基于循环神经网络的95598小尺度网络流量预测
|
摘要
为了准确预测短时间内的网络流量波动,提高95598客服热线网络流量监测性能,文章基于循环神经网络的GRU模型与后向传播神经网络,输入多种流量相关的影响因素,综合构建小尺度网络流量预测的深层网络模型。实验结果表明,与传统浅层神经网络预测模型和深层网络LSTM预测模型相比,文章所提的方法不但在短期流量预测取得更高的准确率,也在较长时序的流量预测上获得更好结果。
In order to accurately predict the fluctuation of network traffic in a short period of time and improve the monitoring performance of 95598 customer service hotline network traffic,considering multi-scale related traffic features, this paper proposes a small-scale network traffic prediction model based on RNN deep network model and BP neural network. The experimental results show that the proposed model achieves better prediction performance not only in short-term network traffic but also in long term traffic prediction than that of traditional neural networks.
In order to accurately predict the fluctuation of network traffic in a short period of time and improve the monitoring performance of 95598 customer service hotline network traffic,considering multi-scale related traffic features, this paper proposes a small-scale network traffic prediction model based on RNN deep network model and BP neural network. The experimental results show that the proposed model achieves better prediction performance not only in short-term network traffic but also in long term traffic prediction than that of traditional neural networks.
引文
[1]唐舟进,彭涛,王文博.一种基于相关分析的局域最小二乘支持向量机小尺度网络流量预测算法[J].物理学报,2014,63(13):130504-1-10.TANG Zhoujin,PENG Tao,WANG Wenbo.A local least square support vector machine prediction algorithm of small scale network traffic based on correlation analysis[J].Acta Physica Sinica,2014,63(13):130504-1-10.
[2]陈颖,魏臻,程磊.基于AVMD-DE和IBSA-KELM的混沌网络流量组合预测[J].计算机应用与软件,2018,35(6):117-121.C H E N Yi n g,W E I Z h e n,C H E N G L e i.C o m b i n a t o r i a l predictionofchaotic network traffic based on AVMD-DE and IBSA-KELM[J].Computer Applications and Software,2018,35(6):117-121.
[3]刘蕴,焦妍,王华东.改进极限学习机的网络流量混沌预测[J].南京理工大学学报,2017,41(4):454-459.LIU Yun,JIAO Yan,WANG Huadong.Chaotic prediction of network traffic based onimproved extreme learning machine[J].Journal of Nanjing University of Science and Technology,2017,41(4):454-459.
[4]张洋,吴斌,张继革,等.基于组合模型的网络流量预测[J].华中科技大学学报(自然科学版),2016,44(S1):29-34.ZHANG Yang,WU Bin,ZHANG Jige,et al.Network traffic forecasting based on combined mode[J].Journal of Huazhong University of Science and Technology(Nature Science Edition),2016,44(S1):29-34.
[5]赵建龙,曲桦,赵季红,等.基于Morlet-SVR和ARIMA组合模型的网络流量预测[J].北京邮电大学学报,2016,39(2):53-57.ZHAO Jianlong,QU Hua,ZHAO Jihong,et al.A comprehensive forecasting model for network traffic based on Morlet-SVR and ARIMA[J].Journal of Beijing University of Posts and Telecommunications,2016,39(2):53-57.
[6]陆明燕,田素诚.大规模网络线路数据流量并行预测方法仿真[J].计算机仿真,2018,35(8):206-209.LU Mingyan,TIAN Sucheng.Large scale network data flow parallel forecasting method simulation[J].Computer Simulation,2018,35(8):206-209.
[7]陈石东,陈向群,黄瑞,等.基于混合流量模型的用电信息采集业务带宽预测方法[J].电力信息与通信技术,2018,16(9):39-44.CHEN Shidong,CHEN Xiangqun,HUANG Rui,et al.Bandwidth prediction method for power consumption information collecting service based on mixed-flow model[J].Electric Power Information and Communication Technology,2018,16(9):39-44.
[8]竹瑞博,安毅,巫健.基于深度学习的电力业务通信带宽需求预测方法[J].电力信息与通信技术,2017,15(9):26-31.ZHU Ruibo,AN Yi,WU Jian.Bandwidth prediction for business requirement of electric power communication network with deep learning[J].Electric Power Information and Communication Technology,2017,15(9):26-31.
[9]王旭强,陈艳龙,杨青,等.基于时序分解的用电负荷分析与预测[J].计算机工程与应用,2018,54(20):230-236.WANG Xuqiang,CHEN Yanlong,YANG Qing,et al.Analysis and prediction of user electricity consumption based on time series decomposition[J].Computer Engineering and Applications,2018,54(20):230-236.
[10]黄晓辉,李京.基于循环神经网络的藏语语音识别声学模型[J].中文信息学报,2018,32(5):49-55.HUANG Xiaohui,LI Jing.The acoustic model for tibetanspeech recognition based on recurrent neural network[J].Journal of Chinese Information Processing,2018,32(5):49-55.
[11]石磊,杜军平,梁美玉.基于RNN和主题模型的社交网络突发话题发现[J].通信学报,2018,39(4):189-198.SHI Lei,DU Junping,LIANG Meiyu.Social network bursty topic discovery based on RNN and topic model[J].Journal on Communications,2018,39(4):189-198.
[12]李鹏,何帅,韩鹏飞,等.基于长短期记忆的实时电价条件下智能电网短期负荷预测[J].电网技术,2018,42(12):4045-4052.LI Peng,HE Shuai,HAN Pengfei,et al.Short term load forecasting of smart grid based on long short term memory recurrent neural networks in condition of real-time electricity price[J].Power System Technology,2018,42(12):4045-4052.
[13]刘明宇,吴建平,王钰博,等.基于深度学习的交通流量预测[J].系统仿真学报,2018,30(11):4100-4105,4114.LIU Mingyu,WU Jianping,WANG Yubo,et al.Traffic flow prediction based on deep learning[J].Journal of System Simulation,2018,30(11):4100-4105,4114.
[14]哈里旦木·阿布都克里木,程勇,刘洋,等.基于双向门限递归单元神经网络的维吾尔语形态切分[J].清华大学学报(自然科学版),2017,57(1):1-6.ABUDUKELIMU Halidanmu,CHENG Yong,LIU Yang,et al.Uyghur morphological segmentation with bidirectional GRUneural network[J].Journal of Tsinghua University(Science and Technology),2017,57(1):1-6.
[15]朱军,张珊珊.95598电话量高峰分析及应对措施[J].电力需求侧管理,2013,15(1):56-57.ZHU Jun,ZHANG Shanshan.95598 summer peaks typical peak call volume and response measures[J].Power Demand Side Management,2013,15(1):56-57.
[16]马超,刘亚淑,骆功宁,等.基于级联随机森林与活动轮廓的3DMR图像分割[J/OL].自动化学报:1-11[2018-10-11].https://doi.org/10.16383/j.aas.c170520.MA Chao,LIU Yashu,LUO Gongning,et al.Combining concatenated random forests and active contour for the 3D MRimages segmentation[J].Acta Automatica Sinica:1-11[2018-10-11].https://doi.org/10.16383/j.aas.c170520.
[17]霍娟,孙晓伟,张明杰.电力负荷预测算法比较-随机森林与支持向量机[J/OL].电力系统及其自动化学报:1-8[2018-09-21].https://doi.org/10.19635/j.cnki.csu-epsa.000093.HUO Juan,SUN Xiaowei,ZHANG Mingjie.Comparison of typical algorithms for load forecasting-random forest and support vector machine[J].Proceedings of the CSU-EPSA:1-8[2018-09-21].https://doi.org/10.19635/j.cnki.csu-epsa.000093.
[2]陈颖,魏臻,程磊.基于AVMD-DE和IBSA-KELM的混沌网络流量组合预测[J].计算机应用与软件,2018,35(6):117-121.C H E N Yi n g,W E I Z h e n,C H E N G L e i.C o m b i n a t o r i a l predictionofchaotic network traffic based on AVMD-DE and IBSA-KELM[J].Computer Applications and Software,2018,35(6):117-121.
[3]刘蕴,焦妍,王华东.改进极限学习机的网络流量混沌预测[J].南京理工大学学报,2017,41(4):454-459.LIU Yun,JIAO Yan,WANG Huadong.Chaotic prediction of network traffic based onimproved extreme learning machine[J].Journal of Nanjing University of Science and Technology,2017,41(4):454-459.
[4]张洋,吴斌,张继革,等.基于组合模型的网络流量预测[J].华中科技大学学报(自然科学版),2016,44(S1):29-34.ZHANG Yang,WU Bin,ZHANG Jige,et al.Network traffic forecasting based on combined mode[J].Journal of Huazhong University of Science and Technology(Nature Science Edition),2016,44(S1):29-34.
[5]赵建龙,曲桦,赵季红,等.基于Morlet-SVR和ARIMA组合模型的网络流量预测[J].北京邮电大学学报,2016,39(2):53-57.ZHAO Jianlong,QU Hua,ZHAO Jihong,et al.A comprehensive forecasting model for network traffic based on Morlet-SVR and ARIMA[J].Journal of Beijing University of Posts and Telecommunications,2016,39(2):53-57.
[6]陆明燕,田素诚.大规模网络线路数据流量并行预测方法仿真[J].计算机仿真,2018,35(8):206-209.LU Mingyan,TIAN Sucheng.Large scale network data flow parallel forecasting method simulation[J].Computer Simulation,2018,35(8):206-209.
[7]陈石东,陈向群,黄瑞,等.基于混合流量模型的用电信息采集业务带宽预测方法[J].电力信息与通信技术,2018,16(9):39-44.CHEN Shidong,CHEN Xiangqun,HUANG Rui,et al.Bandwidth prediction method for power consumption information collecting service based on mixed-flow model[J].Electric Power Information and Communication Technology,2018,16(9):39-44.
[8]竹瑞博,安毅,巫健.基于深度学习的电力业务通信带宽需求预测方法[J].电力信息与通信技术,2017,15(9):26-31.ZHU Ruibo,AN Yi,WU Jian.Bandwidth prediction for business requirement of electric power communication network with deep learning[J].Electric Power Information and Communication Technology,2017,15(9):26-31.
[9]王旭强,陈艳龙,杨青,等.基于时序分解的用电负荷分析与预测[J].计算机工程与应用,2018,54(20):230-236.WANG Xuqiang,CHEN Yanlong,YANG Qing,et al.Analysis and prediction of user electricity consumption based on time series decomposition[J].Computer Engineering and Applications,2018,54(20):230-236.
[10]黄晓辉,李京.基于循环神经网络的藏语语音识别声学模型[J].中文信息学报,2018,32(5):49-55.HUANG Xiaohui,LI Jing.The acoustic model for tibetanspeech recognition based on recurrent neural network[J].Journal of Chinese Information Processing,2018,32(5):49-55.
[11]石磊,杜军平,梁美玉.基于RNN和主题模型的社交网络突发话题发现[J].通信学报,2018,39(4):189-198.SHI Lei,DU Junping,LIANG Meiyu.Social network bursty topic discovery based on RNN and topic model[J].Journal on Communications,2018,39(4):189-198.
[12]李鹏,何帅,韩鹏飞,等.基于长短期记忆的实时电价条件下智能电网短期负荷预测[J].电网技术,2018,42(12):4045-4052.LI Peng,HE Shuai,HAN Pengfei,et al.Short term load forecasting of smart grid based on long short term memory recurrent neural networks in condition of real-time electricity price[J].Power System Technology,2018,42(12):4045-4052.
[13]刘明宇,吴建平,王钰博,等.基于深度学习的交通流量预测[J].系统仿真学报,2018,30(11):4100-4105,4114.LIU Mingyu,WU Jianping,WANG Yubo,et al.Traffic flow prediction based on deep learning[J].Journal of System Simulation,2018,30(11):4100-4105,4114.
[14]哈里旦木·阿布都克里木,程勇,刘洋,等.基于双向门限递归单元神经网络的维吾尔语形态切分[J].清华大学学报(自然科学版),2017,57(1):1-6.ABUDUKELIMU Halidanmu,CHENG Yong,LIU Yang,et al.Uyghur morphological segmentation with bidirectional GRUneural network[J].Journal of Tsinghua University(Science and Technology),2017,57(1):1-6.
[15]朱军,张珊珊.95598电话量高峰分析及应对措施[J].电力需求侧管理,2013,15(1):56-57.ZHU Jun,ZHANG Shanshan.95598 summer peaks typical peak call volume and response measures[J].Power Demand Side Management,2013,15(1):56-57.
[16]马超,刘亚淑,骆功宁,等.基于级联随机森林与活动轮廓的3DMR图像分割[J/OL].自动化学报:1-11[2018-10-11].https://doi.org/10.16383/j.aas.c170520.MA Chao,LIU Yashu,LUO Gongning,et al.Combining concatenated random forests and active contour for the 3D MRimages segmentation[J].Acta Automatica Sinica:1-11[2018-10-11].https://doi.org/10.16383/j.aas.c170520.
[17]霍娟,孙晓伟,张明杰.电力负荷预测算法比较-随机森林与支持向量机[J/OL].电力系统及其自动化学报:1-8[2018-09-21].https://doi.org/10.19635/j.cnki.csu-epsa.000093.HUO Juan,SUN Xiaowei,ZHANG Mingjie.Comparison of typical algorithms for load forecasting-random forest and support vector machine[J].Proceedings of the CSU-EPSA:1-8[2018-09-21].https://doi.org/10.19635/j.cnki.csu-epsa.000093.