Markov model and a modified-SAW for network selection in a heterogeneous wireless environment

The network selection is one of the most important problems in nowadays networking issues; it means that the users want to be best served at each instant of its multimedia experience (VoIP and video conferencing services). In this paper, we address a real-world problem which is the frequent mobility of the users in heterogeneous networks. The paper proposes a framework that allows the users to select the best networks for the whole call session especially form a mobility perspective. The idea consists of starting by the path prediction which is done using the Markov model order 2. After that, we make the network selection on the zones of each predicted path to select one of them to be used by the user. The results show that our proposal performs very well compared to other proposed approaches while maintaining a good Quality of Service (QoS).