ABSTRACT
The need for detection, identification and prediction of anomalies emerged just a short time ago. This task brings multiple challenges that are mainly associated with recording and detection of novel attacks and influences. It draws attention of experts in network security and diagnostics of information and industrial systems. Detection of anomalies in dynamic dataflows largely determines the efficiency of management of computer network information security within information and industrial systems. At the same time, the technology of dynamic dataflow prediction is also very important for building systems intended to detect anomalies in data protection within industrial control systems. Any automated systems are based on available computer capabilities and advances in management theory, mathematical modeling and optimizations methods. Processes that occur in industrial automated systems and that are reflected in dataflows being observed constitute complex multi-component processes, thus making it more complicated to predict such processes. In this case, complex multi-component time series data should be predicted at different (short-term, medium-term and long-term) time scales. A neural network architecture matching the structure of the multi-component time series being predicted should be built for generating a multi-component prediction. It is proposed to decompose the complex multi-component time series into several basic components using the digital signal processing technology, i. e. to perform a preliminary structural analysis of multi-component time series within the observed range of all time series that reflect operation of the industrial control system. Separate predictions with different time horizon are formed for each basic component of the multi-component time series using the available neural network architecture and machine learning taking into account dynamic characteristics of the above components. Anomalies in the observed range of multiple time series that reflect operation of the industrial control system are detected (identified) through component-wise comparison of each component (resulted from the above preliminary digital processing) of any time series within the observed range of all time series, with each prediction of the relevant component of the above time series within the observed range of all time series. This approach that implies component-wise comparison will allow to detect anomalies within the range of observed time series of the industrial control system separately by their different dynamic characteristics, and thus will improve the efficiency of management of information security within information and industrial systems.
- A. Belyayev, S. Petrenko. Anomaly Detection Systems: New Information Security Concepts --- M.: "Ekspress-Elektronika", No. 2, 2004, pp. 36--54.Google Scholar
- A. Ragozin, V.Telezhkin, P.Podkorytov. Prediction of Aggregate Multicomponent Time Series in Industrial Automated Systems Using Neural Network, Lecture Notes in Engineering and Computer Science: Proceedings of The International MultiConference of Engineers and Computer Scientists 2019, 13--15 March, 2019, Hong Kong, pp17--19.Google Scholar
- I. S. Kobersi and V. V. Shadrina, "Use of neural networks for energy management," Izvestiya SFedU. Engineering sciences, no. 7 (84), pp. 190--195.Google Scholar
- V. N. Zuyeva and D. A. Trukhan, "Regression methods for predicting the load schedule of electrical equipment of enterprises, organizations and institutions: monograph," Kuban State Technological University. Krasnodar: KubSTU, 2017, pp. 123--135.Google Scholar
- A. P. Shuravin and S. V. Vologdin, "Filtering input data of neural network using digital signal processing technologies," Bulletin of Kalashnikov ISTU, no. 4, pp. 104--109, 2017.Google ScholarCross Ref
- A. M. Abdurakhmanov, M. V. Volodin, E. Yu. Zybin, and V. N. Ryabchenko, "Methods for predicting power consumption in distribution networks (review)," Russian Internet Journal of Electrical Engineering, pp. 3--23, 2016.Google Scholar
- D. T. Yakupov and O. N. Rozhko, "Prospects for use of artificial neural networks for predicting cargo volume in transport systems," Statistical and mathematical methods in economics, no. 5, pp. 49--58, 2017.Google Scholar
- Yu. N. Katsyuba 'Use of artificial neural networks for predicting technical condition of products' / Yu. N. Katsyuba, L.V. Grigorieva // International Scientific Research Journal - 2016. - No. 3 (45). - Pp. 19--21.Google Scholar
- A. N. Ragozin and E. A. Petryakov, "Predicting economic time series using an adaptive model of autoregression," Scientific and Analytical Economic Journal, no. 1 (2), pp. 25--28, 2016.Google Scholar
- F. Murtagh, J.-L. Starck, and O. Renaud, "On neuro-wavelet modeling," Decision Support Systems Journal, no. 37, pp. 475--484, 2004.Google ScholarDigital Library
- K. Nikola, "DENFIS: dynamic evolving neural-fuzzy inference system and its application for time-series prediction," IEEE Transactions on Fuzzy Systems, vol. 10, no. 2, pp. 144--154, 2002.Google ScholarDigital Library
- S. Tomonobu and T. Hitoshi, "One-hour-ahead load forecasting using neural network," IEEE Transactions on Power Systems, no. 1, pp. 21--24, 2002.Google Scholar
- R. Huang, T. Huang, and Gadh, "Solar generation prediction using the ARMA model in a laboratory-level micro-grid," in IEEE Third International Conference on Smart Grid Communications, Sydney, 2012, pp. 528--533.Google Scholar
- K. Pichotta and R. J. Mooney. (2016). Learning statistical scripts with LSTM recurrent neural networks. AAAI. pp. 2800--2806. Available: https://pdfs.semanticscholar.org/1ceb/038d8b4838120e0dc0a11c949d032cebf5dd.pdf.Google Scholar
- N. Tax, I. Verenich, M. L. Rosa, and M. Dumas. (2017, May). Predictive Business Process Monitoring with LSTM Neural Networks. arXiv.org. Available: https://arxiv.org/pdf/1612.02130.pdf.Google Scholar
- M. Granroth-Wilding and S. Clark, "What Happens Next? Event Prediction Using a Compositional Neural Network Model," AAAI, pp. 2727--2733, 2016.Google Scholar
- F. Murtagh, J.-L. Starck, and O. Renaud, "On Neuro-Wavelet Modeling," Decision Support Systems Journal, no. 37, pp. 475--484, 2004.Google ScholarDigital Library
- N. Singh, "Stochastic modeling of aggregates and products of variable failure rates," IEEE Transactions on Reliability, vol. 44, no. 2, pp. 279--284, 1995.Google ScholarCross Ref
- W. E. Rhoden, "Observation of electromigration at low temperature," IEEE Transactions on Reliability, vol. 40, no. 5, pp. 524--530, 1991.Google ScholarCross Ref
- R. M. Geffhen, J. G. Ryan, and G. J. Slusser, "Contact Metallurgy Development for VLSI Logic," IBM Journal of Research & Development, vol. 31, no. 6, pp. 608--616, 1987.Google ScholarDigital Library
- A. N. Ragozin and A. A. Razumov, "Neural network forecasting with preliminary digital filtering of complex radio signals," in XVI International scientific and technical conference Physics and technical applications of wave processes, Miass, 2018, pp. 285--290.Google Scholar
- F. Fantini, C. Morandi, "Failure modes and mechanisms for VLSI ICs - a review," IEEE Proceedings, vol. 132, no. 3, pp. 74--81. 1985.Google Scholar
Recommendations
Forecasting Seasonal Time Series Using Weighted Gradient RBF Network based Autoregressive Model
CIKM '16: Proceedings of the 25th ACM International on Conference on Information and Knowledge ManagementHow to accurately forecast seasonal time series is very important for many business area such as marketing decision, planning production and profit estimation. In this paper, we propose a weighted gradient Radial Basis Function Network based ...
Prediction of the Fourth Industrial Revolution Based on Time Series
ICIIT '18: Proceedings of the 2018 International Conference on Intelligent Information TechnologyThe history of human industrial development has undergone three industrial revolutions. Based on the occurrence time sequences of the three industrial revolutions, the industrial revolution time prediction function based on quadratic function and the ...
A Prediction-Augmented AutoEncoder for Multivariate Time Series Anomaly Detection
Neural Information ProcessingAbstractTo ensure the normal running of IT systems, multivariate time series changing constantly related to system states need to be monitored to detect unexpected events and anomalies and further prevent adverse effects on the systems. With the rapid ...
Comments