Forecasting 5G Network Multimedia Traffic Characteristics

Abstract

The task of forecasting multimedia data traffic with an important amount of pulsations and the long-term dependence is considered. The results of forecasting multimedia data traffic characteristics were obtained. The use of the spline-extrapolation method has several advantages over other known methods, namely, ease of practical implementation, high accuracy of forecasting, the ability to accurately extrapolate peak "bursts" of traffic, which is especially important when solving problems in real time. The results will allow the raising the efficiency of network equipment use, as well as the provision of the required of buffer devices and the avoidance of network congestion. In addition it will balance the network object download without exceeding the regulatory QoS characteristics values.