基于FARIMA的铁路数据网流量趋势预测
|
摘要
利用FARIMA模型,对铁路数据网中的真实数据流量进行建模并分析,提出一种新型的基于FARIMA模型的铁路数据网流量预测方法,该方法能够同时描述网络流量的长相关特性和短相关特性。将FARIMA过程转换为差分过程和ARMA过程进行趋势预测,并且根据平均绝对误差、绝对百分比误差等多项指标进行比较验证。通过对高速铁路数据网6个月的数据进行建模分析,利用不同的参数设置预测未来2个月的流量趋势,并与真实数据进行对比。实验结果表明该方法比传统的基于ARMA模型的预测方法更为精准,能够适用于铁路数据网流量趋势预测。
This paper analyzed and modelled the actual traffic data of railway data network by analyzing the principle of FARIMA model,and proposed a new traffic forecasting method based on FARIMA.The method can describe the long-range dependence and short-range dependence characteristics of network traffic simultaneously.The FARIMA process was transformed into differential process and ARMA process to forecast tendency.The fitting results were verified with the average absolute error and the mean absolute percentage error.By modeling and analyzing the six-month data in the high-speed railway data network,forecasting the traffic trend in the next 2 months by different parameter settings,and comparing with the real data,the experiment shows that the method is more accurate than the traditional prediction method based on ARMA model,and is absolutely applicable to railway data network traffic trend forecast.
This paper analyzed and modelled the actual traffic data of railway data network by analyzing the principle of FARIMA model,and proposed a new traffic forecasting method based on FARIMA.The method can describe the long-range dependence and short-range dependence characteristics of network traffic simultaneously.The FARIMA process was transformed into differential process and ARMA process to forecast tendency.The fitting results were verified with the average absolute error and the mean absolute percentage error.By modeling and analyzing the six-month data in the high-speed railway data network,forecasting the traffic trend in the next 2 months by different parameter settings,and comparing with the real data,the experiment shows that the method is more accurate than the traditional prediction method based on ARMA model,and is absolutely applicable to railway data network traffic trend forecast.
引文
[1]陈建.网络业务自相似特性及其对排队性能影响的研究[D].成都:西南交通大学,2006.
[2]林青,戴慧珺.基于MWSVR和ARMA混合模型的流量预测[J].计算机工程,2015,41(12):130-134.LIN Qing,DAI Huijun.Flow Prediction Based on Hybrid Model of MWSVR and ARMA[J].Computer Engineering,2015,41(12):130-134.
[3]徐志强,陈剑,陆俊.自相似混合业务流的网络性能研究[J].通信技术,2012(6):117-120.XU Zhiqiang,CHEN Jian,LU Jun.Analysis on Network Performances Based on Self-similarity Hybrid Traffic Flow[J].Communications Technology,2012(6):117-120.
[4]SONG Y,TU X,FEI M.Internet Time-delay Prediction Based on FARIMA Model[J].Chinese Journal of Scientific Instrument,2012,33(4):757-763.
[5]史明虎.基于FARIMA模型的自相似业务流量预测[D].西安:西安电子科技大学,2013.
[6]李士宁,闫焱,覃征.基于FARIMA模型的网络流量预测[J].计算机工程与应用,2006,42(29):148-150.LI Shining,YAN Yan,QIN Zheng.Network Traffic Forecast Based on FARIMA Model[J].Computer Engineering and Applications,2006,42(29):148-150.
[7]SHU Y,FENG H,WANG H,et al.FARIMA Model Based Admission Control to Support QoS Service in the Networks with WiFi Access[C]//The Second International Conference on Mobile Technology,Applications and Systems,2005:90.
[8]BERAN J,FENG Y,GHOSH S.Modelling Long-range Dependence and Trends in Duration Series:an Approach Based on EFARIMA and ESEMIFAR Models[J].Statistical Papers,2015,56(2):431-451.
[9]邹柏贤,刘强.基于ARMA模型的网络流量预测[J].计算机研究与发展,2002,39(12):1645-1652.ZOU Boxian,LIU Qiang.ARMA-based Traffic Prediction and Overload Detection of Network[J].Journal of Computer Research and Development,2002,39(12):1645-1652.
[10]郑坚坚.随机过程[M].合肥:中国科学技术大学出版社,2016.
[11]田垅,刘宗田.最小二乘法分段直线拟合[J].计算机科学,2012,39(S1):482-484.TIAN Long,LIU Zongtian.Least-squares Method Piecewise Linear Fitting[J].Computer Science,2012,39(S1):482-484.
[12]SADEK N,KHOTANZAD A,CHEN T.ATM Dynamic Bandwidth Allocation Using F-ARIMA Prediction Model[C]//The International Conference on Computer Communications and Networks.New York:IEEE,2003:359-363.
[13]邓自立.最优估计理论及其应用:建模、滤波、信息融合估计[M].哈尔滨:哈尔滨工业大学出版社,2005.
[2]林青,戴慧珺.基于MWSVR和ARMA混合模型的流量预测[J].计算机工程,2015,41(12):130-134.LIN Qing,DAI Huijun.Flow Prediction Based on Hybrid Model of MWSVR and ARMA[J].Computer Engineering,2015,41(12):130-134.
[3]徐志强,陈剑,陆俊.自相似混合业务流的网络性能研究[J].通信技术,2012(6):117-120.XU Zhiqiang,CHEN Jian,LU Jun.Analysis on Network Performances Based on Self-similarity Hybrid Traffic Flow[J].Communications Technology,2012(6):117-120.
[4]SONG Y,TU X,FEI M.Internet Time-delay Prediction Based on FARIMA Model[J].Chinese Journal of Scientific Instrument,2012,33(4):757-763.
[5]史明虎.基于FARIMA模型的自相似业务流量预测[D].西安:西安电子科技大学,2013.
[6]李士宁,闫焱,覃征.基于FARIMA模型的网络流量预测[J].计算机工程与应用,2006,42(29):148-150.LI Shining,YAN Yan,QIN Zheng.Network Traffic Forecast Based on FARIMA Model[J].Computer Engineering and Applications,2006,42(29):148-150.
[7]SHU Y,FENG H,WANG H,et al.FARIMA Model Based Admission Control to Support QoS Service in the Networks with WiFi Access[C]//The Second International Conference on Mobile Technology,Applications and Systems,2005:90.
[8]BERAN J,FENG Y,GHOSH S.Modelling Long-range Dependence and Trends in Duration Series:an Approach Based on EFARIMA and ESEMIFAR Models[J].Statistical Papers,2015,56(2):431-451.
[9]邹柏贤,刘强.基于ARMA模型的网络流量预测[J].计算机研究与发展,2002,39(12):1645-1652.ZOU Boxian,LIU Qiang.ARMA-based Traffic Prediction and Overload Detection of Network[J].Journal of Computer Research and Development,2002,39(12):1645-1652.
[10]郑坚坚.随机过程[M].合肥:中国科学技术大学出版社,2016.
[11]田垅,刘宗田.最小二乘法分段直线拟合[J].计算机科学,2012,39(S1):482-484.TIAN Long,LIU Zongtian.Least-squares Method Piecewise Linear Fitting[J].Computer Science,2012,39(S1):482-484.
[12]SADEK N,KHOTANZAD A,CHEN T.ATM Dynamic Bandwidth Allocation Using F-ARIMA Prediction Model[C]//The International Conference on Computer Communications and Networks.New York:IEEE,2003:359-363.
[13]邓自立.最优估计理论及其应用:建模、滤波、信息融合估计[M].哈尔滨:哈尔滨工业大学出版社,2005.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |