METHOD FOR ASSESSING AND FORECASTING THE DEPENDABILITY STATE OF CRITICAL INFRASTRUCTURE OBJECTS

Abstract

This paper addresses the problem of assessing and forecasting the dependability state of critical infrastructure objects under conditions of increasing cyber threats, technical failures, and destabilizing influences. The relevance of the study is determined by the need to ensure the continuity of operation of critical systems through the timely identification of trends indicating deterioration of their condition and the formation of well-grounded management decisions. The aim of the study is to develop a method for assessing and forecasting the dependability of critical infrastructure objects using intelligent decision-support technologies. A method is proposed that combines procedures for collecting and analyzing monitoring data, risk assessment, the formation of an integrated dependability indicator, and forecasting its changes over time. A mathematical model for dependability assessment based on a set of cybersecurity, reliability, availability, survivability, and recoverability indicators of the object has been developed. The decision-support approach has been improved through the use of an intelligent technology that integrates assessment of the current dependability state, forecasting of its changes, and the application of a machine learning model for the early detection of critical states and the selection of the most appropriate response measures. An algorithm for identifying critical states of a critical infrastructure object and generating recommendations for improving its dependability level has been developed. To validate the effectiveness of the proposed approach, simulation experiments were conducted for four operational scenarios of a critical infrastructure object. The obtained results demonstrated an increase in dependability forecasting accuracy to 92.4%, a reduction in the average time required for management decision-making by 31.7%, and a decrease in the integrated risk level by 28.5% compared to traditional approaches. It was established that the use of intelligent decision-support technologies ensures the timely detection of potentially dangerous trends and improves the justification of response measure selection. The practical value of the study lies in the possibility of applying the proposed method in situation centers and information-analytical management systems for critical infrastructure objects.

Keywords: dependability; critical infrastructure objects; decision support; intelligent technologies; state forecasting; risk assessment; situation center; cybersecurity; information and analytical system; monitoring.