基于图卷积神经网络的SDN网络流量预测

doi:10.11896/jsjkx.200800090

摘要/Abstract

摘要： 精确和实时的网络流量预测在SDN网络中扮演着重要角色,同时对流量工程、网络控制起到重要作用。由于网络拓补的约束和时间的动态变化,即空间和时间特征,使得网络流量预测问题已经成为一个公认的科学问题。为了有效提取空间和时间特征,提出一种基于神经网络的预测模型,即结合了图卷积和门控循环单元的模型。图卷积网络可以有针对性地提取到复杂拓补的空间特征,同时门控循环单元能提取到流量的时间特征,两者的结合可以有效地预测软定义网络中的流量。在模型性能比较方面,将提出的GCGRU与经典方法进行了比较。评估指标包括MSE,RMSE,MAE。实验结果表明,GCGRU能够更有效地进行流量预测。

关键词: 流量预测, 图卷积网络, 空间依赖, 时间依赖, 软定义网络

Abstract: Accurate and real-time traffic forecasting plays an important role in the SDN and is of great significance for network traffic engineer,and network plan.Because of the constraints of network topological structure and the dynamic change of time,that is,spatial and time features,network traffic prediction has been considered as a scientific issue.In order to capture the spatial and temporal dependence simultaneously,the Graph Convolutional Gated Recurrent Unit Network model(GCGRU) is proposed,a neural network-based traffic forecasting method,which is in combination with the graph convolutional network (GCN) and gated recurrent unit (GRU).Specifically,GCN is used to learn complex topological structures to capture spatial dependence and Gated Recurrent Unit is used to learn dynamic changes of traffic data to capture temporal dependence.In terms of model perfor-mance comparison,GCGRU proposed in this paper is compared with classic methods.The evaluation metrics include MSE,RMSE,MAE.The experimental results show that GCGRU can perform better in traffic prediction.

Key words: Traffic prediction, Graph convolutional gated recurrent network, Spatial dependence, Temporal dependence, SDN

中图分类号:

TP393.02

宋元隆, 吕光宏, 王桂芝, 贾吾财. 基于图卷积神经网络的SDN网络流量预测[J]. 计算机科学, 2021, 48(6A): 392-397.

SONG Yuan-long, LYU Guang-hong, WANG Gui-zhi, JIA Wu-cai. SDN Traffic Prediction Based on Graph Convolutional Network[J]. Computer Science, 2021, 48(6A): 392-397.

参考文献

[1] KREUTZ D.Software-Defined Networking:A Comprehensive Survey[J].Proceedings of the IEEE,2015,103(1):14-76.
[2] CORTEZ P.Internet Traffic Forecasting using Neural Network[C]//IEEE International Joint Conference on Neural Network Proceedings.2006:2635-2642.
[3] FENG H,SHU Y.Study on network traffic prediction tech-niques[C]//International Conference on Wireless Communications,Networking and Mobile Computing.2005:1041-1044.
[4] DAI J,LI J.VBR MPEG Video Traffic Dynamic PredictionBased on the Modeling and Forecast of Time Series[C]//Fifth International Joint Conference on INC,IMS and IDC.2009:1752-1757.
[5] BARABAS M.Evaluation of network traffic predictionbased on neural networks with multi-task learning and multiresolution decomposition[C]//IEEE 7th International Conference on Intelligent Computer Communication and Processing.2011:95-102.
[6] KELLERER W,KALMBACH P,BLENK A,et al.Adaptable and Data-Driven Softwarized Networks:Review,Opportunities,and Challenges[J].Proceedings of the IEEE,2019,107(4):711-731.
[7] JIA Y,WU J,DU Y.Traffic speed prediction using deep learning method[C]//IEEE 19th International Conference on Intelligent Transportation Systems (ITSC).2016:1217-1222.
[8] LV Y S,DUAN Y J,KANG W W,et al.Traffic flow prediction with big data:a deep learning approach[J].IEEE Transactions on Intelligent Transportation Systems,2015,16(2):865-873.
[9] AZZOUNI A,PUJOLLE G.NeuTM:A neural network-based framework for traffic matrix prediction in SDN[C]//NOMS 2018-2018 IEEE/IFIP Network Operations and Management Symposium.2018:1-5.
[10] RAMAKRISHNAN N,SONI T.Network Traffic PredictionUsing Recurrent Neural Networks[C]//International Conference on Machine Learning and Applications.2018:187-193.
[11] LIU Z.Traffic Matrix Prediction Based onDeep Learning for Dynamic Traffic Engineering[C]//IEEE Symposium on Computers and Communications (ISCC).2019:1-7.
[12] XU B B,CEN K T,HUANG J J,et al.A survey of neural network of graph convolution [J].Chinese Journal of Computers,2020,43(5):755-780.
[13] WU Z,PAN S,CHEN F,et al.A Comprehensive Survey onGraph Neural Networks[J].IEEE Transactions on Neural Networks and Learning Systems,2021,32:4-24.
[14] SATO R.A Survey on The Expressive Power of Graph Neural Networks[J].arXiv:2003.04078,2020.
[15] KIPF T N,WELLING M.Semi-Supervised Classification withGraph Convolutional Networks[J].arXiv:1609.02907,2016.
[16] RUSEK K.RouteNet:Leveraging Graph Neural Networks for Network Modeling and Optimization in SDN[J].IEEE Journal on Selected Areas in Communications,2020,38(10):2260-2270.
[17] CUI Z,HENRICKSON K,KE R,et al.High-Order Graph Convolutional Recurrent Neural Network:A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting[J].arXiv:1802.07007.
[18] SHUMA N,DAVID I,NARAN G,et al.The Emerging Field of Signal Processing on Graphs[J].IEEE Signal Processing Magazine,2013,30(3):83-98.
[19] DEFFERRARD M,BRESSON X,VANDERGHEYNST P.Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering[J].arXiv:1606.09375.
[20] UHLIG S,QUOITIN B,LEPROPRE J,et al.Providing publicintradomain traffic matrices to the research community[J].Acm Sigcomm Computer Communication Review,2006,36(1):83-86.

相关文章 15

[1]	吕明琪, 洪照雄, 陈铁明. 一种融合时空关联与社会事件的交通流预测方法[J]. 计算机科学, 2021, 48(2): 264-270.
[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]	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.
[4]	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.
[5]	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.
[6]	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.
[7]	张彤,秦小麟. 时间依赖路网上的移动对象K近邻查询算法[J]. 计算机科学, 2020, 47(1): 79-86.
[8]	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.
[9]	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.
[10]	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.
[11]	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.
[12]	李佳佳, 沈盼盼, 夏秀峰, 刘向宇. 时间依赖路网中反向 k近邻查询[J]. 计算机科学, 2019, 46(1): 232-237.
[13]	赵卓峰,杨宗润. 基于残差修正GM(1,1)模型的车流量预测[J]. 计算机科学, 2017, 44(4): 96-99.
[14]	葛诗春,刘雄飞,周锋. CRH2型动车组列车信息传输网络流量建模与预测[J]. 计算机科学, 2017, 44(10): 91-95.
[15]	柳永波,刘乃安,李晓辉,冀琼. 基于流量预测的无线mesh网络负载均衡路由协议[J]. 计算机科学, 2017, 44(1): 109-112.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed