[1]陈浩杰,黄锦,左兴权,等.基于宽度&深度学习的基站网络流量预测方法[J].郑州大学学报(工学版),2022,43(01):7-13.[doi:10.13705/j.issn.1671-6833.2022.01.011]
 CHEN Haojie,HUANG Jin,ZUO Xingquan,et al.Base Station Network Traffic Prediction Method Based on Wide & Deep Learning[J].Journal of Zhengzhou University (Engineering Science),2022,43(01):7-13.[doi:10.13705/j.issn.1671-6833.2022.01.011]
点击复制

基于宽度&深度学习的基站网络流量预测方法()
分享到:

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
43
期数:
2022年01期
页码:
7-13
栏目:
出版日期:
2022-01-09

文章信息/Info

Title:
Base Station Network Traffic Prediction Method Based on Wide & Deep Learning
作者:
陈浩杰12黄锦12左兴权12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 Haojie12 HUANG Jin12 ZUO Xingquan12 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
关键词:
Keywords:
Wide & Deep model deep learning base station network traffic traffic prediction time series prediction neural network
分类号:
TP393.0
DOI:
10.13705/j.issn.1671-6833.2022.01.011
文献标志码:
A
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.

参考文献/References:

[1] 赵一权.无线网络运营数据分析与预测研究[D].北 京: 北京邮电大学,2018.

 [2] 蒋品.基于机器学习的蜂窝网络基站流量分析与预 测研究[D].北京: 北京邮电大学,2019. 
[3] 危彦.蜂窝网络中基于流量预测的节能关键技术研 究[D].杭州: 浙江大学,2012. 
[4] 张佳鑫,张兴,李永竞,等.蜂窝网络中基站关系与 业务关系网络与应用[J]. 中 国 科 学: 信 息 科 学, 2017,47( 5) : 648-663.
 [5] MADAN R,MANGIPUDI P S.Predicting computer network traffic: a time series forecasting approach using DWT,ARIMA and RNN[C]/ /2018 Eleventh International Conference on Contemporary Computing ( IC3) . Piscataway: IEEE,2018: 1-5. 
[6] LU H P,YANG F. Research on network traffic prediction based on long short-term memory neural network[C]/ /2018 IEEE 4th International Conference on Computer and Communications ( ICCC) . Piscataway: IEEE,2018: 1109-1113.
 [7] HUANG C W,CHIANG C T,LI Q H.A study of deep learning networks on mobile traffic forecasting[C]/ / 2017 IEEE 28th Annual International Symposium on Personal,Indoor,and Mobile Radio Communications ( PIMRC) . Piscataway: IEEE,2017: 1-6.
 [8] GUI Y H,WANG D S,GUAN L Y,et al. Optical network traffic prediction based on graph convolutional neural networks[C]/ /2020 Opto-Electronics and Communications Conference ( OECC) . Piscataway: IEEE, 2020: 1-3.
 [9] HOCHENBAUM J,VALLIS O S,KEJARIWAL A. Automatic anomaly detection in the cloud via statistical learning[EB/OL]. ( 2017- 04- 24) [2021- 05- 01]. https: / /arxiv.org /abs/1704. 07706. 
[10] YANG Z Y,ZHANG D Z,TANG J. Predicting PON networking traffic flow based on LSTM neural network with periodic characteristic data[C]/ /2020 IEEE 5th Optoelectronics Global Conference ( OGC ) . Piscataway: IEEE,2020: 39-42. 
[11] LIU H Z,YANG L T,CHEN J J,et al. Multivariate multi-order Markov multi-modal prediction with its applications in network traffic management[J]. IEEE transactions on network and service management, 2019,16( 3) : 828-841. 
[12] HAN Y,JING Y W,LI K,et al. Network traffic prediction using variational mode decomposition and multi-reservoirs echo state network[J]. IEEE access, 2019,7: 138364-138377. 
[13] 骆凯,罗军勇,尹美娟,等.一种基于动态阈值的突 发流量 异 常 检 测 方 法[J]. 信息工程大学学报, 2016,17( 4) : 509-512.
 [14] GHOSH D,VOGT A. Outliers: an evaluation of methodologies[C] / /Proceedings of the Survey Research Methods Section-JSM 2012. Washington DC: ASA, 2012: 3455-3460. 
[15] MIRZARGAR M,WHITAKER R T,KIRBY R M. Curve boxplot: generalization of boxplot for ensembles of curves[J]. IEEE transactions on visualization and computer graphics,2014,20( 12) : 2654-2663. 
[16] CLEVELAND U R B,CLEVELAND U W S,MCRAE U J E,et al.STL: a seasonal-trend decomposition procedure based on loess[J].Journal of official statistics, 1990,6( 1) : 3-73. 
[17] SCHULTE J A. Wavelet analysis for non-stationary, nonlinear time series[J]. Nonlinear processes in geophysics,2016,23( 4) : 257-267. 
[18] RILLING G,FLANDRIN P,GONCALVES P. On empirical mode decomposition and its algorithms[C] / /Proceedings of IEEE-EURASIP Workshop on Nonlinear Signal and Image Processing.Piscataway: IEEE, 2003: 8-11. 
[19] CHENG H T,KOC L,HARMSEN J,et al.Wide & deep learning for recommender systems[C]/ /Proceedings of the 1st Workshop on Deep Learning for Recommender Systems. New York: ACM,2016: 7-10.

更新日期/Last Update: 2022-01-09