Current systems either relegate aperiodic tasks to background status when aperiodic response time is not critical or use polling when it is. The authors develop a novel approach to this scheduling problem, which they characterize as bandwidth-preserving algorithms. The goal is to develop algorithms with superior performance that also have predictable behavior and can be used by a real-time-system developer in constructing and integrating systems. The authors develop a full analysis of the worst-case behavior and stability of this family of algorithms.
|Original language||English (US)|
|Title of host publication||Unknown Host Publication Title|
|Number of pages||10|
|State||Published - 1987|
ASJC Scopus subject areas
- Hardware and Architecture
- Computer Networks and Communications