Email this article Application of the theory of petri nets in the development of simulation models of business processes based on the IDEF3 methodology
- Authors: Petrosov D.А.1
-
Affiliations:
- Financial University under the Government of the Russian Federation
- Issue: Vol 11, No 3 (2024)
- Pages: 89-97
- Section: MATHEMATICAL MODELING, NUMERICAL METHODS AND COMPLEX PROGRAMS
- URL: https://journal-vniispk.ru/2313-223X/article/view/285912
- DOI: https://doi.org/10.33693/2313-223X-2024-11-3-89-97
- EDN: https://elibrary.ru/QONIXQ
- ID: 285912
Cite item
Open Access
Access granted
Subscription Access
Abstract
In this study, we propose a model of an artificial neural network used as a specialized superstructure over a genetic algorithm, which allows influencing the process of finding solutions directly during the synthesis of solutions. Such a combination of methods will allow controlling the trajectory of the population in the solution space, which is especially important when working with big data processing technology, when stopping the solution search process due to the attenuation of the evolutionary procedure or finding the population in a local extremum requires stopping the genetic algorithm, performing additional adjustment of operators and restarting, the use of such an approach is ineffective, especially when working with big data and labor-intensive calculations. This article proposes a model of an artificial neural network that allows recognizing the state of the population of the genetic algorithm and making a decision to change the operating parameters of the genetic algorithm operators. The proposed model allows recognizing the processes of attenuation of the evolutionary procedure when solving the problem of structural and parametric synthesis of large discrete systems and determining measures of influence on the operating parameters of the genetic algorithm. This model recognizes the state of the population with an accuracy of more than 95%, which allows to significantly reduce the time for finding solutions in problems of applying a genetic algorithm to work with big data.
Full Text
##article.viewOnOriginalSite##About the authors
David А. Petrosov
Financial University under the Government of the Russian Federation
Author for correspondence.
Email: dapetrosov@fa.ru
ORCID iD: 0000-0002-8214-052X
SPIN-code: 2574-6798
Cand. Sci. (Eng.), Associate Professor, Head, Department of Information Technologies
Russian Federation, MoscowReferences
- Buevich A.G., Sergeev A.P., Shichkin A.V. et al. Model for forecasting surface methane concentration in the Arctic region based on an artificial neural network with a long chain of short-term memory elements and wavelet transform of the initial data. Arctic: Ecology and Economics. 2023. Vol. 13. No. 3 (51). Pp. 428–436. (In Rus.)
- Bukhanov D.G., Polyakov V.M. Intrusion detection system in IP networks using artificial neural networks of adaptive resonance theory with a hierarchical memory structure. Information and Security. 2019. Vol. 22. No. 1. Pp. 44–67. (In Rus.)
- Puchkov E.V., Lila V.B. Methodology of training a recurrent artificial neural network with dynamic stack memory. Software Products and Systems. 2014. No. 4. Pp. 132-135. (In Rus.)
- Perepelkin V.Yu. Using recurrent neural networks for forecasting time series. Modern Science: Current Problems of Theory and Practice. Series: Natural and Technical Sciences. 2023. No. 7-2. Pp. 80–82. (In Rus.)
- Antoshkin V.A., Zatsepin D.K. Methodology for deploying a neural network for time series analysis using the ISAVRS server. Computer Science and Applied Mathematics. 2023. No. 29. Pp. 5–10. (In Rus.)
- Efanov V.N., Mufazzalov D.F. Genetic algorithm for stabilization of complex control systems. Information, Measuring and Control Systems. 2024. Vol. 22. No. 2. Pp. 31–43. (In Rus.)
- Galaktionova E.S., Korytova T.V., Avadeni Yu.I., Gramatchikova V.E. Management of motor transport enterprises using scheduling theory and genetic algorithms. Azimuth of Scientific Research: Economics and Management. 2021. Vol. 10. No. 2 (35). Pp. 145–148. (In Rus.)
- Markov A.D., Fedoseev D.A., Drobysheva V.O. Selecting a genetic algorithm crossover operator for solving an asset management problem. Scientific Electronic Journal “Meridian”. 2020. No. 9 (43). Pp. 48–50. (In Rus.)
- Sofronova E.A. Genetic algorithm with non-dominated sorting for solving the problem of traffic flow control. Issues of the Theory of Security and Stability of Systems. 2022. No. 24. Pp. 110–121. (In Rus.)
- Petrosov D.A., Petrosova N.V. Artificial neural networks in problems of genetic algorithm control in the process of structural-parametric synthesis of large discrete systems with given behavior. Prospects of Science. 2018. No. 11 (110). Pp. 125–130. (In Rus.)
- Petrosov D.A., Ignatenko V.A. Application of Petri information networks for modeling a neural network in the problem of controlling an adapted genetic algorithm in solving problems of structural-parametric synthesis of discrete systems. Successes of Modern Science and Education. 2016. Vol. 5. No. 12. Pp. 138–141. (In Rus.)
- Korolkov A.P., Popov V.V., Kozlov A.A. Using genetic algorithms to build adaptive decision support systems in special software for a unified duty dispatch service based on situational management models. Natural and Man-Made Risks (Physical, Mathematical and Applied Aspects). 2013. No. 4 (8). Pp. 66–74. (In Rus.)
- Petrosov D.A., Petrosova N.V., Feklin V.G. Models of genetic algorithm operators based on the mathematical apparatus of Petri net theory. Science and Business: Development Paths. 2019. No. 7 (97). Pp. 65–68. (In Rus.)
- Petrosov D.A., Petrosova N.V., Feklin V.G. Development of a simulation model of a genetic algorithm based on the mathematical apparatus of Petri net theory. Prospects of Science. 2019. No. 7 (118). Pp. 25–28. (In Rus.)
- Rykov A.D., Davydov V.M. Formation of technological processes based on Petri nets. Scientific Notes of TSU. 2019. Vol. 10. No. 2. Pp. 147–152. (In Rus.)
- Babkin A.N., Akchurina L.V., Alekseenko S.P. Modeling threats of information attacks on the Internet based on Petri nets. Bulletin of the Voronezh Institute of the Ministry of Internal Affairs of Russia. 2023. No. 2. Pp. 101–106. (In Rus.)
- Petrosov D.A. Modeling artificial neural networks using the mathematical apparatus of Petri net theory. Prospects of Science. 2020. No. 12 (135). Pp. 92–95. (In Rus.)
- Bashkin V.A. On the approximation of the resource equivalences in Petri nets with the invisible transitions. Modeling and Analysis of Information Systems. 2020. Vol. 27. No. 2. Pp. 234–253.
- Nesterov R.A., Savelyev S.Yu. Generation of Petri nets using structural property-preserving transformations // Proceedings of the Institute for System Programming of the RAS. 2021. Vol. 33. No. 3. Pp. 155–170.
- Petrosov D.A., Zelenina A.N. Model of an artificial neural network for solving the problem of controlling a genetic algorithm using the mathematical apparatus of Petri net theory. Modeling, Optimization and Information Technology. 2020. No. 4 (31). Pp. 1–12. (In Rus.)
Supplementary files
