Network Traffic Prediction by Using Holt-Trend Time Series Model

Authors

  • Ahmed H. Alahmadi

Abstract

Network traffic prediction plays an important role in design, management and optimization modeling telecommunication network. Prediction of network traffic can allow planning capacity of network and we can improve the quality of service. Thus, now a days predicting of network traffic is significant interest of study for enhancing quality of services. Thus, achieving good quality of service for best future network traffic engineering the network traffic prediction is necessity. In this paper, we propose Holt-Trend (HTES) time series model to predict network traffic. The time series prediction model is employed to predict real network traffic. The Holt-Trend model is   examine by using on line network traffic data that collected from WIDE backbone Network. The standard evaluation metrics such as mean square error, root mean square error and mean absolute percentage error were used to evaluate the   prediction results of proposed model. The experimental results show that the proposed model can be an effective way to enhance prediction of network traffic prediction.

Published

2020-02-29

Issue

Section

Articles