Comparison of the efficiency of the random forest algorithm and artificial neural networks of the RNN class in the problem of managing the process of structural-parametric synthesis of business process models based on a genetic algorithm

The results presented in this study are relevant for solving the problem of increasing the efficiency of the genetic algorithm in problems related to the use of big data. In the framework of most existing approaches to the application of the evolutionary procedure, efficiency improvement methods are used that are based on classical approaches aimed at pre-setting the operating parameters of the genetic algorithm operators in a specific subject area. At the same time, when working with big data, there is a need to stop and restart the genetic algorithm to obtain the best solutions, since the population of the evolutionary algorithm can be in local extremes and / or the efficiency of the increase in the quality of individuals does not allow finding the required solution in a given time interval. In this case, it becomes relevant to develop new methods that allow you to manage the search process. One of the approaches to solving this problem is the use of the mathematical apparatus of artificial neural networks of the RNN class, which have proven their effectiveness in solving the classification problem and can be used to identify the state of the population of the genetic algorithm. In addition to the approach based on the use of artificial neural networks, it is relevant to assess the possibility of using the "random forest" algorithm to solve the problem of recognizing the state of a population and making decisions on changing the operating parameters of the genetic algorithm operators directly in the process of work, which will allow influencing the trajectory of the population in the solution space. Within the framework of this article, the results of computational experiments on solving the problem of classifying the state of a population of a genetic algorithm by two modern methods will be considered: the "random forest" algorithm and the artificial neural network RNN, the modeling of which is performed using a graph approach based on the theory of Petri nets, which will allow combining the developed models with the model of a genetic algorithm adapted to solving the problem of structural-parametric synthesis using nested Petri nets.

1. Bova V.V., Leshchanov D.V. Modified algorithm for searching regularities in large dimensional data based on genetic optimization. Informatization and communication. 2021;(3):67–72. (In Russ.). https://doi.org/10.34219/2078-8320-2021-12-3-67-72

2. Polukhin P.V. Application of genetic algorithms to optimize solution of filtering and prediction problems in dynamic program testing systems. Yugra State University Bulletin. 2022;(4):120–132. (In Russ.). https://doi.org/10.18822/byusu202204120-132

3. Utkin L., Konstantinov A. Random Survival Forests Incorporated by the Nadaraya-Watson Regression. Informatics and Automation. 2022;21(5):851–880. https://doi.org/10.15622/ia.21.5.1

4. Yifter T.T., Razoumny Y.N., Orlovsky A.V., Lobanov V.K. Monitoring the spread of Sosnowskyi’s hogweed using a random forest machine learning algorithm in Google Earth Engine. Computer Research and Modeling. 2022;14(6):1357–1370. https://doi.org/10.20537/2076-7633-2022-14-6-1357-1370

5. Lomakin N.I., Maramygin M.S., Polozhentsev A.A., Shabanov N.T., Naumova S.A., Starovoitov M.K. RF Deep Learning Model "Random Forest" for Forecasting Organizational Profit in the Digital Economy. The World Economics. 2023;(11):824–839. (In Russ.). https://doi.org/10.33920/vne-04-2311-06

6. Kharakhinov V.A., Sosinskaya S.S. The use of Petri nets for the software product design to analyze data using neural networks. Science Bulletin of the Novosibirsk State Technical University. 2018;(4):91–100. (In Russ.). https://doi.org/10.17212/1814-1196-2018-4-91-100

7. Tronin V.G., Stetsko A.A. Modelirovanie servera i rabochei stantsii vychislitel'noi seti s pomoshch'yu raskrashennykh setei Petri. Software & Systems. 2008;(3):95–97. (In Russ.).

8. Petrosov D.A. Modeling of artificial neural networks using the mathematical apparatus of Petri nets theory. Science Prospects. 2020;(12):92–95. (In Russ.).

9. Petrosov D.A., Koroteev M.V., Andriyanov N.A., Kosarev V.E. Intellektual'nyi strukturno-parametricheskii sintez imitatsionnykh modelei i biznes-protsessov. Moscow: OOO "Rusains"; 2024. 100 p. (In Russ.).

10. Makarov V.I. Optimization of the Genetic Algorithm using Parallel Computing. Software Engineering. 2023;14(8):401–406. (In Russ.). https://doi.org/10.17587/prin.14.401-406