№1, 2020

ONE MODEL OF REAL-TIME MONITORING OF COMPUTER NETWORKS

Ramiz H. Shikhaliyev

To ensure the normal and safe functioning of modern computer networks (CN), reliable and effective monitoring models are required. These models should allow analyzing a large volume of network traffic data streams in real time. However, the traditional data mining approaches used today cannot solve this task. To solve this problem, it is more suitable to use data stream mining techniques. This article proposes a real-time monitoring model of CN in which data stream mining algorithms are used. The proposed model is multitasking, that is, depending on the objectives of monitoring the CN, the corresponding algorithms for the intellectual analysis of data flows can be used to analyze data flows of network traffic. To do this, the algorithms, such as clustering data streams, classifying data streams, analyzing patterns, and analyzing time series, are used. Thus, the proposed model can allow real-time monitoring of CN in a variety of contexts, for example, detect trends, anomalies and patterns, as well as real-time forecasts, etc. (pp.90-97).

Keywords: monitoring, network traffic data stream, data stream clustering, data stream classification, time series analysis.
References
  • Шыхалиев Р.Г. О применении интеллектуальных технологий в мониторинге компьютерных сетей // Искусственный интеллект, 2011, №1, с.124−132.
  • Wesam S.B., Saud A.A. Anomaly detection in network traffic using stream data mining: review // Research Journal of Applied Sciences, 2016, vol.11, no.10, pp. 1076−1082.
  • Mohamed MG., Arkady Z., Shonali K. Mining Data Streams: A Review // SIGMOD Record, 2005, vol.34, no.2, pp.18−26.
  • Neha G., Indrjeet R. Stream Data Mining: A Survey // International Journal of Engineering Research and Applications, 2013, vol.3, no.1, pp.1113−1118.
  • Ryszard E.J., Miliosz M.H. Packet Sampling for Network Monitoring, Technical Report 2007. http://cern.ch/openlab
  • Davide T., Silvio V., Dario R., Antonio P. Exploiting packet sampling measurements for traffic characterization and classification // International Journal of Network Management, 2012, vol.22, no.6, pp.451−476.
  • Marco C., Damien F., David J.M., Andrew W.M., Raffaele B. Per flow packet sampling for high-speed network monitoring / Proceedings of the First International Conference on Communication Systems And NETworks, 2009, pp.463−472.
  • Song S., Ling L., Manikopoulo C.. Flow-based statistical aggregation schemes for network anomaly detection / Proceedings of the IEEE International Conference on Networking Sensing and Control, 2006, pp.786−791.
  • Bin L., Chuang L., Jian Q. A NetFlow based flow analysis and monitoring system in enterprise networks // Computer networks, 2008, vol. 52, no.5, pp.1074−1092.
  • Marco F., Kawahara R., Ishibashi K., Mori T. Detection accuracy of network anomalies using sampled flow statistics // International Journal of Network Management, 2011, vol. 21, no.6, pp.513−535.
  • Accurate and flexible flow-based monitoring for high-speed networks, Master Thesis. Autonomous University of Madrid, 2013, 38 p.
  • Wang B., Su J. A survey of elephant flow detection in SDN / Proceedings of the 6th International Symposium on Digital Forensic and Security, 2018, pp.208−213.
  • Gerald T. Real Time Network Traffic Monitoring. Technical Report: 5–99, Computing Laboratory, University of Kent, 1999.
  • Ahmed M. M. M. A real time distributed network monitoring platform (RTDNM), Doctoral Thesis, Universiti Sains Malaysia, 2009, 224 p.
  • Xu T., Qiong S., Xiaohong H., Yan M. A Dynamic Online Traffic Classification Methodology based on Data Stream Mining / Proceedings of the World Congress on Computer Science and Information Engineering, 2009, pp.298–302.
  • Kuai X., Feng W. Real-time behaviour profiling for network monitoring // International Journal of Internet Protocol Technology, 2010, vol.5, no.1/2, pp.65−80.
  • Aryan T.M., Tomasz W.W., Chunming R. Real-Time Handling of Network Monitoring Data Using a Data-Intensive Framework / Proceedings of the IEEE 5th International Conference on Cloud Computing Technology and Science, 2013.
  • Li L., Hu Z.-Y. The Research of Data Stream Technology in Computer Network Security Monitoring / Proceedings of the International Conference on Intelligent Systems Research and Mechatronics Engineering, 2015, pp.1904−1907.
  • John F., Matthew B., Michael H. Introduction to stream: A Framework for Data Stream Mining Research. http://www2.uaem.mx/r-mirror/web/packages/stream/vignettes/stream.pdf
  • Silva, J.A., Faria, E.R., Barros, R.C., Hruschka, E.R., de Carvalho, A.C., Gama, J., Data stream clustering: A survey // ACM Computing Surveys, 2013, vol.46, no.1, p.13.
  • Kholghi M., Keyvanpour M. An Analytical Framework for Data Stream Mining Techniques Based on Challenges and Requirements // International Journal of Engineering, Science and Technology, 2011, vol.3, no.3, pp.2507−2513.
  • Chao S.C., Lin K.C., Chen M.S. Flow Classification for Software-Defined Data Centers Using Stream Mining // IEEE Transactions on Services Computing, 2019, vol. 12 , no. 1, pp.105–116.
  • Sidda Reddy V., Rao T.V., Govardhan A. Data mining techniques for data streams mining // Review of computer engineering studies, 2017, vol.4, no.1, pp.31−35.
  • Golab L., Özsu M.T. Issues in data stream management // ACM SIGMOD Record, vol.32, no.2, 2003, pp.5−14.
  • Tatbul N., Cetintemel U., Zdonik S., Cherniack M., Stonebraker M. Load Shedding on Data Streams, Proceedings of the Workshop on Management and Processing of Data Streams, 2003.
  • Florin R., Alin D. Sketching Sampled Data Streams / Proceedings of the IEEE 25th International Conference on Data Engineering, 2009, vol.1−3, pp.381−392.
  • Babcock B., Babu S., Datar M., Motwani R., Widom J. Models and issues in data stream systems / Proceedings of the twenty-first ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems, 2002, pp.1−16.
  • Aggarwal C, Han J., Wang J., Yu P. S. A Framework for Projected Clustering of High Dimensional Data Streams / Proceedings of the Thirtieth international conference on Very large data bases, 2004, vol.30, pp.852−863.
  • Cormode G., Muthukrishnan S. What's hot and what's not: Tracking most frequent items dynamically // ACM Transactions on Database Systems, 2005, vol.30, no.1, pp.249−278.
  • Gaber, M, M., Zaslavsky, A., and Krishnaswamy, S. Towards an Adaptive Approach for Mining Data Streams in Resource Constrained Environments / Proceedings of the 6th International Conference on Data Warehousing and Knowledge Discoverey, 2004, Data Warehousing And Knowledge Discovery, Proceedings: Lecture Notes in Computer Science, vol.3181, pp.189−198.
  • Aggarwal C. An Introduction to Data Streams // Data Streams: Models and Algorithms, 2007, pp.1−18.
  • Gama J. Knowledge Discovery from Data Streams. 1st edition. Chapman & Hall/CRC, Boca Raton, 2010.
  • Sharma N., Masih S., Makhija P. A Survey on Clustering Algorithms for Data Streams // International Journal of Computer Applications, 2018, vol.182, no.22, pp.18−24.
  • Gaber M. M., Zaslavsky A., Krishnaswamy S. A Survey of Classification Methods in Data Streams // Data Streams: Models and Algorithms, 2007, pp.39−59.
  • Subbulakshmi B., Deis C., Periya Nayaki A. Survey on Frequent Pattern Mining over Data Streams // International Journal of Engineering Research and Technology, 2013, vol.2, no. 12, pp.2276−2283.
  • Jinlong W., Congfu X., Weidong C., Yunhe P. Survey of the study on frequent pattern mining in data streams / Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, 2004, vol.1−7, pp.5917−5922.