Application of Prophet Mixture Model on Long-Term Prediction of Base Station Cell Network Traffic

doi:10.3778/j.issn.1002-8331.2102-0111

Abstract

Abstract: Most of the traditional network traffic prediction methods focus on short-term, while long-term prediction can better guide the base station cell wireless equipment expansion and contraction. Ensemble empirical mode decomposition（EEMD） can convert the non-stationary time series into a stationary time series, and Prophet model can accurately make a more accurate long-term prediction of traffic series. Based on the advantages of the above model methods and the non-linear and non-stationary characteristics of the base station cell network traffic, Prophet hybrid EEMD method（E-Prophet） is proposed for base station cell network traffic prediction. First, the EEMD is adopted to decompose the network traffic series into several intrinsic mode functions（IMF） components and a residual component; then, the Prophet model is used to model each component, and the predictions of each component are linearly combined to obtain the final prediction result. The method is verified using real-world base station cell network traffic data, and the results show that E-Prophet model has higher accuracy and robustness in long-term prediction of network traffic compared with Prophet, SARIMA, LSTM, and the model combining EMD and Prophet.

Key words: network traffic prediction, ensemble empirical mode decomposition（EEMD）, Prophet model, time series prediction

摘要： 传统网络流量预测方法大多数关注短期预测，而长期预测能够更好地指导基站小区无线设备扩缩容。集合经验模态分解（ensemble empirical mode decomposition，EEMD）能够使非平稳时间序列转化成平稳时间序列，Prophet模型能够准确地对流量序列进行较准确的长期预测，基于以上模型方法的优点和基站小区网络流量的非线性和非平稳性特点，提出一种Prophet混合EEMD的基站小区网络流量预测方法（E-Prophet）。采用EEMD将网络流量序列分解成若干固有模态函数（intrinsic mode functions，IMF）分量和一个残差分量；利用Prophet模型对各分量建模，并将各分量预测结果进行线性组合，得到最终的预测结果。利用实际基站小区网络流量数据对方法进行验证，结果表明：E-Prophet对于网络流量长期预测比Prophet、SARIMA、LSTM以及结合EMD和Prophet的模型具有更高的准确度和鲁棒性。

关键词: 网络流量预测, 集合经验模态分解（EEMD）, Prophet模型, 时间序列预测

ZHANG Jiachen, ZUO Xingquan, HUANG Hai, HAN Jing, ZHANG Baisheng. Application of Prophet Mixture Model on Long-Term Prediction of Base Station Cell Network Traffic[J]. Computer Engineering and Applications, 2022, 58(14): 80-88.

张家晨, 左兴权, 黄海, 韩静, 张百胜. Prophet混合模型应用于基站网络流量长期预测[J]. 计算机工程与应用, 2022, 58(14): 80-88.

References

[1] SHAKEEL A，TANAKA T，KITAJO K.Time-series prediction of the oscillatory phase of EEG signals using the least mean square algorithm-based AR model[J].Applied Sciences，2020，10（10）：3616.
[2] AKAIKE H.A new look at the statistical model identification[J].IEEE Transactions on Automatic Control，1974，19（6）：716-723.
[3] BAKER R，CHOI B S.ARMA model identification[J].Journal of the Royal Statistical Society，1994，43（1）：206.
[4] BOX G E，JENKINS G M，REINSEL G C.Time series analysis：forecasting and control[M].[S.l.]：John Wiley & Sons，2011.
[5] LE L V，SINH D，LIN B S P，et al.Applying big data，machine learning，and SDN/NFV to 5G traffic clustering，forecasting，and management[C]//2018 4th IEEE Conference on Network Softwarization and Workshops（NetSoft），2018：168-176.
[6] CAO A，QIAO Y，SUN K，et al.Network traffic analysis and prediction of hotspot in cellular network[C]//2018 International Conference on Network Infrastructure and Digital Content（IC-NIDC），2018：452-456.
[7] WANG L，LI Z，SONG C.Network traffic prediction based on seasonal ARIMA model[C]//Proceedings of the World Congress on Intelligent Control and Automation（WCICA），2004：1425-1428.
[8] YAN H，OUYANG H.Financial time series prediction based on EEMD-RNN[J].Design Engineering，2020：394-405.
[9] RUMELHART D E，HINTON G E，WILLIAMS R J.Learning representations by back-propagating errors[J].Nature，1986，323：533-536.
[10] VAN OOYEN A，NIENHUIS B.Improving the convergence of the back-propagation algorithm[J].Neural Networks，1992，5（3）：465-471.
[11] CUI H，YAO Y，ZHANG K，et al.Network traffic prediction based on Hadoop[C]//International Symposium on Wireless Personal Multimedia Communications，2015：29-33.
[12] LI H.Network traffic prediction of the optimized BP neural network based on glowworm swarm algorithm[J].Systems Science and Control Engineering，2019，7（2）：64-70.
[13] 刘付斌，冯丽娜.基于EEMD与RBF神经网络的网络流量预测[J].计算机应用与软件，2014（6）：72-74.
LIU F B，FENG L N.Network traffic prediction based on EEMD and RBF neural networks[J].Computer Applications and Software，2014（6）：72-74.
[14] 高波，张钦宇，梁永生，等.基于EMD及ARMA的自相似网络流量预测[J].通信学报，2011，32（4）：47-56.
GAO B，ZHANG Q Y，LIANG Y S，et al.Predicting self-similar networking traffic based on EMD and ARMA[J].Journal of Communications，2011，32（4）：47-56.
[15] LU H，YANG F.A network traffic prediction model based on wavelet transformation and LSTM network[C]//2018 IEEE 9th International Conference on Software Engineering and Service Science，2018：1-4.
[16] WEI Y，WANG J，WANG C.Network traffic prediction based on wavelet transform and season ARIMA model[C]//Lecture Notes in Computer Science，2011.
[17] QIAN Y，XIA J，FU K，et al.Network traffic forecasting by support vector machines based on empirical mode decomposition denoising[J].Communications and Networks，2012：3327-3330.
[18] WANG P，LIU Y.Network traffic prediction based on improved BP wavelet neural network[C]//2008 4th International Conference on Wireless Communications，Networking and Mobile Computing，2008：1-5.
[19] TAYLOR S J，LETHAM B.Forecasting at scale[J].The American Statistician，2018，72（1）：37-45.
[20] BELKACEM S.COVID-19 Data analysis and forecasting：algeria and the world[J].arXiv：2007.09755，2020.
[21] CHMIELIAUSKAS D，GURSNYS D.LTE cell traffic grow and congestion forecasting[C]//2019 Open Conference of Electrical，Electronic and Information Sciences，2019：1-5.
[22] 龚志强，邹明玮，高新全，等.基于非线性时间序列分析经验模态分解和小波分解异同性的研究[J].物理学报，2005，54（8）：3947-3957.
GONG Z Q，ZOU M W，GAO X Q，et al.On the difference between empirical mode decomposition and wavelet decomposition in the nonlinear time series[J].Acta Physica Sinica，2005，54（8）：3947-3957.
[23] 刘杰，黄亚楼.基于BP神经网络的非线性网络流量预测[J].计算机应用，2007，27（7）：1770-1772.
LIU J，HUANG Y L.Nonlinear network traffic prediction based on BP neural network[J].Journal of Computer Applications，2007，27（7）：1770-1772.
[24] 程光，龚俭，丁伟.大规模网络流量行为累加分解研究[J].计算机工程与科学，2002，24（5）：53-56.
CHENG G，GONG J，DING W.Research on the accumulation decomposition of traffic behaviors in a large-scale network[J].Computer Engineering & Science，2002，24（5）：53-56.
[25] HUANG N E，SHEN Z，LONG S R，et al.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J].Proceedings of the Royal Society of London，Series A，1998，454（1971）：903-995.
[26] WANG Z Y，QIU J，LI F F.Hybrid models combining EMD/EEMD and ARIMA for long-term streamflow forecasting[J].Water，2018，10（7）：853.
[27] HOU H，ANDREWS H.Cubic splines for image interpolation and digital filtering[J].IEEE Transactions on Acoustics，Speech，and Signal Processing，1978，26（6）：508-517.
[28] HUANG N E，WU M L C，LONG S R，et al.A confidence limit for the empirical mode decomposition and Hilbert spectral analysis[J].Proceedings of the Royal Society of London，Series A：Mathematical，Physical and Engineering Sciences，2003，459（2037）：2317-2345.
[29] WU Z，HUANG N E.Ensemble empirical mode decomposition：a noise-assisted data analysis method[J].Advances in Adaptive Data Analysis，2009，1（1）：1-41.
[30] LEI Y，HE Z，ZI Y.Application of the EEMD method to rotor fault diagnosis of rotating machinery[J].Mechanical Systems & Signal Processing，2009，23（4）：1327-1338.
[31] VAN HOEY S，VAN DER KWAST J，NOPENS I，et al.Python package for model STructure ANalysis（pySTAN）[J].EGU General Assembly Conference Abstracts，2013，15：1-2.
[32] DALGKITSIS A，LOUTA M，KARETSOS G T.Traffic forecasting in cellular networks using the LSTM RNN[C]//Proceedings of the 22nd Pan-Hellenic Conference on Informatics，2018：28-33.
[33] 卢鹏飞，须成杰，张敬谊，等.基于SARIMA-LSTM的门诊量预测研究[J].大数据，2019，5（6）：101-110.
LU P F，XU C J，ZHANG J Y，et al.Research on the prediction of outpatient volume based on SARIMA-LSTM[J].Big Data Research，2019，5（6）：101-110.
[34] LASZUK D.Python implementation of empirical mode decomposition algorithm[Z].GitHub Repository，2017.