Base Station Network Traffic Prediction Method Based on Wide & Deep Learning
[1]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]
Copy
Journal of Zhengzhou University (Engineering Science)[ISSN
1671-6833/CN
41-1339/T] Volume:
43
Number of periods:
2022 01
Page number:
7-13
Column:
Public date:
2022-01-09
- Title:
- Base Station Network Traffic Prediction Method Based on Wide & Deep Learning
- Keywords:
- Wide &; Deep model; deep learning; base station network traffic; traffic prediction; time series prediction; neural network
- CLC:
- TP393.0
- DOI:
- 10.13705/j.issn.1671-6833.2022.01.011
- 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.
- 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．
- Similar References:
Memo
-
Last Update:
2022-01-09