Dynamic Regression Model for Predicting Emergency Situations Radio Electronic Equipment to Improve the Efficiency of Accident Resolution

The relevance of the study is due to the need to predict emergency situations at critical infrastructure facilities (CIF) to optimize repair planning and improve the sustainable operation of radio electronic equipment (REE). A dynamic model with recursion has been developed to predict emergency situations and improve the efficiency of emergency response at CIF. Improving the efficiency of response and emergency response in the decision support system (DSS) is achieved due to the fact that the model dynamically adjusts forecasts of the number of REE failures upon receipt of new data on failures. As a result, an original mathematical model based on the k-median method, clustering and probabilistic simulation modeling has been proposed, using recursion to increase the forecast horizon for equipment failures within the framework of long-term planning. In order to increase the accuracy of the forecast, the model takes into account the timely (dynamic) failure of REE at the forecasting stage itself. The practical significance lies in the possibility of forming an operational decision support system for dispatchers of situation centers based on the developed model. The implementation of this model into the system will allow dispatchers to quickly make decisions about the redistribution of resources and the timely dispatch of repair teams.