A Network Traffic Prediction Method Based on LSTM

doi:10.12142/ZTECOM.201902004

ZTE Communications ›› 2019, Vol. 17 ›› Issue (2): 19-25.DOI: 10.12142/ZTECOM.201902004

• Special Topic • Previous Articles Next Articles

A Network Traffic Prediction Method Based on LSTM

WANG Shihao, ZHUO Qinzheng, YAN Han, LI Qianmu, QI Yong

School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu 210094, China

Received:2018-02-13 Online:2019-06-11 Published:2019-11-14
About author:WANG Shihao is a postgraduate student of Nanjing University of Science and Technology, China. He received the bachelor's degree from Nanjing Institute of Technology, China in 2017. His research interests include network traffic prediction and network intrusion detection|ZHUO Qinzheng was a postgraduate student of Nanjing University of Science and Technology, China. He received the bachelor's and master's degree from Nanjing University of Information Science and Technology, China in 2015 and 2018. His research interests include network traffic prediction, data mining, and deep learning|YAN Han received the Ph.D. degree from Nanjing University of Information Science and Technology in 2000. He is an associate professor with Nanjing University of Science and Technology, China. His research interests include software modeling, web computation, information security, and agile software development, and his current focus is on computing system management. He received the second class prizes for national defense science and technology. More than 40 academic papers have been published|LI Qianmu (liqianmu@126.com) received the B.Sc. and Ph.D. degrees from Nanjing University of Science and Technology, China in 2001 and 2005, respectively. He is a professor with the School of Computer Science and Engineering, Nanjing University of Science and Technology, China. He is also a Ph.D. supervisor and the director of Department of Software Engineering. His research interests include information security, computing system management, and data mining. He received the China Network and Information Security Outstanding Talent Award and multiple Education Ministry Science and Technology Awards. More than 120 high-level papers have been published and more than 150 patents have been applied and authorized|QI Yong is a Ph.D. supervisor and professor with Nanjing University of Science and Technology, China. He is also the director of Jiangsu Intelligent Transportation Information Perception and Data Analysis Engineering Laboratory. His main research interests include data mining and intelligent transportation systems. He received more than 10 scientific awards, such as China University Research Cooperation Innovation Award, the Ministry of Educations Scientific and Technological Progress Award, and the Jiangsu Science and Technology Award. More than 100 academic papers have been published, and more than 60 patents for inventions and applications have been granted
Supported by:
This paper supported by ZTE Industry-Academia-Research Cooperation Funds under Grant No(2016ZTE04-11);National Key Research and Development Program: Key Projects of International Scientific and Technological Innovation Cooperation Between Governments under Grant No(2016YFE0108000);Fundamental Research Funds for the Central Universities under Grant(30918012204);Jiangsu Province Key Research and Development Program under Grant(BE2017739)

Abstract

Abstract:

As the network sizes continue to increase, network traffic grows exponentially. In this situation, how to accurately predict network traffic to serve customers better has become one of the issues that Internet service providers care most about. Current traditional network models cannot predict network traffic that behaves as a nonlinear system. In this paper, a long short-term memory (LSTM) neural network model is proposed to predict network traffic that behaves as a nonlinear system. According to characteristics of autocorrelation, an autocorrelation coefficient is added to the model to improve the accuracy of the prediction model. Several experiments were conducted using real-world data, showing the effectiveness of LSTM model and the improved accuracy with autocorrelation considered. The experimental results show that the proposed model is efficient and suitable for real-world network traffic prediction.

Key words: recurrent neural networks, time series, network traffic prediction

WANG Shihao, ZHUO Qinzheng, YAN Han, LI Qianmu, QI Yong. A Network Traffic Prediction Method Based on LSTM[J]. ZTE Communications, 2019, 17(2): 19-25.

Figures/Tables 12

Figure 1. The recurrent neural networks structure diagram.

Figure 2. LSTM structural diagram of neural network model.

Figure 3. Neural network structure of LSTM and DNN.

Figure 4. Aurocorrelation analysis.

Table 1 Echo status network parameters.

Parameter	Value
In size	1
Reservoir size	1β000
Leaking rate	0.3
Spectral radius	0.136
Linear regression algorithm	Ridge regression

Table 2 LSTM neural network parameters.

Parameter	Value
Dropout fraction	10%
Time steps	10
RNN units	200
RNN layers	1
Dense units	[10,10]
Batch size	10

Table 3 Average absolute percentage error analysis.

Date	Time granularity	ESN	LSTM	LSTM and DNN
Date set A	5 min	2.81%	1.41%	1.39%
Date set A	1 h	7.63%	4.69%	4.51%
Data set B	5 min	3.50%	3.29%	1.32%
Data set B	1 h	5.04%	4.47%	2.80%
Data set C	5 min	4.41%	12.04%
Data set C	1 h	0.59%	14.00%

Figure 5. Comparison of performance of loss function under different data sets and training iterations.

Figure 6. Prediction effect of the data set A with 1-hour time granularity.

Figure 7. Prediction effect of the data set A with 5-minute time granularity.

Figure 8. Prediction effect of the data set B with 1-hour time granularity.

Figure 9. Prediction effect of the data set B with 5-minute time granularity.

References 19

[1]	BABIARZ R, BEDO J . Internet Traffic Midterm Forecasting: a Pragmatic Approach Using Statistical Analysis Tools[M] //BOAVIDA F, PLAGEMANN T, STILLER B, et al.(eds). Networking 2006. Networking Technologies, Services, and Protocols; Performance of Computer and Communication Networks; Mobile and Wireless Communications Systems. Lecture Notes in Computer Science: vol 3976. Berlin, Heidelberg, Germany: Springer, 2006: 111-121
[2]	ALARCON-AQUINO V, BARRIA J A . Multiresolution FIR Neural-Network-Based Learning Algorithm Applied to Network Traffic Prediction[J]. IEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews), 2006,36(2):208-220. DOI: 10.1109/tsmcc.2004.843217
[3]	KRISHNAMURTHY B, SEN S, ZHANG Y, et al. Sketch-Based Change Detection: Methods, Evaluation, and Applications [C]//3rd ACM SIGCOMM Conference on Internet Measurement. Miami Beach, USA, 2003: 234-247. DOI: 10.1145/948205.948236
[4]	YANG M M, ZHU T Q, ZHOU W L , et al. Attacks and Countermeasures in Social Network Data Publishing [J]. ZTE Communications, 2016,14(S0):2-9. DOI: 10.3969/j.issn.1673-5188.2016.S0.001
[5]	CHRISTIAN J, MOHAMED B . A Software-Defined Approach to IoT Networking[J]. ZTE Communications, 2016,14(1):61-68. DOI: 10.3969/j.issn.1673-5188.2016.01.009
[6]	GROSCHWITZ N K, POLYZOS G C. A Time Series Model of Long-Term NSFNET Backbone Traffic [C]//International Conference on Communications. New Orleans, USA, 1994: 1400-1404. DOI: 10.1109/ICC.1994.368876
[7]	BASU S, MUKHERJEE A, KLIVANSKY S. Time Series Models for Internet Traffic [C]//Conference on Computer Communications. San Francisco, USA, 1996: 611-620. DOI: 10.1109/INFCOM.1996.493355
[8]	SHU Y T, WANG L, ZHANG L F, etc. Internet Network Business Forecast Based on FARIMA Model[J]. Chinese Journal of Computers, 2001,24(1):46-54
[9]	LIU X W, FANG X M, QIN Z H , et al. A Short-Term Forecasting Algorithm for Network Traffic Based on Chaos Theory and SVM[J]. Journal of Network and Systems Management, 2011,19(4):427-447. DOI: 10.1007/s10922-010-9188-3
[10]	WANG H F, HU D J. Comparison of SVM and LS-SVM for Regression [C]//International Conference on Neural Networks and Brain. Beijing, China, 2005: 279-283. DOI: 10.1109/ICNNB.2005.1614615
[11]	BENGIO Y, SIMARD P, FRASCONI P . Learning Long-Term Dependencies with Gradient Descent is Difficult[J]. IEEE Transactions on Neural Networks, 1994,5(2):157-166. DOI: 10.1109/72.279181
[12]	HOCHREITER S . The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions[J]. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 1998,6(2):107-116. DOI: 10.1142/s0218488598000094
[13]	HOCHREITER S, SCHMIDHUBER J . Long Short-Term Memory[J]. Neural Computation, 1997,9(8):1735-1780. DOI: 10.1162/neco.1997.9.8.1735
[14]	COLAH. Understanding LSTM Networks [EB/OL]. ( 2015- 08- 27). http://colah.github.io/posts/2015-08-Understanding-LSTMs
[15]	DING X, CANU S, DENOEUX T. Neural Network Based Models for Forecasting [C]//Proc. ADT'95. New York, USA: Wiley and Sons, 1995: 243-252
[16]	CORTEZ P, RIO M, ROCHA M , et al. Multi-Scale Internet Traffic Forecasting Using Neural Networks and Time Series Methods[J]. Expert Systems, 2010. DOI: 10.1111/j.1468-0394.2010.00568.x
[17]	FARIA A E Jr . Review of Forecasting: Methods and Applications (by MAKRIDAKIS S, WHEELWRIGHT S C, HYNDMAN R J, Third Edition)[J]. International Journal of Forecasting, 2002,18(1):158-59. DOI: 10.1016/s0169-2070(01)00130-3
[18]	HINTON G E, SRIVASTAVA N, KRIZHEVSKY A , et al. Improving Neural Networks by Preventing Co-Adaptation of Feature Detectors [EB/OL]. ( 2012-07-03).
[19]	ZAREMBA W, SUTSKEVER I, VINYALS O. Recurrent Neural Network Regularization [EB/OL].( 2014-09-08).

A Network Traffic Prediction Method Based on LSTM

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 12

References 19

Related Articles 1

Recommended Articles

Metrics