Traffic Congestion Prediction using Soft computing Technique

-Network traffic forecasting has many important role to play in the domain of network traffic congestion control, its management and network traffic engineering. Characterizing the traffic and modeling are necessary for efficient functioning of the network. It is very vital for any model to depict self similarity, heavy tailed distribution and long range dependence (LRD). Thus modeling of time series is a challenging task. In the present work video stream prediction for application in services like video-on-demand, videoconferencing, video broadcasting, etc has been proposed. The main objective being is to forecast the variable bit rate (VBR) data stream for the allocation of efficient bandwidth of video signal. This plays an important role in traffic congestion control prediction. The model is fitted on a real data, consisting of training and test sets, taken from the video stream files of Telecommunication Networks Group, Technical University of Berlin, Germany. Here, an artificial intelligence model, known as Adaptive Neuro Fuzzy Inference System (ANFIS) has been proposed. The actual traffic data and the predicted traffic data is compared for performance evaluation of the model. Based on the prediction error the performance metrics are evaluated. Results confirm the simplicity and the better performance of ANFIS model. The work shows that ANFIS is able to forecast traffic congestion control from the point of view of bandwidth allocation. Key Words-Network Traffic, ANFIS, LRD, VBR.