基于宽度&深度学习的基站网络流量预测方法-《郑州大学学报(工学版)》

文章信息/Info

Title:: Base Station Network Traffic Prediction Method Based on Wide & Deep Learning

作者:: 陈浩杰¹; 2; 黄锦¹; 2; 左兴权¹; 2; 韩静³; 张百胜³; 北京邮电大学计算机学院;北京邮电大学可信分布式计算与服务教育部重点实验室;中兴通讯股份有限公司;

Author(s):: CHEN Haojie¹; 2; HUANG Jin¹; 2; ZUO Xingquan¹; 2; HAN Jing³; ZHANG Baisheng³; 1.School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China;
2.Key Laboratory of Trustworthy Distributed Computing and Service (BUPT)，Ministry of Education, Beijing 100876, China;3.Zhongxing Telecommunication Equipment Corporation, Shenzhen 518057, China

Keywords:: Wide &; Deep model; deep learning; base station network traffic; traffic prediction; time series prediction; neural network

摘要:: 针对无线网络流量长期预测问题，提出一种基于宽度&深度学习的基站网络流量预测方法。首先，利用S-H-ESD（Seasonal Hybrid Extreme Studentized Deviate Test）算法和数据平滑方法对网络流量数据进行预处理，以降低噪声数据对预测的影响。然后，将网络流量作为宽度&深度模型的深度部分（神经网络）的输入，将无线资源控制（Radio Resource Control，RRC）连接数和物理资源块（Physical Resource Block，PRB）利用率作为模型的宽度部分输入，通过深度和宽度部分结合来预测网络流量。该方法为所有基站的网络流量建立一个预测模型，以简化建模过程。将该方法用于实际网络流量预测，实验结果表明，该方法比季节性差分自回归滑动平均模型（Seasonal Autoregressive Integrated Moving Average，SARIMA）和BP神经网络模型具有更高的预测准确度。

Abstract:: Aiming at the long-term prediction problem of wireless communication network traffic, a base station network traffic prediction method was proposed based on Wide & Deep learning. Firstly, S-H-ESD (seasonal hybrid extreme studentized deviate test) algorithm and data smoothing method were used to preprocess the network traffic data, and to reduce the impact of noise data on the prediction. Then, the network flow was input into the deep part (neural network) of the Wide & Deep model, the radio resource control (RRC) and physical resource block (PRB) were input into the wide part (linear model) of the Wide & Deep model, and the deep and wide parts were combined to predict the network traffic. The method established one prediction model for the network traffic of all base stations. The root mean squared logarithmic error (RMSLE) of prediction results was 0.985, which was significantly better than that of the traditional seasonal autoregressive integrated moving average model (RMSLE was 2.095) and that of the long short-term memory network model (RMSLE was 3.281). Experimental results showed that the Wide & Deep model could better solve the problem of long-term prediction of wireless network traffic via combining the memory ability of the linear model and the generalization ability of the depth model.