Use of artificial intelligence models to check requirements for functional stability of information systems

DOI: 10.31673/2409-7292.2024.030002

Abstract

Active informatization of society requires increasingly active use of information systems. With the growing need to use them to solve certain problems, the requirements for information systems on the one hand, and their sizes on the other, also grow. It is obvious that functional stability occupies an increasingly significant place in the operation of information systems. As a result, the most diverse ways to characterize and provide it physically are being developed. As a result, a number of indicators and criteria for the functional stability of systems have already been developed, as well as requirements for the organization of the system itself. The purpose of all this is to make the information systems used as functionally stable as possible. Despite the development of new indicators and criteria of functional stability and requirements, the fulfillment of which ensures functional stability, at the moment they all have a very significant drawback: they are quite difficult to implement technically. As a result, as information systems grow in size or degrade, it becomes increasingly difficult to assess whether they are functionally sustainable or not. As a result, there is a need to optimize already developed assessment methods and ensure functional stability. Recently, interest in the use of machine learning models has increased, including for the optimization of calculations. Recent studies show that machine learning models in some cases cope with this task quite successfully. Therefore, the question of their application in the study of functional stability of information systems is logical. This work investigates the application of several machine learning models to optimize the verification of the fulfillment of the condition, the fulfillment of which ensures the functional stability of the information system under consideration.

Keywords: information systems, machine learning, artificial intelligence, neural networks, decision trees, network technologies.