闫龙川;李妍;宋浒;邹昊东;王丽君;

• 1:国家电网有限公司信息通信分公司
• 2:国网江苏省电力有限公司信息通信分公司
• 3:国网电力科学研究院有限公司

摘要(Abstract)：

Web流量预测一直是数据中心网络的热点问题，对于提高网络服务质量具有重要意义。由于Web流量具有非线性、自相关性和周期性等复杂特点，对其准确预测有很大的挑战性。为充分挖掘出Web流量的可预测信息，同时使预测模型具有充分的可解释性和可配置性，本文提出一种基于Prophet和深度自回归(DeepAR)的组合预测模型。其中，Prophet是基于时序分解的加性模型，对Web流量的趋势、季节性周期、节假日信息进行建模。同时，使用基于概率预测的DeepAR模型对Prophet残差隐含的自回归信息建模，捕获长短期依赖关系，以减低Prophet残差的方差，并充分捕获Web流量的自回归信息。在真实的Web流量数据集上进行验证实验，结果表明在RMSE和MAE两项评价指标上均优于对比模型，验证了该组合模型的有效性。

关键词(KeyWords)： 时间序列;Web流量预测;Prophet模型;深度学习;自回归

Abstract:

Keywords:

基金项目(Foundation): 国家电网有限公司科技项目(5700-202018194A-0-0-00);; 国家自然科学基金(61972118)

作者(Authors): 闫龙川;李妍;宋浒;邹昊东;王丽君;

DOI: 10.16088/j.issn.1001-6600.2021071505

参考文献(References)：

• [1] 中国互联网络信息中心.第47次中国互联网络发展状况统计报告[R].北京：中国互联网络信息中心，2021.
• [2] GUO Z G,ZHANG Y F,LV J X,et al.An online learning collaborative method for traffic forecasting and routing optimization[J].IEEE Transactions on Intelligent Transportation Systems,2021,22(10):6634-6645.DOI:10.1109/TITS.2020.2986158.
• [3] ALAWE I,KSENTINI A,HADJADJ-AOUL Y,et al.Improving traffic forecasting for 5G core network scalability:a machine learning approach[J].IEEE Network,2018,32(6):42-49.DOI:10.1109/MNET.2018.1800104.
• [4] 黎嘉诚.基于小波神经网络的校园网络流量预测研究[D].南昌：南昌大学，2019.
• [5] BOX G E P,JENKINS G M,REINSEL G C,et al.Time series analysis:forecasting and control[M].Hoboken:John Wiley & Sons,2016.
• [6] HONG W C.Application of seasonal SVR with chaotic immune algorithm in traffic flow forecasting[J].Neural Computing and Applications,2012,21(3):583-593.DOI:10.1007/s00521-010-0456-7.
• [7] TROIA S,ALVIZU R,ZHOU Y D,et al.Deep learning-based traffic prediction for network optimization[C]// 2018 20th International Conference on Transparent Optical Networks(ICTON).Piscataway,NJ:IEEE,2018:1-4.DOI:10.1109/ICTON.2018.8473978.
• [8] ANDREOLETTI D,TROIA S,MUSUMECI F,et al.Network traffic prediction based on diffusion convolutional recurrent neural networks[C]∥ IEEE INFOCOM 2019-IEEE Conference on Computer Communications Workshops(INFOCOM WKSHPS).Piscataway,NJ:IEEE,2019:246-251.DOI:10.1109/INFCOMW.2019.8845132.
• [9] ROUGHAN M,ZHANG Y,WILLINGER W,et al.Spatio-temporal compressive sensing and internet traffic matrices(extended version)[J].IEEE/ACM Transactions on Networking,2012,20(3):662-676.DOI:10.1109/TNET.2011.2169424.
• [10] XU Y,XU W J,YIN F,et al.High-accuracy wireless traffic prediction:a GP-based machine learning approach[C]// GLOBECOM 2017-2017 IEEE Global Communications Conference.Piscataway,NJ:IEEE,2017:1-6.DOI:10.1109/GLOCOM.2017.8254808.
• [11] WANG J,TANG J,XU Z Y,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.Piscataway,NJ:IEEE,2017:1-9.DOI:10.1109/INFOCOM.2017.8057090.
• [12] HUA Y X,ZHAO Z F,LI R P,et al.Deep learning with long short-term memory for time series prediction[J].IEEE Communications Magazine,2019,57(6):114-119.DOI:10.1109/MCOM.2019.1800155.
• [13] 谢贵才，段磊，蒋为鹏，等.多尺度时序依赖的校园公共区域人流量预测[J].软件学报，2021,32(3):831-844.DOI:10.13328/j.cnki.jos.006183.
• [14] 冯宁，郭晟楠，宋超，等.面向交通流量预测的多组件时空图卷积网络[J].软件学报，2019,30(3):759-769.DOI:10.13328/j.cnki.jos.005697.
• [15] 张建晋，王韫博，龙明盛，等.面向季节性时空数据的预测式循环网络及其在城市计算中的应用[J].计算机学报，2020,43(2):286-302.
• [16] PENG K,MENZIES T.Documenting evidence of a reuse of ‘“why should I trust you?”:explaining the predictions of any classifier’[C]// Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering.New York:ACM,2016:1135-1144.DOI:10.1145/3468264.3477217.
• [17] LUNDBERG S M,LEE S I.A unified approach to interpreting model predictions[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems.New York:ACM,2017:4768-4777.
• [18] 葛娜，孙连英，石晓达，等.Prophet-LSTM组合模型的销售量预测研究[J].计算机科学，2019,46(S1):446-451.
• [19] CHEN T T,LEE S J.A weighted LS-SVM based learning system for time series forecasting[J].Information Sciences,2015,299:99-116.DOI:10.1016/j.ins.2014.12.031.
• [20] WANG L,ZENG Y,CHEN T.Back propagation neural network with adaptive differential evolution algorithm for time series forecasting[J].Expert Systems with Applications,2015,42(2):855-863.DOI:10.1016/j.eswa.2014.08.018.
• [21] QIU X H,REN Y,SUGANTHANP N,et al.Empirical mode decomposition based ensemble deep learning for load demand time series forecasting[J].Applied Soft Computing,2017,54:246-255.DOI:10.1016/j.asoc.2017.01.015.
• [22] SALINAS D,FLUNKERT V,GASTHAUS J,et al.DeepAR:probabilistic forecasting with autoregressive recurrent networks[J].International Journal of Forecasting,2020,36(3):1181-1191.DOI:10.1016/j.ijforecast.2019.07.001.
• [23] TAYLOR S J,LETHAM B.Forecasting at scale[J].The American Statistician,2018,72(1):37-45.DOI:10.7287/peerj.preprints.3190v2.
• [24] 杨新宇，杨树森，李娟.基于非线性预处理网络流量预测方法的泛洪型DDoS攻击检测算法[J].计算机学报，2011,34(2):395-405.