Title :
Probabilistic performance analysis in multiprocessor scheduling
Author :
Nissanke, Nimal ; Leulseged, Amare ; Chillara, Srinivas
Author_Institution :
Sch. of Comput., Inf. Syst. & Math., South Bank Univ., London, UK
Abstract :
A novel probabilistic framework for the study of performance issues in multiprocessor scheduling of tasks with uncertain characteristics is proposed. It enables the determination of various performance measures, such as the overall completion rate from a probabilistic picture of the tasks currently under execution, formed from a probabilistic description of newly arriving tasks and assignment of processors. Once optimised, these measures may be used to guide the decisions of schedulers at run time.
Keywords :
embedded systems; multiprocessing systems; performance evaluation; probability; processor scheduling; uncertain systems; multiprocessor scheduling; newly arriving tasks; optimised performance measures; overall completion rate; probabilistic performance analysis; processor assignment; real-time embedded systems; run-time scheduler decisions; uncertain task characteristics;
Journal_Title :
Computing & Control Engineering Journal
DOI :
10.1049/cce:20020403
