ZTE

ZTE Communications ›› 2015, Vol. 13 ›› Issue (4): 61-64.doi: 10.3969/j.issn.1673-5188.2015.04.009

• Research Paper • Previous Articles    

Predicting LTE Throughput Using Traffic Time Series

Xin Dong1, Wentao Fan1, Jun Gu2   

  1. 1. Beijing University of Posts and Telecommunications, Beijing,100876, China;
    2. ZTE Corporation, Shanghai 201203, China
  • Received:2015-07-31 Online:2015-12-25 Published:2015-12-25
  • About author:Xin Dong (dongxin2014@gmail.com) is pursuing her master’s degree in telecommunications at Beijing University of Post and Telecommunications (BUPT). Her research interests include data mining and time series analysis. She has previously researched the prediction of time serials of traffic flow.
    Wentao Fan (ffantastic@126.com) is pursuing his master’s degree in telecommunications at BUPT. His research interests include data mining, and network analysis and optimization based on mobile devices. He has researched the prediction of time serials of traffic flow using the SVR method.
    Jun Gu (gu.jun@zte.com.cn) is a chief engineer of 4G radio network planning at ZTE Corporation. He has 10 years’research and field experience in network principles, standardization, simulation, algorithm design, and planning and optimization.

PDF (PC)

Abstract: Throughput prediction is essential for congestion control and LTE network management. In this paper, the autoregressive integrated moving average (ARIMA) model and exponential smoothing model are used to predict the throughput in a single cell and whole region in an LTE network. The experimental results show that these two models perform differently in both scenarios. The ARIMA model is better than the exponential smoothing model for predicting throughput on weekdays in a whole region. The exponential smoothing model is better than the ARIMA model for predicting throughput on weekends in a whole region. The exponential smoothing model is better than the ARIMA model for predicting throughput in a single cell. In these two LTE network scenarios, throughput prediction based on traffic time series leads to more efficient resource management and better QoS.

Key words: ARIMA, exponential smoothing method, throughput prediction