Identification of the type of distribution and its application in assessing the functioning of complex systems based on Bayesian intelligent technologies

Zhukov R.A., Prachev A.D., Lamzina E.A.

This study presents a methodology for assessing the functioning of complex systems, taking into account the type of distribution of indicators characterizing the functioning of structural elements of such a system operating under conditions of uncertainty. Unlike previous studies, the work integrates the identification of the type of indicator distribution with their Bayesian assessment, taking into account the norms characterizing the required results of the functioning of the structural elements of the system. The type of distribution and its characteristics provide more complete information about the properties of an object and their consideration affects the results of evaluating the functioning of elements of complex systems, especially in cases of the presence of “heavy” tails characteristic of a number of socio-economic processes and systems. It is shown that it is advisable to identify the type of distribution based on modified data due to the exclusion of the best trend in statistical characteristics. The determination of the best type of distribution is carried out according to the Kolmogorov – Smirnov agreement criterion, which showed the best (according to the available sample) statistical estimates compared to other criteria or a mixture of them. The obtained type of distribution is used in the probabilistic assessment of the results of the functioning of subsystem elements based on Bayesian intelligent technologies that successfully operate in conditions of uncertainty, and which make it possible to present such results on numerical and linguistic scales in a general hierarchical information model. The methodology was tested using the example of the object subsystem (G.B.Kleiner’s spatio-temporal classification) of the economic subsystem of the Tula region, considered as a complex system — a socio-ecological-economic system. The volume of gross domestic product by region in six sections of the all-Russian classifier of economic activities (sections A, B, C, D, E) was used as assessment indicators. In some cases, it is possible to reduce the level of uncertainty in the estimates of indicators.; to obtain estimates that are more stringent than the norm, which ultimately leads to the conclusion that the use of the distribution type in the formation of probabilistic estimates of indicators of structural elements of complex systems makes it possible to justify their correct application within the framework of the concept of evidence-based modeling.

Keywords: distribution type, sampling, trend, model, Bayesian intelligent technologies
Citation in English: Zhukov R.A., Prachev A.D., Lamzina E.A. Identification of the type of distribution and its application in assessing the functioning of complex systems based on Bayesian intelligent technologies // Computer Research and Modeling, 2026, vol. 18, no. 4, pp. 1021-1034
Citation in English: Zhukov R.A., Prachev A.D., Lamzina E.A. Identification of the type of distribution and its application in assessing the functioning of complex systems based on Bayesian intelligent technologies // Computer Research and Modeling, 2026, vol. 18, no. 4, pp. 1021-1034
DOI: 10.20537/2076-7633-2026-18-4-1021-1034
URL: http://crm-en.ics.org.ru/journal/article/3757/
Creative Commons License This work is licensed under a Creative Commons Attribution-NoDerivs 3.0 Unported License.

Copyright © 2026 Zhukov R.A., Prachev A.D., Lamzina E.A.

Indexed in Scopus

Full-text version of the journal is also available on the web site of the scientific electronic library eLIBRARY.RU

The journal is included in the Russian Science Citation Index

The journal is included in the RSCI

International Interdisciplinary Conference "Mathematics. Computing. Education"

Website Copyright © 2009–2026 Institute of Computer Science