Complex real-time systems, such as those envisaged for autonomous vehicle control, are expected to exhibit; adaptive and dynamic behavior, resilience to software/hardware failures and graceful degradation under conditions of overload. Two objectives need to be met before such properties can be realized. First, critical services must be guaranteed to provide results of a minimum acceptable quality and reliability by their deadlines. Second, the utility of the system needs to be maximized. An approach to meeting the above objectives is presented. This approach combines the benefits of both fixed priority pre-emptive and best-effort scheduling: off-line analysis is used to guarantee that critical timing requirements will be met, whilst at run-time, a simple adaptive threshold policy arbitrates between competing optional components, enhancing the system utility obtained.
Flexible scheduling for adaptable real-time systems
Ein flexibler Scheduling-Algorithmus für adaptive Echtzeitsysteme
1995
10 Seiten, 4 Bilder, 17 Quellen
Conference paper
English
An Adaptable Object Model for Real-Time Systems Design
British Library Conference Proceedings | 1996
|Distributed Real-time Scheduling for Flexible Manufacturing
British Library Online Contents | 1995
|