DocumentCode :
3673547
Title :
Analysis of Hypoexponential Computing Services for Big Data Processing
Author :
Sergey Zapechnikov;Natalia Miloslavskaya;Alexander Tolstoy
Author_Institution :
Moscow Eng. Phys. Inst., Nat. Res. Nucl. Univ., Moscow, Russia
fYear :
2015
Firstpage :
579
Lastpage :
584
Abstract :
The paper presents two analytical models to study the performance and availability of queueing systems with the hypo exponential service time and finite queue. The analytical results obtained are verified using discrete-event simulation. A few numerical examples for varying number of service stages, service rates and arrival rates are given. The results presented in the paper can be used for analysis of MapReduce and multi-stage Big Data processing.
Keywords :
"Analytical models","Numerical models","Queueing analysis","Computational modeling","Servers","Big data","Steady-state"
Publisher :
ieee
Conference_Titel :
Future Internet of Things and Cloud (FiCloud), 2015 3rd International Conference on
Type :
conf
DOI :
10.1109/FiCloud.2015.57
Filename :
7300870
Link To Document :
بازگشت