Loosely-coordinated, distributed, packet-level network simulation

Abstract

The complexity and dynamics of the Internet is driving the demand for scalable and efficient network simulation. In this thesis, we describe a novel approach to scalability and efficiency of parallel network simulation that partitions the networks into domains and simulation time into intervals. Each domain is simulated independently of and concurrently with the others over the same simulation time interval. At the end of each interval, traffic statistics data, including per flow average packet delays and packet drop rates, are exchanged between domain simulators. The simulators iterate over the same time interval until the exchanged information converges to the value within a prescribed precision before progress to the next time interval. This approach allows the parallelization with infrequent synchronization, and achieves significant simulation speedups. Large memory size required by simulation software hinders the simulation of large-scale networks. To overcome this problem, our system supports distributed simulations in such a way that each participating simulator possesses only data related to the part of the network it simulates. This solution supports simulations of large-scale networks on machines with modest memory size.