An overview of fluid-based quick simulation techniques for large packet-switched communication networks

We consider a large packet-switched communication network. Traffic in such networks is heavily aggregated especially in the network core. Fluid traffic models have been used for this reason and because the individual packets are very small compared to the volume of aggregated traffic. Fluid models have also been considered for the network components themselves in order to explore the possibility of simulation speed-up. In the event-driven simulation of Kesidis et al⁶ of such a "fluid" network, a "ripple effect" was described to explain the substantial degradation in simulation speed-up as the network size grew, especially when work-conserving bandwidth schedulers were present. Thereafter, studies attempted to identify under what network dimensions and designs and under what traffic conditions the ripple effect is minimized. Hybrids of packet/fluid and event/time-driven simulation strategies were considered. This paper gives an overview of the fluid network modeling approach and surveys recent work on such hybrid approaches.