Round-Trip Time Prediction Using Machine Learning Methods
Ivan Alexandrovich STEPANOV,
Roman Evgenevich PONOMARENKO,
Denis Rostislavovich GOLOVASH,
Anton Yurevich POKIDKO,
Aleksandr Igorevich GETMAN https://doi.org/10.15514/ISPRAS-2025-37(5)-4
Abstract
The congestion control algorithms in the TCP protocol use RTT predictions indirectly or directly to determine congestion. The main algorithm for predicting RTT based on a weighted moving average is the Jacobson Algorithm. However, this algorithm may not work quite efficiently if the RTT is subject to a heavy-tailed distribution. In this paper, we propose an RTT prediction method based on supervised learning in both the offline and online cases. The results show improvement in the performance of algorithms based on supervised learning compared to the classical Jacobson algorithm in terms of MAPE, MAE, and MSE metrics. In addition, the high efficiency of online learning in comparison with offline learning in the case of data drift is shown.
About the Authors
Ivan Alexandrovich STEPANOV
Ivannikov Institute for System Programming of the Russian Academy of Sciences, Moscow Institute of Physics and Technology (National Research University)
Russian Federation
Russian Federation
Postgraduate student of the ISP RAS, intern researcher at ISP RAS, an assistant at the Department of Computer Science and Computational Mathematics at MIPT. Research interests: network traffic analysis using machine learning.
Roman Evgenevich PONOMARENKO
Ivannikov Institute for System Programming of the Russian Academy of Sciences
Russian Federation
Russian Federation
Junior researcher at ISP RAS. Research interests: software architecture, program optimization, deep packet inspection.
Denis Rostislavovich GOLOVASH
Ivannikov Institute for System Programming of the Russian Academy of Sciences
Russian Federation
Russian Federation
A laboratory assistant at the ISP RAS, a student at the Moscow State University. Research interests: network traffic analysis using machine learning.
Anton Yurevich POKIDKO
Ivannikov Institute for System Programming of the Russian Academy of Sciences
Russian Federation
Russian Federation
Research intern at Compiler Technology department of ISP RAS. Research interests: drift in machine learning and neural networks, transfer learning, federated learning, online learning, network traffic analysis.
Aleksandr Igorevich GETMAN
Ivannikov Institute for System Programming of the Russian Academy of Sciences, Moscow Institute of Physics and Technology (National Research University), National Research University «Higher School of Economics»,
Lomonosov Moscow State University
Russian Federation
Russian Federation
Cand. Sci. (Phys.-Math.), senior researcher at ISP RAS, assistant at CMC MSU and MIPT, associate professor at HSE. Research interests: binary code analysis, data format recovery, network traffic analysis and classification.
References
1. Mo, J., La, R. J., Anantharam, V., and Walrand, J. (1999, March). Analysis and comparison of TCP Reno and Vegas. In IEEE INFOCOM'99. Conference on Computer Communications. Proceedings. Eighteenth Annual Joint Conference of the IEEE Computer and Communications Societies. The Future is Now (Cat. No. 99CH36320) (Vol. 3, pp. 1556-1563). IEEE.
2. Hernández, José-Alberto, and Iain W. Phillips. "Weibull mixture model to characterise end-to-end Internet delay at coarse time-scales." IEE Proceedings-Communications 153.2 (2006): 295-304.
3. Cerroni, W., Foschini, L., Grabarnik, G. Y., Shwartz, L., and Tortonesi, M. (2017). Estimating delay times between cloud datacenters: A pragmatic modeling approach. IEEE Communications Letters, 22(3), 526 529.
4. Rizo-Dominguez, L., Munoz-Rodriguez, D., Vargas-Rosales, C., Torres-Roman, D., and Ramirez-Pacheco, J. (2014). RTT prediction in heavy tailed networks. IEEE Communications Letters, 18(4), 700 703.
5. Hu, Wen, Zhi Wang, and Lifeng Sun. "Guyot: a hybrid learning-and model-based RTT predictive approach." 2015 IEEE International Conference on Communications (ICC). IEEE, 2015.
6. Dasgupta, B., D. Valles, and S. McClellan. "Estimating TCP RTT with LSTM Neural Networks." Proceedings on the International Conference on Artificial Intelligence (ICAI). The Steering Committee of The World Congress in Computer Science, Computer Engineering and Applied Computing (WorldComp). 2019.
7. Hagos, D. H., Engelstad, P. E., Yazid, A., and Griwodz, C. (2019, October). A deep learning approach to dynamic passive RTT prediction model for TCP. In 2019 IEEE 38th International Performance Computing and Communications Conference (IPCCC) (pp. 1-10). IEEE.
8. Dong, Ai, Zhijiang Du, and Zhiyuan Yan. "Round trip time prediction using recurrent neural networks with minimal gated unit." IEEE Communications Letters 23.4 (2019): 584-587.
9. Berger, Vance W., and YanYan Zhou. "Kolmogorov–smirnov test: Overview." Wiley statsref: Statistics reference online (2014).
10. Berkson, Joseph. "Some difficulties of interpretation encountered in the application of the chi-square test." Journal of the American Statistical Association 33.203 (1938): 526-536.
11. Engmann, Sonja, and Denis Cousineau. "Comparing distributions: the two-sample anderson-darling test as an alternative to the kolmogorov-smirnoff test." Journal of applied quantitative methods 6.3 (2011).
12. Jaworski, Maciej, Leszek Rutkowski, and Plamen Angelov. "Concept drift detection using autoencoders in data streams processing." International Conference on Artificial Intelligence and Soft Computing. Cham: Springer International Publishing, 2020.
13. Nau, Robert. "The mathematical structure of ARIMA models." Duke University Online Article 1.1 (2014): 1-8.
14. Bifet, Albert, and Ricard Gavalda. "Learning from time-changing data with adaptive windowing." Proceedings of the 2007 SIAM international conference on data mining. Society for Industrial and Applied Mathematics, 2007.
15. Gomes, H. M., Bifet, A., Read, J., Barddal, J. P., Enembreck, F., Pfharinger, B., ... and Abdessalem, T. (2017). Adaptive random forests for evolving data stream classification. Machine Learning, 106, 1469 1495.
16. Gomes, H. M., Barddal, J. P., Ferreira, L. E. B., and Bifet, A. (2018, April). Adaptive random forests for data stream regression. In ESANN.
17. Montiel, J., Halford, M., Mastelini, S. M., Bolmier, G., Sourty, R., Vaysse, R., ... and Bifet, A. (2021). River: machine learning for streaming data in python. Journal of Machine Learning Research, 22(110), 1-8.
Review
For citations:
STEPANOV I.A., PONOMARENKO R.E., GOLOVASH D.R., POKIDKO A.Yu., GETMAN A.I. Round-Trip Time Prediction Using Machine Learning Methods. Proceedings of the Institute for System Programming of the RAS (Proceedings of ISP RAS). 2025;37(5):53-66. https://doi.org/10.15514/ISPRAS-2025-37(5)-4
Email this article 