DocumentCode
2896059
Title
Performance evaluation of ATM architectures in multimedia traffic environments
Author
Behera, Siddharth ; Meempat, Gopal
Author_Institution
Dept. of Comput. Sci. & Eng., Nebraska Univ., Lincoln, NE, USA
fYear
1991
fDate
8-11 Dec 1991
Firstpage
695
Lastpage
704
Abstract
A simulation model for the performance evaluation of fast packet switching architectures under multimedia traffic conditions is presented. The simulator is based on an integration of the SLAM-II tool with special-purpose C routines that model the internal structure and operational details of the basic switching fabrics. Two types of traffic sources, namely, Bernoulli sources and correlated sources (modeled as two-state Markov chains) are considered. The latter class of sources provides an accurate model for multimedia traffic components, such as voice and video, which are inherently bursty. The results of the simulation indicate the significant deterioration of the switch performance under correlated traffic from that predicted by the Bernoulli models. Furthermore, they illustrate the efficacy of the input-windowing mechanism in remedying this drawback to a substantial degree
Keywords
Markov processes; digital simulation; multimedia systems; packet switching; performance evaluation; telecommunications computing; time division multiplexing; ATM architectures; Bernoulli sources; SLAM-II tool; correlated sources; fast packet switching architectures; input-windowing mechanism; internal structure; multimedia traffic environments; operational details; performance evaluation; simulation model; special-purpose C routines; switch performance; two-state Markov chains; Asynchronous transfer mode; Computational modeling; Computer architecture; Fabrics; ISDN; Packet switching; Predictive models; Switches; Telecommunication traffic; Traffic control;
fLanguage
English
Publisher
ieee
Conference_Titel
Simulation Conference, 1991. Proceedings., Winter
Conference_Location
Phoenix, AZ
Print_ISBN
0-7803-0181-1
Type
conf
DOI
10.1109/WSC.1991.185675
Filename
185675
Link To Document