Title :
Performance-aware software rejuvenation strategies in a queueing system
Author :
Okamura, Hiroyuki ; Dohi, Tadashi
Author_Institution :
Dept. of Inf. Eng., Hiroshima Univ., Higashi-Hiroshima, Japan
Abstract :
This paper deals with the performance analysis of a queueing system with rejuvenation controls. In particular, we describe the arrival process by the Markov-modulated Poisson process (MMPP) and consider a gradually degraded sever system. Under this situation, we discuss the system throughput of the queueing system and the optimal rejuvenation strategy maximizing the throughput based on the semi-Markov decision process in the case where the arrival and service rates are observable.
Keywords :
Markov processes; queueing theory; software fault tolerance; software performance evaluation; Markov-modulated Poisson process; performance-aware software rejuvenation strategies; queueing system; semiMarkov decision process; sever system; Aging; Degradation; Equations; Markov processes; Servers; Software systems;
Conference_Titel :
Software Aging and Rejuvenation (WoSAR), 2010 IEEE Second International Workshop on
Conference_Location :
San Jose, CA
Print_ISBN :
978-1-61284-344-5
DOI :
10.1109/WOSAR.2010.5722099