Stochastic Process Models for Packet/Analytic-Based Network Simulations
Traditional discrete-event packet-level approaches to simulating computer networks become computationally infeasible as the number of network nodes or their complexity increases. An alternative approach, in which packet-level traffic sources are replaced by fluid sources, has been proposed to address this challenge. In this paper we compare the amount of computational effort needed to simulate a network using a packet-level approach versus a fluid-based approach. We quantitatively characterize the amount of computational effort needed by each approach using the notion of a simulation’s event rate, and derive expressions for the event rate of a packet and fluid flow at both the input and output sides of a queue. We show that fluid simulation can require less computational effort for simple networks. However, as the network size and complexity grow, the so-called ”ripple effect” can result in fluid simulations becoming more expensive than their packet-level counterparts. This suggests that time-driven (approximate) fluid simulation techniques may be needed to efficiently simulate large scale networks.