Dynamic Bandwidth Provisioning Using ARIMA-Based Traffic Forecasting for Mobile WiMAX
With fast proliferation of QoS-enabled wireless packet networks, need for effective QoS control is increasing. In this paper, the authors focus on QoS provisioning in Mobile WiMAX Access Service Network (ASN). They investigate a dynamic bandwidth provisioning method that can help to increase resource utilization. Their approach consists of two stages: traffic forecasting, followed by bandwidth provisioning. For the first stage, they use Auto-Regressive Integrated Moving Average (ARIMA) model to forecast traffic based on online measurement. For the second stage, they use a bandwidth provisioning scheme that allocates bandwidths depending on the traffic forecasting. They modeled their problem as a Fractional Knapsack Problem for which they used a greedy algorithm in order to find an approximate solution.