Queueing analysis of delay constrained voice traffic in a packet switching system

Unlike data traffic, the voice packet stream from a node has very high correlation between consecutive packets. In addition, in order for the speech to be properly reconstructed, a delay constraint must be satisfied. A queueing model that accurately predicts packet loss probabilities for such a system is presented. Analytical results are obtained from an embedded bivariate Markov chain and are validated by a simulation program. Based on this model, the impact of the delay constraint, talkspurt detection thresholds, and packet size on packet loss are studied. Two schemes, named 'instant' and 'random', for discarding late packets are considered. Simulation results show that better performance can be obtained by using the latter scheme. >