A learning automata-based method for estimating the mobility model of nodes in Mobile Ad-Hoc NETworks

The mobility model of typical mobile ad-hoc networks (MANET) can be used for more efficient performance evaluation of such networks. There are a large number of researches for generating various mobility models to use in performance evaluation of mobile ad-hoc networks and also on performance evaluation itself of these networks. But in most of these researches the mobility model of MANET is predefined and based on this mobility model, the performance evaluation goes on. Since in real world applications the mobility model of MANETs is unknown or may be changed during the time, the need for a method of detecting or estimating the MANETpsilas mobility model is evident. In this paper a learning automata-based method for estimating the MANETpsilas mobility model has been proposed. Simulation results show that, in approximately 90% of cases, the proposed algorithm can estimate the mobility model correctly.