Artificial neural networks by using the internet traffics on the internet exit routers (MTRG) estimated traffic analysis and planning for the future

In this study, particularly, traffic knowledge was collected on routers which are used in 20 locations according to time period and the internet connection characteristics were determined for every location. MRTG was used for collecting these values.An Artificial Neural Networks (ANN) application was developed by using collected values which contain variables of hour, day, mount, upload/download and connected users. Matlab Neural Network Toolbox was used for realizing of Neural Network applications. Back propagation (BP) and radial basis function (RBF) neural networks were used as network models. The solutions for each method were compared and recognized that BPN was found as a best method between back propagation (BP) and radial basis function (RBF).Keywords: Artificial neural networks, Back Propagation-BP, Radial Basis Function-RBF, MRTG, Internet traffic.