Approaches to predicting changes in the state of supporting components of an information management system

The article presents approaches to predicting the dynamics of the state of supporting components of information and control systems using the example of modeling the power system of a manufacturing enterprise. A method for modeling other types of supporting components based on the proposed approaches is considered. Modeling the state of the power system of a manufacturing enterprise is based on its representation in the form of a set of T-shaped cells consisting of resistance, capacitance and inductance. Forecasting changes in the state of the supporting components of the information and control system is carried out using a multilayer feed-forward neural network, taking into account nonlinear factors determined by the external and internal state of the production environment. Environmental parameters, data on depreciation of actuators and equipment, and regulatory production requirements are used as independent variables, and the power of the enterprise's energy system is used as a dependent variable. In this case, the power calculation is carried out on the basis of the described power system model using T-shaped cells. The model was trained on the basis of accumulated data. The obtained results of modeling the state of the supporting components of information control systems show that using a feedforward neural network model with one hidden layer and six nodes in it to predict the dynamics allows one to obtain an accurate power forecast taking into account various nonlinear factors. Experimental data are presented that prove the effectiveness of the approaches proposed by the authors for predicting the state of supporting components.

1. Lyaskovskaya E.A., Kurbangaliev M.R. Electric power problems and possibilities for efficient energy consumption at enterprises. Vestnik Yuzhno-Ural'skogo gosudarstvennogo universiteta. Seriya: Ekonomika i menedzhment = Bulletin of the South Ural State University. Series: Economics and Management. 2017;11(3):108–115. (In Russ.).

2. Childebaev B.S., Arzaliev B., Kamaridinov Zh., Aidarov R. Justification of energy supply risks production and risk prevention measures. Vestnik nauki i obrazovaniya. 2022;(5-2):7–11. (In Russ.).

3. Shevnina Ju.S. Decomposition method for a complex nonlinear system based on a process approach. Sistemy upravleniya i informatsionnye tekhnologii. 2021;(3):24–29. (In Russ.). https://doi.org/10.36622/VSTU.2021.85.3.005

4. Shevnina Yu.S. Hierarchical model nonlinear dynamic system. Sovremennaya nauka: aktual'nye problemy teorii i praktiki. Seriya: Estestvennye i tekhnicheskie nauki = Modern Science: actual problems of theory and practice. Series: Natural and Technical Sciences. 2021;(8):135–139. (In Russ.). https://doi.org/10.37882/2223-2966.2021.08.40

5. Shevnina Yu.S. Automating the assessment of the power grid state in remote areas of Russia using smart structures. Programmnye produkty i sistemy = Software & Systems. 2022;(2):240–245. (In Russ.). https://doi.org/10.15827/0236-235X.138.240-245

6. Boykova T.V., Grigoriev A.S., Makolkin D.V., Korolev S.A., Tutnov I.A. Quality and reliability of low-power power systems. Nadezhnost' i kachestvo slozhnykh sistem = Reliability & Quality of Complex Systems. 2023;(3):28–37. (In Russ.). https://doi.org/10.21685/2307-4205-2023-3-4

7. Petrov V.L., Kuznetsov N.M., Morozov I.N. Electric energy demand management in mining industry using smart power grids. Gornyi informatsionno-analiticheskii byulleten' = Mining Informational and Analytical Bulletin. 2022;(2):169–180. (In Russ.). https://doi.org/10.25018/0236_1493_2022_2_0_169

8. Borisov V.V., Kurilin S.P., Zharkov A.P., Sokolov A.M. Multidimensional prediction of heterogeneous electromechanical systems for risk management based on fuzzy temporal ontological and cognitive models. Sistemy upravleniya, svyazi i bezopasnosti = Systems of Control, Communication and Security. 2022;(4):83–102. (In Russ.). https://doi.org/10.24412/2410-9916-2022-4-83-102

9. Yarushkina N.G., Moshkin V.S., Andreev I.A., Ishmuratova G.I. Hybridization of fuzzy time series and fuzzy ontologies in the diagnosis of complex technical systems. In: Data Science Session at the 5th International Conference on Information Technology and Nanotechnology, DS-ITNT 2019: Ceur Workshop Proceedings: DS-ITNT 2019 – Proceedings of the Data Science Session at the 5th International Conference on Information Technology and Nanotechnology, 21-24 May 2019, Samara, Russia. 2019. P. 252–259. https://doi.org/10.18287/1613-0073-2019-2416-252-259

10. Borisov V.V., Luferov V.S. The method of multidimensional analysis and forecasting states of complex systems and processes based on Fuzzy Cognitive Temporal Models. Sistemy upravleniya, svyazi i bezopasnosti = Systems of Control, Communication and Security. 2020;(2):1–23. (In Russ.).

11. Yarushkina N.G., Moshkin V.S., Ishmuratova G.R., Andreev I.A., Moshkina I.A. Application of fuzzy time series and fuzzy ontology integration in diagnostics of technical systems. Ontologiya proektirovaniya = Ontology of Designing. 2018;8(4):594–604. (In Russ.). https://doi.org/10.18287/2223-9537-2018-8-4-594-604

12. Fedulov A.S. Fuzzy relational cognitive maps. Izvestiya Rossiiskoi akademii nauk. Teoriya i sistemy upravleniya = Journal of Computer and Systems Sciences International. 2005;44(1):112–124.