Abstract The usual measures of traffic correlation do not determine the traffic process completely. Consequently there may be a number of traffic processes which induce the same correlation but which differ in other features and so differ in impact on performance. An experiment was devised to distinguish the effects of traffic process features from the effects due to the correlation alone. The batch renewal process is the ideal of a correlated traffic process and so provides the standard (in terms of buffer congestion, etc.) against which the performance impact of any other correlated traffic process may be compared. This paper presents results of the experiment as performed upon the Markov modulated processes, together with further analysis to assess the applicability of the findings, and concludes that a Markov modulated process is likely to yield more optimistic estimates of cell loss rate, delay, etc., than are attributable to the traffic correlation alone, especially in simple models with a low number of phases.
Correlated Traffic Modelling: Batch Renewal and Markov Modulated Processes
1997-01-01
24 pages
Article/Chapter (Book)
Electronic Resource
English
Traffic improvement, urban renewal
Engineering Index Backfile | 1959
|Traffic and transportation in urban renewal
Engineering Index Backfile | 1960
|Study on iterative availability algorithm of Markov renewal equation
British Library Online Contents | 2004
|Modelling of ATM Traffic Processes
NTIS | 1989
|Renewal Processes and Repairable Systems
NTIS | 2003
|