Network Traffic Prediction Model Based on Training Data

Jinwoo Park, Syed M. Raza, Pankaj Thorat, Dongsoo S. Kim, Hyunseung Choo

Abstract: Real-time audio and video services have gained much popularity in last decade, and now occupying a large portion of the total network traffic in the Internet. As the real-time services are becoming mainstream the demand for Quality of Service (QoS) is greater than ever before. To satisfy the increasing demand for QoS, it is necessary to use the network resources to the fullest. In this regards, the available bandwidth based routing is a promising solution. Unfortunately the instantaneous available bandwidth of a network is not enough as it may change the next moment in highly dynamic networks. To solve this issue, we present a prediction model for network traffic, on the basis of which network available bandwidth can be estimated. This paper utilizes the efforts done in regard to road traffic prediction to formulate a prediction model for network traffic.