E3S Web Conf.
Volume 157, 2020Key Trends in Transportation Innovation (KTTI-2019)
|Number of page(s)||8|
|Section||Environmental and Energy Management|
|Published online||20 March 2020|
Adaptive method of detecting traffic anomalies in high-speed multi-service communication networks
Radioavionica JSC, 4 lit. B Troitsky pr., St. Petersburg 190005, Russia
2 Admiral Makarov State University of Maritime and Inland Shipping, 5/7 Dvinskaya srt., St. Petersburg, 198035, Russia
3 Emperor Alexander I St. Petersburg State Transport University, 9 Moskovsky pr., Saint Petersburg, 190031, Russia
* Corresponding author: firstname.lastname@example.org
In the paper, an adaptive hybrid heuristic (behavioral) method for detecting small traffic anomalies in high-speed multiservice communication networks, which operates in real time, is proposed and investigated. The relevance of this study is determined by the fact that network security management processes in high-speed multiservice communication networks need to be implemented in a mode close to real-time mode, as well as identifying possible network security threats in the early stages of the implementation of possible network attacks. The proposed method and algorithm belong to the class of adaptive methods and algorithms with preliminary training. The average relative error in estimating the evaluated traffic parameters does not exceed 10%, which is sufficient for the implementation of operational network management tasks. Anomalies of the expectation of traffic intensity and its dispersion are identified if their valuesexceed the normal values by 15% or more, which makes it possible to detect possible network attacks in the early phases of their implementation, for example, at the stage of scanning ports and interfaces of the attacked system. The procedure for detecting anomalous traffic behavior is implemented based on the Mamdani’s method of hierarchical fuzzy logical inference. A study of the proposed method for detecting anomalous behavior of network traffic showed its high efficiency.
© The Authors, published by EDP Sciences, 2020
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.