Perfect Simulations for Random Trip Mobility Models

Abstract

The random trip model was recently proposed as a generic mobility model that contains many particular mobility models, including the widely-known random waypoint and random walks, and accommodates more realistic scenarios. The probability distribution of the movement of a mobile in all these models typically varies with time and converges to a distribution (viz- stationary distribution), whenever the last exists. Protocol performance during this transient phase and in steady-state may differ significantly. This justifies the interest in perfect sampling of the initial node mobility state, so that the simulation of the node mobility is perfect, i.e. it is in steady state throughout a simulation. In this work, we describe implementation of the perfect sampling for some random trip models. Our tool produces a perfect sample of the node mobility state, which is then used as input to the widely-used ns-2 network simulator. We further show some simulation results for a particular random trip mobility model, based on a real-world road map. The performance metrics that we consider include various node communication properties and their evolution with time. The results demonstrate difference between transient and steady-state phases and that the transient phase can be long lasting (in the order of a typical simulation duration), if the initial state is drawn from a non steady-state distribution. The results give strong arguments in favor to running perfect simulations. Our perfect sampling tool is available to public at: http://www.cs.rice.edu//spl sim/santa/research/mobility.