Analytical model for jitter in networks with IPP traffic
In this paper we analyze jitter behavior for Interrupted Poisson process (IPP) as incoming traffic. We propose model for jitter on one node, as well as for end-to-end jitter with IPP traffic on network nodes. Our model describes jitter behavior with respect to phase probabilities, traffic load, and tagged traffic share in aggregate traffic flow. We conclude that jitter for IPP is heavily dependent on phase probabilities, and larger than jitter for Poisson process, as one limit case of IPP. End-to-end jitter always takes values between first node jitter value and sum of individual jitter values on each node. We offer more precise evaluation of these values, which also leads to some fast-to-compute approximations for limit cases of phase probabilities and traffic load. We propose our results as guidelines for jitter evaluation for real IP traffic.