ONE METHOD FOR INTELLECTUAL PROACTIVE MONITORING OF COMPUTER NETWORKS - Problems of Information Technology

ONE METHOD FOR INTELLECTUAL PROACTIVE MONITORING OF COMPUTER NETWORKS - Problems of Information Technology

ONE METHOD FOR INTELLECTUAL PROACTIVE MONITORING OF COMPUTER NETWORKS - Problems of Information Technology

ONE METHOD FOR INTELLECTUAL PROACTIVE MONITORING OF COMPUTER NETWORKS - Problems of Information Technology

ONE METHOD FOR INTELLECTUAL PROACTIVE MONITORING OF COMPUTER NETWORKS - Problems of Information Technology
ONE METHOD FOR INTELLECTUAL PROACTIVE MONITORING OF COMPUTER NETWORKS - Problems of Information Technology
AZERBAIJAN NATIONAL ACADEMY OF SCIENCES

№2, 2021

ONE METHOD FOR INTELLECTUAL PROACTIVE MONITORING OF COMPUTER NETWORKS

Ramiz H. Shikhaliyev

The article proposes a method for intelligent proactive monitoring of computer networks (CN). To ensure proactive monitoring of the CN, it is proposed to use artificial intelligence methods, in particular, deep learning (DL). Network monitoring systems now work well in near real-time. However, traditional monitoring systems generally do not have a proactive monitoring function. Despite the fact that today the CN has sufficient computing power, bandwidth and memory, the identification of important events among the huge volumes of monitoring data remains a problem. Consequently, untimely detection of CN problems can lead to network disruptions, the provision of network services and a decrease in CN security. Unlike traditional monitoring, intelligent proactive monitoring can provide more information about the state of the CN. Proactive monitoring of the CN is based on predicting the behavior of the network. At the same time, one of the main requirements for intelligent proactive monitoring of CN is the accuracy of predictions, which characterizes the ability of the prediction method. To achieve the accuracy of predictions during proactive monitoring of the CN, a homogeneous ensemble is used, which consists of a single basic learning algorithm. As a basic learning algorithm. the LSTM (Long Short-Term Memory) model is used. To create basic learning models for the LSTM ensemble, the "Bagging" algorithm is used. The method proposed in this work will make it possible to ensure a relatively high accuracy of prediction the problems in the CN, therefore, to ensure sufficient efficiency of the proactive monitoring system of the CN (pp.41-52).

Keywords: computer networks, proactive monitoring of computer networks, deep learning, LSTM, prediction.
DOI : 10.25045/jpit.v12.i2.04
References
  • M. Dilman and D. Raz Efficient Reactive Monitoring // IEEE Journal on Selected Areas in Communications, vol. 20, no. 4, 2002, pp. 668−676.
  • R. Khan, S. U. Khan, R. Zaheer and M. I. Babar An Efficient Network Monitoring and Management System // International Journal of Information and Electronics Engineering, vol. 3, no. 1, 2013, pp.122−126.
  • S. Lee, K. Levanti, H. S. Kim Network monitoring: Present and future // Computer Networks vol. 65, no. 2, 2014, pp. 84–98.
  • V. Sekar, M. K. Reiter, W. Willinger, H. Zhang, R. R. Kompella, David G. Andersen CSAMP: A System for Network-Wide Flow Monitoring / Proceedings of the 5th USENIX Symposium on Networked Systems Design & Implementation, 2008, pp. 233−246.
  • T. Fu, A review on time series data mining // Engineering Applications of Artificial Intelligence, vol. 24, no. 1, 2011, pp. 164−181.
  • Makridakis S., Spiliotis E. and Assimakopoulos V. Statistical and machine learning forecasting methods: Concerns and ways forward // PLOS ONE, vol. 13, no. 3, 2018, 26 p. https://dx.plos.org/10.1371/journal.pone.0194889
  • Baptista M., Sankararaman S., de Medeiros I. P., Nascimento C., Prendinger H. and Henriques E. M. Forecasting fault events for predictive maintenance using data-driven techniques and arma modeling // Computers Industrial Engineering, vol. 115, 2018, pp. 41–53.
  • Cerqueira V., Torgo L. and Soares C. Machine learning vs statistical methods for time series forecasting: Size matters, arXiv preprint arXiv:1909.13316, 2019. Available: https://arxiv.org/abs/1909.13316
  • Kajitani Y., Hipel K. W. and Mcleod A. I. Forecasting nonlinear time series with feed-forward neural networks: a case study of canadian lynx data // Journal of Forecasting, vol. 24, no. 2, 2005, pp. 105−117.
  • Mohammed B., Awan I., Ugail H. and Younas M., Failure prediction using machine learning in a virtualised hpc system and application // Cluster Computing, 2018, pp. 1−15.
  • Abdel-Basset M., Abdel-Fatah L. and Sangaiah A. K. Metaheuristic algorithms: A comprehensive review // Computational Intelligence for Multimedia Big Data on the Cloud with Engineering Applications. Elsevier, 2018, pp. 185−231.
  • Holland J. H., Adaptation in Natural and Artificial Systems, An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence. The MIT Press, 1992, 211 p.
  • Kennedy J. Particle swarm optimization // Encyclopedia of machine learning, 2010, pp. 760–766.
  • Salcedo-Sanz S., Del Ser J., Landa-Torres I., Gil-López S., and Portilla-Figueras J., The coral reefs optimization algorithm: a novel metaheuristic for efficiently solving optimization problems // The Scientific World Journal, vol. 2014, 2014.
  • Muthiah-Nakarajan V. and Noel M. M. Galactic swarm optimization: A new global optimization metaheuristic inspired by galactic motion // Applied Soft Computing, vol. 38, 2016, pp. 771–787.
  • Mirjalili S. and Lewis A. The whale optimization algorithm // Advances in Engineering Software, vol. 95, 2016, pp. 51–67.
  • Goodfellow I., Bengio Y. and Courville A., Deep Learning (AdaptiveComputation and Machine Learning series). MIT press, 2016.
  • Gamboa J. C. B. Deep learning for time-series analysis // arXiv preprint arXiv:1701.01887, 2017. https://arxiv.org/abs/1701.01887
  • Hochreiter S. and Schmidhuber J. Long short-term memory // Neural computation, vol. 9, no. 8, 1997, pp. 1735–1780.
  • Bruneo D. and De Vita F. On the use of lstm networks for predictive maintenance in smart industries / IEEE International Conference on Smart Computing. IEEE, 2019, pp. 241−248.
  • Schuster M. and Paliwal K. Bidirectional recurrent neural networks // IEEE Transactions on Signal Processing, vol. 45, no. 11, 1997, pp. 2673−2681.
  • Luong T., Pham H. and Manning C. D. Effective approaches to attention-based neural machine translation, 2015, pp. 1412−1421.
  • G. Nguyen, S. Dlugolinsky, V. Tran, Á. L. García Deep learning for proactive network monitoring and security protection, IEEE Access, vol. 8, 2016, pp. 19696−19716.
  • Elmasry M. Predict Network Application Performance Using Machine Learning and Predictive Analytics / Thesis, Rochester Institute of Technology, 2019.
  • A. Abusitta, M. Bellaiche, M.Dagenais, T. Halabi A deep learning approach for proactive multi-cloud cooperative intrusion detection system // Future Generation Computer Systems vol. 98, 2019, pp. 308−318.
  • J. R.de Santiago Proactive Measurement Techniques For Network Monitoring In Heterogeneous Environments / Doctoral thesis, Universidad Autónoma de Madrid, 2013.
  • Salfner, F., Lenk, M., Malek, M.: A survey of online failure prediction methods // ACM Computing Surveys vol. 42, no. 3, 2010, pp.1−42.
  • R.Herbrich and T. Graepel, Ensemble Methods: Foundations and Algorithms, Taylor & Francis Group, LLC, 2012, 222 p.
  • A. Metzger and F. Focker, Predictive Business Process Monitoring Considering Reliability Estimates / International Conference on Advanced Information Systems Engineering CAISE 2017, pp 445−460.