Informatics and Applications
2023, Volume 17, Issue 4, pp 71-80
MODELS FOR STUDY OF THE INFLUENCE OF STATISTICAL CHARACTERISTICS OF COMPUTER NETWORKS TRAFFIC ON THE EFFICIENCY OF PREDICTION BY MACHINE LEARNING TOOLS
- S. L. Frenkel
- V. N. Zakharov
Abstract
The article is an attempt to streamline and categorize a huge stream of publications on modern methods, techniques, and models of data forecasting of various nature in terms of their applicability for traffic forecasting in computer networks. The specified ordering is performed within the framework of the proposed conceptual model of forecasting algorithms. Within the framework of this conceptual model, the characteristics of both computer network traffic models and traffic control methods that can be explicitly or implicitly used in modern prediction software tools are highlighted. It is shown that the analysis of such probabilistic aspects of data description as the presence of significant nonstationarity, some nonlinear effects in data models, as well as the specifics of data distribution laws can influence the efficiency of learning predictors.
[+] References (27)
- Chen, A., J. Law, and M. Aibin. 2021. A survey on
traffic prediction techniques using artificial intelligence
for communication networks. Telecom 2(4):518-535. doi:
10.3390/telecom2040029.
- Frenkel, S. 2023. On impact of data models on predictability assessment of time series. Data analysis and
optimization. Eds. B. Goldengorin and S. Kuznetsov. Optimization and its applications ser. Springer. 202:103-134.
doi: 10.1007/978-3-031-31654-8_7.
- Fettke, P. 2020. Conceptual modelling and artificial intelligence: Overview and research challenges from the
perspective of predictive business process management.
CEUR Workshop Procee. 2542:157-164.
- Shalev-Shwartz, S. 2014. Understanding machine learning:
From theory to algorithms. Cambridge University Press.
449 p.
- Brovelli, M., F Sanso, and G. Venuti. 2003. A discussion
on the Wiener-Kolmogorov prediction principle with
easy-to compute and robust variants. J. Geodesy 76:673-683. doi: 10.1007/s00190-002-0292-3.
- Merhav, N., and M. Feder. 1998. Universal prediction.
IEEE T. Inform. Theory 44(6):2124-2147. doi: 10.1109/18.720534.
- Ryabko, B. 2009. Compression-based methods for nonparametric prediction and estimation of some characteristics of time series. IEEE T. Inform. Theory 55(9):4309-4315. doi: 10.1109/TIT.2009.2025546.
- Box, G. E. P., G. M. Jenkins, and G. Reinsel. 2008. Time
series analysis: Forecasting and control. New York, NY: 17. John Wiley & Sons, Inc. 709 p.
- Aryan, M. 2017. Efficient methods for large-scale empirical risk minimization. Philadelphia, PA: University of Pennsylvania. PhD Thesis. 303 p.
- Sharma, S. 2017. Activation functions in neural net-works. Available at: https://towardsdatascience.com/ activation-functions-neural-networks-1cbd9f8d91d6 (accessed December 4, 2023).
- Weiwei, J. 2022. Cellular traffic prediction with machine learning: A survey. Expert Syst. Appl. 201:117-163. doi: 10.1016/j.eswa.2022.117163.
- Miller, J., andA. Sanjurjo. 2019. Surprised by the hot hand fallacy? A truth in the law of small numbers. arXiv.org. 49 p. Available at: https://arxiv.org/abs/1902.01265v1 (accessed December 4, 2023).
- Jiang, M., M. Nikolic, S. Hardy, and L. Trajkovic. 2001. Impact of self-similarity on wireless data Network performance. Conference (International) on Communications Proceedings. Piscataway, NJ: IEEE. 2:477-481. doi: 10.1109/ICC.2001.936986.
- Brignoli, D. 2008. DDOS detection based on traffic selfsimilarity. Christchurch, New Zealand: University Canterbury. Master Thesis. 100 p.
- Lleland, IE.,M. S. Taqqu, W Willinger, and D. V. Wilson. 1994. On the self-similar nature of Ethernet traffic (extended version). IEEE ACM T. Network. 2(1):1-15. doi: 10.1109/90.282603.
- Coskun, B., B. Vardar-Acar, and C. Demirtas. 2019. A generalized correlated random walk, converging to fractional Brownian motion. arXiv.org. 21 p. Available at: https://arxiv.org/abs/1903.05424v3 (accessed December 4, 2023).
- Riya, J., and P. Chetty 2020. What is a stationarity test and how to do it? PG. Available at: https://www.projectguru.in/what-is-a-stationarity-test-how-to-do-it (accessed December 4, 2023).
- Park, C., F Hernandez, L. Long, and J. Mar- ron. 2011. Long-range dependence analysis of internet traffic. J. Appl. Stat. 38(7):1407-1433. doi: 10.1080/
02664763.2010.505949.
- Sornette, D., and J. Andersen. 2000. Increments of uncorrelated time series can be predicted with a universal 75% probability of success. Int. J. Mod. Phys. C 11(4):713-720. doi: 10.1142/S0129183100000626.
- Frenkel, S. 2022. Predicting the direction of changes in the values of time series for relatively small training samples. Cyber security, cryptography, and machine learning. Eds. S. Dolev, J. Katz, and A. Meisels. Lecture notes in computer science ser. Cham, Switzerland: Springer. 13301:118-134. doi: 10.1007/978-3-031-07689-3_9.
- Song, W, S. Duan, D. Chen, E. Zio, W Yan, and F. Cai. 2022. Finite iterative forecasting model based on fractional generalized Pareto motion. Fractal 6(9):471-490. doi: 10.33 90/fractalfract6090471.
- Pan, C., Y Wang, H. Shi, J. Shi, and R. Cai. 2022. Network traffic prediction incorporating prior knowledge for an intelligent network. Sensors 22(7):2674-2690. doi: 10.3390/s22072674.
- Tong, H., C. Li, and J. He. 2004. A boosting-based framework for self-similar and non-linear internet traffic prediction. Advances in neural networks. Eds. F Yin, J. Wang, and C. Guo. Lecture notes in computer science ser. Berlin, Heidelberg: Springer. 3174:931-936. doi: 10.1007/978-3-540-28648-6_148.
- Zhang, J., D. Tan, and H. Zhu. 2017. From machine learning to deep learning: progress in machine intelligence for rational drug discovery. Drug Discov. Today 22(11): 1680-1685. doi: 10.1016/j.drudis.2017.08.010.
- Nikravesh, A. Y., S. A. Ajila, andC.-H. Lung. 2017. Anautonomic prediction suite for cloud resource provisioning. J. Cloud Computing 6(3). 20 p. doi: 10.1186/s13677-017- 0073-4.
- Dolev, S., S. Frenkel, and V. Zakharov. 2021. Fore-casting tools in practical applications: Selection and evaluation methodology. Conference (International) on Engineering Technologies and Computer Science Proceedings. Piscataway, NJ: IEEE. 37-44. doi: 10.1109/ EnT52731.2021.00013.
- Lukashenko, O., E. Morozov, and M. Pagano. 2019. A Gaussian approximation of the distributed computing process. Informatika i ee Primeneniya - Inform. Appl. 13(2):109-116. doi: 10.14357/19922264190215. EDN: PKNUSZ.
[+] About this article
Title
MODELS FOR STUDY OF THE INFLUENCE OF STATISTICAL CHARACTERISTICS OF COMPUTER NETWORKS TRAFFIC ON THE EFFICIENCY OF PREDICTION BY MACHINE LEARNING TOOLS
Journal
Informatics and Applications
2023, Volume 17, Issue 4, pp 71-80
Cover Date
2023-12-10
DOI
10.14357/19922264230410
Print ISSN
1992-2264
Publisher
Institute of Informatics Problems, Russian Academy of Sciences
Additional Links
Key words
network traffic prediction; probabilistic models
Authors
S. L. Frenkel  and V. N. Zakharov
Author Affiliations
Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences, 44-2 Vavilov Str., Moscow 119333, Russian Federation
|