A stochastic reward net model for performance analysis of prioritized DQDBMAN

The performance of prioritized distributed queue dual bus (DQDB) metropolit an area network (MAN) under bursty traffic environment is studied in this a rticle. The tagged node model is adopted to simplify the analysis. The proc esses of the packet arrivals to the tagged node, the empty-slot pattern fro m the upstream, and the request pattern from the downstream are assumed to be Markov Modulated Poisson Processes, a more general and appropriate model to capture the bursty characteristics existing in the traffic Bows in high -speed networks. A stochastic reward nets model for the prioritized DQDB MA N is presented. With the help of the stochastic petri net package developed in Duke University, the steady state and as well as the transient behavior of packet loss ratio of tagged node are investigated. The influence of the burstiness of the empty-slot pattern, packet arrival and request pattern o n the tagged node's performance are examined. (C) 1999 Elsevier Science B.V . All rights reserved.