Objetivo
The goal of the proposed research is to develop a real-time scheduling framework for applications demanding various types of tasks, constraints, and scheduling paradigms within the same system. The FIRST project will investigate the following issues:
1) Co-operation and coexistence of standard real-time scheduling schemes, such as time-triggered and even-triggered, dynamic and fixed priority, off-line based;
2) Integration of different task types such as hard and soft, or more flexible notions, e.g from control or quality-of-service demands;
3) Temporal encapsulation of subsystems to support composability and reusability of available components 4) Monitoring and maintenance of control systems over the Internet. FIRST will provide functionality for the schemes for POSIX compliant operating systems, including Internet access.
OBJECTIVES
The objective of the proposed research is to develop a real-time scheduling framework for applications demanding various types of tasks, constraints, and scheduling paradigms within the same system. The FIRST project will investigate the following issues:;
1) co- operation and coexistence of standard real-time scheduling schemes, time- triggered and event-triggered, dynamic and fixed priority based, as well as off-line based;
2) integration of different task types such as hard and soft, or more flexible notions, e.g from control or quality-of-service demands, and fault-tolerance mechanisms;
3) temporal encapsulation of subsystems in order to support the composability and reusability of available components including legacy subsystems;
4) monitoring and maintenance of control systems over the Internet. FIRST will provide functionality for the schemes for POSIX compliant operating systems, including monitoring and maintenance of control systems over the Internet.
DESCRIPTION OF WORK
To address the goals of FIRST we have structured our work under five main workpackages that run for about 3 years. However, to monitor progress and to clearly define intermediate deliverables we partition the work into phases - following the spiral model for software development. The workpackages follow the logical phases of the project?s life-cycle. The major deliverables are tied to the completion of each workpackage.
These workpackages are:
1) Architecture Framework: considers how to integrate more flexible scheduling so that soft and firm real-time components can be utilised, fault tolerance is enhanced by the potential for dynamic reconfiguration, and incremental changes to software resulting can be accommodated;
2) Scheduler and Task integration Framework: will investigate the issue of integrating diverse scheduling schemes, such as fixed priority based, dynamic priority based, and offline construction, and task constraints. This includes the issue of combining time triggered and event triggered invocation paradigms, fault tolerance scheduling, hard and soft tasks, flexible constraints;
3) Operating Systems: will determine operating system functionality required to implement the support for the architectural framework in POSIX. Of particular concern is the efficiency and predictability of the various approaches along with their underlying complexity;
4) Internet Based Control: will address the issue of monitoring and control of the real-time system via the internet using a web based interface;
5) Case Studies and Examples: will apply the framework to several case studies in order to evaluate the efficacy of the overall approach. The use of general benchmarks will also be considered.
The workpackages will overall produce the following results:
- Architecture description, application interface- New scheduling algorithms, guide for application requirements, scheduling analysis tool;
- Operating System primitives for Shark and MARTE OS- Internet Control Tool;
- Case Studies teleoperated robot arm and autonomous robots;
- Proposal for inclusion and scheduling mechanisms in POSIX standard. Two dedicated workpackages, Dissemination and Exploitation, will make the results available and known to the academic and industrial communities of interest.
Ámbito científico
- natural sciencescomputer and information sciencesinternetinternet access
- natural sciencescomputer and information sciencessoftwaresoftware applicationssystem softwareoperating systems
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringcontrol systems
- natural sciencescomputer and information sciencessoftwaresoftware development
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringroboticsautonomous robots
Convocatoria de propuestas
Data not availableRégimen de financiación
CSC - Cost-sharing contractsCoordinador
721 23 VAESTERAAS
Suecia