Modeling Connectivity of Ad Hoc Network Using Fuzzy Logic & Regression Analysis

One of the ad hoc network challenges is the network connectivity due to changeable and dynamic topology of network nodes. Since in ad hoc network every nodes plays the role of router, so it is possible that the movement of one or more nodes may disconnect the network. If the network get disconnected the desired data cannot be send from source to destination .So , in order to alleviate this problem we need some model that can tell us the number of connected nodes in the network for a given node density and transmission range . In this paper we propose a linear model to predict the network connectivity for the given node density and transmission range. We first use fuzzy logic to understand the connectivity by varying node density and transmission range. the resultant data is used for validation of our proposed model by using regression analysis. The R square value of our model is 0.9955, Ftest value is 178.29 and P value is 0.0001 , which indicates that our model is statistically significant . Keywords—Ad hoc networks, connectivity, topology control, critical transmitting range, node density, regression , correlation ,routing ,statistical analysis system, critical points, k-connectivity, fuzzy logic.