Modeling of prediction bandwidth density with backpropagation neural network (BPNN) methods

Abstract

Using computer networks in campus area which is open access will cause some problems at the speed to access the information. The allocation of bandwidth that provided sometimes does not match the needs of the client, so it takes an accurate prediction of bandwidth usage. This research obtained that Neural Network backpropagation modeling can solve the problem. The stages of research conducted the stage of training and testing phase. Data training is traffic data weekly and conducted by feed-forward back method, with max error 0.001, max hidden layer neuron 5000, constant momentum 0.95 and increase ratio 0.1. Before the data train is conducted, the scaling of the input and target values in the range of 0.1-0.9, then resumes the denormalization after the data train to return the data into Kb form. The results obtained from the training process in the form of comparison data, training performance, and regression. Furthermore, data testing, conducted by using a network that has been developed from the previous results. The test results are shown in the form of real data and predictive data using 8 input layers. In the prediction process, the mean square error generated is 0.0031792 which indicates a low error rate, so it can be stated that the resulting modeling has a level of output accuracy in predicting the use of computer network bandwidth is very high.