DocumentCode :
3413420
Title :
Traffic analysis in large-scale high-speed integrated networks: validation of nodal decomposition approach
Author :
Lau, Wing-Cheong ; Li, San-qi
Author_Institution :
Dept. of Electr. & Comput. Eng., Texas Univ., Austin, TX, USA
fYear :
1993
fDate :
1993
Firstpage :
1320
Abstract :
The conditions under which nodal decomposition can be applied for networkwide, multimedia traffic analysis are determined. Through extensive simulation studies of individual departure source characteristics and intersource cross-correlation at the output side of a network node, the nodal decomposition approach is validated for large-scale high-speed, integrated networks. Both homogeneous and heterogeneous traffic environments in which individual sources are modeled as various two-state/multiple-state Markov-modulated processes are considered. By applying the validated nodal decomposition approach, the problem of analyzing the performance of a multimedia network as a whole becomes tractable. Each ATM node is modeled by a queue with infinite buffers and a deterministic server
Keywords :
Markov processes; asynchronous transfer mode; multimedia systems; queueing theory; telecommunication networks; telecommunication traffic; ATM; Markov-modulated processes; departure source characteristics; deterministic server; heterogeneous traffic; homogeneous traffic; infinite buffers; intersource cross-correlation; large-scale high-speed integrated networks; multimedia traffic analysis; network node; network performance; nodal decomposition; queueing analysis; Computational modeling; High speed integrated circuits; Integrated circuit interconnections; Intelligent networks; Large scale integration; Performance analysis; Queueing analysis; Streaming media; Telecommunication traffic; Traffic control;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
INFOCOM '93. Proceedings.Twelfth Annual Joint Conference of the IEEE Computer and Communications Societies. Networking: Foundation for the Future, IEEE
Conference_Location :
San Francisco, CA
Print_ISBN :
0-8186-3580-0
Type :
conf
DOI :
10.1109/INFCOM.1993.253395
Filename :
253395
Link To Document :
بازگشت