280-5316
0280-5316
language
English
LU publication?
yes
id
e7090f25-acdf-4414-bbb2-0f8e88eaf49b (old id 546028)
date added to LUP
2016-04-01 15:42:08
date last changed
2019-05-23 15:55:59
@phdthesis{e7090f25-acdf-4414-bbb2-0f8e88eaf49b,
  abstract     = {This thesis deals with methods for handling resource constraints in embedded control systems and real-time computing systems. By dynamic feedback-based resource scheduling it is possible to achieve adaptability andincreased performance for these systems.<br/><br>
<br/><br>
A feedback scheduling strategy is presented, which uses feedback from plant states to distribute computing resources optimally among a set of controller tasks. Linear-quadratic controllers are analyzed, and expressions relating the expected cost to the sampling period and the plant state are derived and used for on-line sample-rate adjustments.<br/><br>
<br/><br>
A flexible implementation of model predictive control (MPC) tasks is described. A termination criterion is derived that, unlike traditional MPC, takes the effects of computational delay into account in the optimization. A scheduling scheme is also described, where the MPC cost functions being minimized are used as dynamic task priorities for a set of MPC tasks.<br/><br>
<br/><br>
A method for optimizing the use of computational resources in a multi-camera-based positioning system is studied. The covariance of the estimation error is minimized, while meeting computation time constraints.<br/><br>
<br/><br>
A novel predictor for delay control in server systems is introduced. The predictor uses instantaneous measurements of queue length and arrival times and is continuously updated as new requests arrive according to a receding horizon principle. The predictor is evaluated in simulation and by experiments on an Apache web server.<br/><br>
<br/><br>
The MATLAB/Simulink-based simulator TrueTime is presented. TrueTime is a codesign tool that facilitates simulation of distributed real-time control systems. TrueTime also supports simulation of wireless communication and resource constraints associated with wireless sensor/actuator networks.},
  author       = {Henriksson, Dan},
  issn         = {0280-5316},
  language     = {eng},
  publisher    = {Department of Automatic Control, Lund Institute of Technology, Lund University},
  school       = {Lund University},
  series       = {PhD Thesis TFRT-1074},
  title        = {Resource-Constrained Embedded Control and Computing Systems},
  url          = {https://lup.lub.lu.se/search/ws/files/4452427/546030.pdf},
  year         = {2006},
}