基于时空特征的移动网络流量预测模型

doi:10.11896/jsjkx.181102207

计算机科学 ›› 2019, Vol. 46 ›› Issue (12): 108-113.doi: 10.11896/jsjkx.181102207

基于时空特征的移动网络流量预测模型

张杰¹, 白光伟¹, 沙鑫磊¹, 赵文天¹, 沈航^1,2

(南京工业大学计算机科学与技术学院南京211816)¹;
(南京邮电大学通信与网络技术国家工程研究中心南京210003)²

收稿日期:2018-11-28 出版日期:2019-12-15 发布日期:2019-12-17
通讯作者: 白光伟(1961-),男,教授,博士生导师,CCF杰出会员,主要研究方向为移动互联网、多媒体网络服务质量、网络系统性能分析和评价等,E-mail:bai@njtech.edu.cn。
作者简介:张杰(1993-),男,硕士生,主要研究方向为网络流量预测等,E-mail:njutzhangjie@njtech.edu.cn;沙鑫磊(1995-),男,硕士生,主要研究方向为智能移动网络、智能路由算法等;赵文天(1995-),男,硕士生,CCF学生会员,主要研究方向为绿色移动网络;沈航(1984-),男,博士,讲师,CCF会员,主要研究方向为移动互联网、无线多媒体通信协议等。
基金资助:
本文受国家自然科学基金项目(61502230,61073197,61501224),江苏省自然科学基金项目(BK20150960),江苏省普通高校自然科学研究项目(15KJB520015),南京市科技计划项目(201608009),南京大学计算机软件新技术国家重点实验室资助项目(KFKT2017B21),江苏省研究生科研与实践创新计划项目(KYCX18_1074)资助。

Mobile Traffic Forecasting Model Based on Spatio-temporal Features

ZHANG Jie¹, BAI Guang-wei¹, SHA Xin-lei¹, ZHAO Wen-tian¹, SHEN Hang^1,2

(College of Computer Science and Technology,Nanjing Tech University,Nanjing 211816,China)¹;
(National Engineering Research Center for Communication and Network Technology,Nanjing University ofPosts and Telecommunications,Nanjing 210003,China)²

Received:2018-11-28 Online:2019-12-15 Published:2019-12-17

摘要/Abstract

摘要： 研究表明,历史流量数据可以用于移动网络流量的预测,同时周边区域的流量信息可以提高流量预测的准确性。为此,文中提出一种基于时空特征的移动网络流量预测模型STFM。STFM模型利用目标区域及周围区域的历史移动网络流量对目标区域的流量进行预测。其核心思想是,首先利用三维卷积网络(3D CNN)从流量中提取移动网络流量空间上的特征,再利用时间卷积网络(TCN)提取移动网络流量时间上的特征,最后全连接层对提取的特征与实际的流量值建立映射关系,产生预测的流量值。根据实验的验证与分析,STFM在移动网络流量预测上的标准均方根误差(NRMSE)相比TCN,CNN和CNN-LSTM分别减少了28%,21.7%和10%。因此,STFM模型能够有效提高移动网络流量预测的准确率。

关键词: 移动网络, 流量预测, 时空特征, 卷积网络, 全连接层

Abstract: Research shows that historical traffic data can be used for the prediction of mobile network traffic,and traffic information in surrounding areas can improve the accuracy of traffic prediction.To this end,this paper proposed the traffic prediction model STFM for mobile network based on spatio-temporal features.STFM uses the historical mobile traffic of the target area and surrounding areas to predict the traffic of the target area.Firstly,3D convolutional neural network(3D CNN) is used to extract the spatial features of the mobile network traffic,then time convolutional network (TCN) is used to extract the temporal features of the mobile network traffic.Finally,fully connected layers establish a mapping relationship between the real traffic and extracted features and generate a predicted traffic value.Validation and analysis of experiments show that the STFM reduce the normalized root mean square error (NRMSE) by 28%,21.7% and 10%,compared to TCN,CNN and CNN-LSTM Consequently,STFM can effectively improve the accuracy of mobile network traffic prediction.

Key words: Mobile network, Traffic prediction, Spatio-temporal feature, Convolution neural network, Fully connected layers

中图分类号:

TP393

张杰, 白光伟, 沙鑫磊, 赵文天, 沈航. 基于时空特征的移动网络流量预测模型[J]. 计算机科学, 2019, 46(12): 108-113.

ZHANG Jie, BAI Guang-wei, SHA Xin-lei, ZHAO Wen-tian, SHEN Hang. Mobile Traffic Forecasting Model Based on Spatio-temporal Features[J]. Computer Science, 2019, 46(12): 108-113.

参考文献 18

[1]	Cisco Visual Networking Index:Forecast and Methodology 2016－2021[EB/OL].https://www.cisco.com/c/en/us/solutions/collateral/service-provider/visual-networking-index-vnicomplete-white-paper-c11-481360.html.
[2]	SUNDARESAN K.5G:An Evolution towards a Revolution[C]// Proceedings of ACM International Conference on Mobile Computing and Networking.New Delhi,India,2018:659-659.
[3]	IMRAN A,ZOHA A.Challenges in 5G:How to Empower SON with Big Data for Enabling 5G [J].IEEE Network,2014,28(6):27-33.
[4]	NIU Z,WU Y,GONG J,et al.Cell Zooming For Cost-Efficient Green Cellular Networks [J].IEEE Communications Magazine,2010,48(11):74-79.
[5]	XU F,LIN Y,HUANG J,et al.Big Data Driven Mobile Traffic Understanding and Forecasting:A Time Series Approach [J].IEEE Transactions on Services Computing,2016,9(5):796-805.
[6]	SHU Y,YU M,LIU J,et al.Wireless Traffic Modeling and Pre- diction Using Seasonal ARIMA Models[C]//Proceedings of IEEE International Conference on Communications.Anchorage:IEEE,2003:1675-1679.
[7]	LI R,ZHAO Z,ZHENG J,et al.The learning and prediction of application-level traffic data in cellular networks [J].IEEE Transactions on Wireless Communications,2017,16(6):3899-3912.
[8]	ZHANG C,PAUL P.Long-term mobile traffic forecasting using deep spatio-temporal neural networks[C]//Proceedings of ACM International Symposium on Mobile Ad Hoc Networking and Computing.Angeles:ACM,2018:231-240.
[9]	OLIVEIRA T P,BARBAR J S,SOARES A S.Computer Network Traffic Prediction:A Comparison between Traditional and Deep Learning Neural Networks [J].International Journal of Big Data Intelligence,2016,3(1):28-37.
[10]	NAREJO S,PASERO E.An Application of Internet Traffic Prediction with Deep Neural Network [J].Multidisciplinary Approaches to Neural Computing,2018,69(1):139-149.
[11]	HUANG C W,CHIANG C T,LI Q.A Study of Deep Learning Networks on Mobile Traffic Forecasting[C]//Proceedings of IEEE Personal,Indoor,and Mobile Radio Communications.Montreal:IEEE,2017:1-6.
[12]	LI R,ZHAO Z,ZHOU X,et al.The Prediction Analysis of Cellular Radio Access Network Traffic:From Entropy Theory to Networking Practice [J].IEEE Communications Magazine,2014,52(6):234-240.
[13]	FU R,ZHANG Z,LI L.Using LSTM and GRU neural network methods for traffic flow prediction[C]//Proceedings of IEEE Youth Academic Annual Conference of Chinese Association of Automation.Wuhan:IEEE Press,2016:324-328.
[14]	YU F,KOLTUN V.Multi-scale context aggregation by dilated convolutions[C]//Proceedings of International Conference on Learning Representations.San Juan:ICLR,2016.
[15]	HE K,ZHANG X,REN S,et al.Deep residual learning for ima- ge recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Nevada:IEEE,2016:770-778.
[16]	ZHOU F Y,JIN L P,DONG J.Review of Convolutional Neural Network[J].Chinese Journal of Computers,2017,40(6):1229-1251.
[17]	IOFFE S,SZEGEDY C.Batch normalization:accelerating deep network training by reducing internal covariate shift[C]//Proceedings of International Conference on International Conference on Machine Learning.Lille:ACM,2015:448-456.
[18]	GIANNI B,MARCO D N,ROBERTO L,et al.A multi-source dataset of urban life in the city of Milan and the Province of Trentino[J].Scientific Data,2015,2:150055.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于时空特征的移动网络流量预测模型

Mobile Traffic Forecasting Model Based on Spatio-temporal Features

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献 18

相关文章 15

Metrics

本文评价

推荐阅读 10

[1]	王教金, 蹇木伟, 刘翔宇, 林培光, 耿蕾蕾, 崔超然, 尹义龙. 基于3D全时序卷积神经网络的视频显著性检测[J]. 计算机科学, 2020, 47(8): 195-201.
[2]	曹素娥, 杨泽民. 基于聚类分析算法和优化支持向量机的无线网络流量预测[J]. 计算机科学, 2020, 47(8): 319-322.
[3]	罗婷瑞, 贾建, 张瑞. 基于可调Q因子小波变换和迁移学习的癫痫脑电信号检测[J]. 计算机科学, 2020, 47(7): 199-205.
[4]	蒋宗礼, 李苗苗, 张津丽. 基于融合元路径图卷积的异质网络表示学习[J]. 计算机科学, 2020, 47(7): 231-235.
[5]	任天赐, 黄向生, 丁伟利, 安重阳, 翟鹏博. 全局双边网络的语义分割算法[J]. 计算机科学, 2020, 47(6A): 161-165.
[6]	祁宝莲, 钟坤华, 陈芋文. 基于卷积神经网络的半监督手术视频流程识别[J]. 计算机科学, 2020, 47(6A): 172-175.
[7]	熊亭, 戚湧, 张伟斌. 基于DCGRU-RF模型的路网短时交通流预测[J]. 计算机科学, 2020, 47(5): 84-89.
[8]	李太松,贺泽宇,王冰,颜永红,唐向红. 基于循环时间卷积网络的序列流推荐算法[J]. 计算机科学, 2020, 47(3): 103-109.
[9]	姚立霜, 刘丹, 裴作飞, 王云锋. 基于EMD聚类的实时网络流量预测模型[J]. 计算机科学, 2020, 47(11A): 316-320.
[10]	张德干, 杨鹏, 张捷, 高瑾馨, 张婷. 基于量子粒子群优化策略的车联网交通流量预测方法[J]. 计算机科学, 2020, 47(11A): 327-333.
[11]	李凯文, 徐琳, 陈强. 基于CPNet的相对图像质量评估[J]. 计算机科学, 2020, 47(11): 159-167.
[12]	方杰, 李培峰, 朱巧明. 基于多注意力机制的事件同指消解方法[J]. 计算机科学, 2019, 46(8): 277-281.
[13]	孔繁钰, 周愉峰, 陈纲. 基于时空特征挖掘的交通流量预测方法[J]. 计算机科学, 2019, 46(7): 322-326.
[14]	郭晟楠, 林友芳, 金文蔚, 万怀宇. 基于时空循环卷积网络的城市区域人口流量预测[J]. 计算机科学, 2019, 46(6A): 385-391.
[15]	冯贵兰, 李正楠, 周文刚. 大数据分析技术在网络领域中的研究综述[J]. 计算机科学, 2019, 46(6): 1-20.