Access Convergence for Heavy Load Markov Ethernet Bursty Traffic Using Two-level Statistical Multiplexing

Abstract

A method for modeling aggregated heavy Markov bursty Ethernet traffic from different sources is proposed in this paper, particularly that prevailing between gateway services and internet routing devices, with the aim of achieving rate accommodation. In other words, to accommodate different rates while filtering out delays in the queue, to achieve access network convergence. Although gateway functions can be used to achieve this by adapting service rates, as many gateways as services are required. Instead of considering the distributed gateway services method, statistical multiplexing is chosen for this study for cost efficiency in network resources. Unfortunately, statistical multiplexing exhibits greater packet variation (jitter) and transfer delay. These delays, basically resulting from positive correlations or time dependency in the queue system, are addressed through infinitesimal queue modeling, based on the diffusion process approximated by Ornstein-Uhlenbeck, which deals with infinitesimal changes in the Markov queue. The related analysis has resulted in an exponential queueing model for univariate and/or multivariate servers obtained through Markov Gaussian approximation. An experiment based on two different voice algorithms shows rate accommodation, and a fluid solution, which is dynamically outputted according to the transmission link availability during each transition time, without any significant delay. Hence, better transfer delay and rate control is obtained through the proposed two multiplexing levels within an Ethernet LAN