Title :
Sensitivity and uncertainty analysis in performability modelling
Author :
Haverkort, Boudewijn R. ; Meeuwissen, Adrianus M H
Author_Institution :
Tele-Inf. & Open Syst., Twente Univ., Enschede, Netherlands
Abstract :
The authors present an exact Taylor series model of steady state performability measures and discuss the validity region of this approximation. They also describe an uncertainty analysis approach based on Monte Carlo simulation, apply both approaches to a performability mode, and discuss their relative merits. They vary the dependencies between model parameters and discuss their influence. For the case studies done, the sensitivity analysis overestimated the mean performability and underestimated its variance
Keywords :
Monte Carlo methods; distributed processing; performance evaluation; series (mathematics); uncertainty handling; Monte Carlo simulation; exact Taylor series model; mean performability; model parameters; performability mode; steady state performability measures; uncertainty analysis approach; validity region; Distributed computing; Failure analysis; Fault tolerant systems; Open systems; Performance analysis; Performance evaluation; Sensitivity analysis; Steady-state; Taylor series; Uncertainty;
Conference_Titel :
Reliable Distributed Systems, 1992. Proceedings., 11th Symposium on
Conference_Location :
Houston, TX
Print_ISBN :
0-8186-2890-1
DOI :
10.1109/RELDIS.1992.235138
