计算机科学

计算机科学 ›› 2022, Vol. 49 ›› Issue (11A): 210800165-7.doi: 10.11896/jsjkx.210800165

• 计算机网络 • 上一篇    下一篇

多源跨域数据融合的无线通信网络流量预测

马冀1, 林尚静2, 李月颖2, 庄琲2, 贾睿2, 田锦1   

  1. 1 金陵科技学院网络与通信工程学院 南京 211169
    2 北京邮电大学电子工程学院 北京 100876
  • 出版日期:2022-11-10 发布日期:2022-11-21
  • 通讯作者: 马冀(maji@jit.edu.cn)
  • 基金资助:
    国家重点研发计划(2019YFC1511400);泛网无线通信教育部重点实验室开放基金(KFKT0-2020102);北京邮电大学中央高校基本科研业务费新进教师人才项目(2021RC07)

Traffic Prediction for Wireless Communication Networks with Multi-source and Cross-domain Data Fusion

MA Ji1, LIN Shang-jing2, LI Yue-ying2, ZHUANG Bei2, JIA Rui2, TIAN Jin1   

  1. 1 School of Networking and Communication Engineering,Jinling Institute of Technology,Nanjing 211169,China
    2 School of Electronic Engineering,Beijing University of Posts and Telecommunications,Beijing 100876,China
  • Online:2022-11-10 Published:2022-11-21
  • About author:MA Ji,born in 1982,Ph.D,lecturer.His main research interests include deep learning,distributed computing and edge computing.
  • Supported by:
    National Key R & D Program of China(2019YFC1511400),Key Laboratory of Universal Wireless Communications(BUPT),Ministry of Education(KFKT-2020102) and Fundamental Research Funds for the Central Universities(BUPT)( 2021RC07).

PDF (PC)

455

摘要： 精准地预测无线通信网络流量能够辅助运营商进行精细化运营,更高效地配备与部署基站资源,从而满足大量涌现的各种业务需求。然而,高度复杂的时空依赖性以及多源跨域因素的影响使得无线通信流量的精准预测面临着巨大的挑战。首先,对无线通信流量从时间属性、空间属性、社会属性、以及自然属性进行相关性分析,数据分析表明,无线通信流量具有多源跨域性;其次,基于对无线通信流量多重属性的全面分析,提出了一种改进的密集全连接网络模型MST-DenseNet。该模型利用单个DenseUnit结构的卷积操作捕获无线通信流量的空间相关性,利用多个并列的DenseUnit结构捕获无线通信流量在不同时间尺度上的相关性,同时考虑跨域数据对流量的影响,最终将通信流量自身的时空特征与跨域数据中的社会特征、自然特征高效融合,实现对无线通信流量的精准预测。在实际蜂窝数据集上与现有模型进行预测误差的对比,结果表明MST-DenseNet具有更高的预测精度。

关键词: 无线流量预测, 多源跨域, 数据融合, 时空依赖性, 密集卷积网络

Abstract: Precise prediction of wireless communication network traffic can assist operators in fine-tuned operations to efficiently allocate and deploy base station resources,and cater to a large number of emerging business needs.However,the highly complex temporal-spatial dependence and the influence of multi-source and cross-domain factors make accurate prediction of wireless communication traffic face huge challenges.Firstly,the correlation analysis of wireless communication traffic from temporal,spatial,social and natural attributes shows that wireless communication traffic has multi-source and cross-domain characteristics.Secondly,this paper proposes an improved dense fully connected network model MST-DenseNet.The model uses the convolution operation of a single DenseUnit structure to capture the spatial correlation of traffic,and uses multiple parallel DenseUnit structures to capture the temporal correlation of traffic on different scales.At the same time,considering the impact of cross-domain dataset on wireless traffic,this model integrates the temporal and spatial characteristics of communication traffic itself with the social and natural characteristics of cross-domain dataset to achieve accurate prediction of wireless communication traffic.Experiments show that,on the actual cellular dataset,MST-DenseNet has higher prediction accuracy compared with existing model.

Key words: Wireless traffic prediction, Multi-source cross-domain, Data fusion, Temporal-spatial dependence, Densenet

中图分类号: 

  • TN92
[1]SADEK N,KHOTANZAD A.Multi-scale high-speed network traffic prediction using k-factor Gegenbauer ARMA model[C]//Proceedings of the 2004 IEEE International Conference on Communications.Piscataway,IEEE,2004:2148-2152.
[2]HAG H M,SHARIF S M.An adjusted ARIMA model for internet traffic[C]//AFRICON 2007.Piscataway,IEEE,2007:1-6.
[3]HU X,DAI G,GE Y,et al.A Simplified Deep Residual Network for Citywide Crowd Flows Prediction[C]//2018 14th International Conference on Semantics,Knowledge and Grids(SKG).2018:60-67.
[4]GUO S,LIN Y,LI S,et al.Deep spatial-temporal 3D convolutional neural networks for traffic data forecasting[J].IEEE Transactions on Intelligent Transportation Systems,2019,20(10):3913-3926.
[5]HUANG D Y,YANG B,WU Z H,et al.Spatio-Temporal Fully Connected Convolutional Neural Networks for Citywide Cellular Prediction[J].Computer Engineering and Applications,2021,57(9):168-175.
[6]CUI Z Y,LI Z H.Network Traffic Prediction Based on k-hops Graph Convolutinal Autoencoder[J].Computing Technology and Automation,2020,39(4):169-174.
[7]ZHENG C,FAN X,WANG C,et al.Gman:a graph multi-attention network for traffic prediction[J].arXiv:1911.08415,2019.
[8]GUO S N,LIN Y F,JIN W W,et al.Citywide Crowd Flows Prediction Based on Spatio-Temporal Recurrent Convolutional Networks[J].Computer Science,2019,46(6A):385-391.
[9]ZHANG Z W,WU D,ZHANG C J.Study of Cellular Traffic Prediction Based on Multi-channel Sparse LSTM[J].Computer Science,2021,48(6):296-300.
[10]WU Y C.Research on Network Traffic Forecast Based on Neural Network[D].Sichuan:University of Electronic Science and Technology,2020.
[11]GU Z Y,CHEN C,ZHENG J J,et al.Traffic flow prediction based on STG-CRNN[J].Control and Decision,2022,37(3):645-653.
[12]ZHAO L,SONG Y,ZHANG C,et al.T-GCN:a temporal graph convolutional network for traffic prediction[J].IEEE Transactions on Intelligent Transportation Systems,2019,21(9):3848-3858.
[13]ZHANG H.Research and Improvement of Optimization Algorithms in Deep Learning[D].Beijing:Beijing University of Posts and Telecommunications,2018.
[14]LI X L,PAN G,WU Z H,et al.Prediction of urban human mo-bility using large-scale taxi traces and its applications[J].Frontiers of Computer Science,2012,6(1):111-121.
[15]JING W,JIAN T,XU Z,et al.Spatiotemporal modeling and prediction in cellular networks:A big data enabled deep learning approach[C]//IEEE INFOCOM 2017-IEEE Conference on Computer Communications.IEEE,2017.
[16]ZHANG C T,ZHANG H X,QIAO J P,et al.Deep Transfer Learning for Intelligent Cellular Traffic Prediction Based on Cross-Domain Big Data[J].IEEE Journal on Selected Areas in Communications,2019,37(6):1389-1401.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发