基于Prophet-DeepAR模型的Web流量预测

doi:10.16088/j.issn.1001-6600.2021071505

摘要/Abstract

摘要： 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: 时间序列, Web流量预测, Prophet模型, 深度学习, 自回归

Abstract: Web traffic prediction has always been a hot issue in data center networks, which is of great significance for improving the quality of network services. Due to the complex characteristics of web traffic such as non-linearity, autocorrelation, and periodicity, it is very challenging to accurately predict it. In order to fully mine the predictable information of web traffic and make the prediction model fully interpretable and configurable, this paper proposes a combined prediction model based on Prophet and deep autoregression (DeepAR). Among them, Prophet is an additive model based on time series decomposition, which models the trend, seasonal period, and holiday information of Web traffic. At the same time, the autoregressive information implied by the Prophet residual is modeled using the DeepAR model based on probability prediction, and the long-term and short-term dependencies are captured to reduce the variance of the Prophet residual and fully capture the autoregressive information of web traffic. In this paper, the verification experiments are carried out on the real Web traffic dataset, and the results show that the evaluation indicators of RMSE and MAE are better than the comparative models, which verifies the effectiveness of the combined model.

Key words: time series, web traffic forecasting, prophet model, deep learning, auto-regression

中图分类号:

TP393.06

闫龙川, 李妍, 宋浒, 邹昊东, 王丽君. 基于Prophet-DeepAR模型的Web流量预测[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 172-184.

YAN Longchuan, LI Yan, SONG Hu, ZOU Haodong, WANG Lijun. Web Traffic Prediction Based on Prophet-DeepAR[J]. Journal of Guangxi Normal University(Natural Science Edition), 2022, 40(3): 172-184.

参考文献

[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.

相关文章 15

[1]	张萍, 徐巧枝. 基于多感受野与分组混合注意力机制的肺结节分割研究[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 76-87.
[2]	李永杰, 周桂红, 刘博. 基于YOLOv3模型的人脸检测与头部姿态估计融合算法[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 95-103.
[3]	吴军, 欧阳艾嘉, 张琳. 基于多头注意力机制的磷酸化位点预测模型[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 161-171.
[4]	梁鑫, 陈小玲, 张兴发, 李元. 一类带有GARCH类误差项的自回归滑动平均模型[J]. 广西师范大学学报（自然科学版）, 2022, 40(1): 195-205.
[5]	路凯峰, 杨溢龙, 李智. 一种基于BERT和DPCNN的Web服务分类方法[J]. 广西师范大学学报（自然科学版）, 2021, 39(6): 87-98.
[6]	吴玲玉, 蓝洋, 夏海英. 基于卷积神经网络的眼底图像配准研究[J]. 广西师范大学学报（自然科学版）, 2021, 39(5): 122-133.
[7]	陈文康, 陆声链, 刘冰浩, 李帼, 刘晓宇, 陈明. 基于改进YOLOv4的果园柑橘检测方法研究[J]. 广西师范大学学报（自然科学版）, 2021, 39(5): 134-146.
[8]	杨州, 范意兴, 朱小飞, 郭嘉丰, 王越. 神经信息检索模型建模因素综述[J]. 广西师范大学学报（自然科学版）, 2021, 39(2): 1-12.
[9]	邓文轩, 杨航, 靳婷. 基于注意力机制的图像分类降维方法[J]. 广西师范大学学报（自然科学版）, 2021, 39(2): 32-40.
[10]	薛涛, 丘森辉, 陆豪, 秦兴盛. 基于经验模态分解和多分支LSTM网络汇率预测[J]. 广西师范大学学报（自然科学版）, 2021, 39(2): 41-50.
[11]	唐熔钗, 伍锡如. 基于改进YOLO-V3网络的百香果实时检测[J]. 广西师范大学学报（自然科学版）, 2020, 38(6): 32-39.
[12]	张明宇, 赵猛, 蔡夫鸿, 梁钰, 王鑫红. 基于深度学习的波浪能发电功率预测[J]. 广西师范大学学报（自然科学版）, 2020, 38(3): 25-32.
[13]	李维勇, 柳斌, 张伟, 陈云芳. 一种基于深度学习的中文生成式自动摘要方法[J]. 广西师范大学学报（自然科学版）, 2020, 38(2): 51-63.
[14]	刘英璇, 伍锡如, 雪刚刚. 基于深度学习的道路交通标志多目标实时检测[J]. 广西师范大学学报（自然科学版）, 2020, 38(2): 96-106.
[15]	张金磊, 罗玉玲, 付强. 基于门控循环单元神经网络的金融时间序列预测[J]. 广西师范大学学报（自然科学版）, 2019, 37(2): 82-89.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed