Evaluation of the efficiency of the problem of choosing the extreme values of the parameters of the parametric family of regenerating processes

Thus, the formal formulation of the problem of evaluating the effectiveness of search optimization procedures on simulation models of regenerating processes under strict time constraints has been completed. A procedure for parametric tuning of the optimization algorithm has been developed, which sequentially refines the values of the functional specified by the model and redistributes the remaining model regeneration cycles between the investigated values of the controlled parameter. The problem of maximizing the probability of the correct choice is posed and solved, i.e. selection, according to the results of the simulation experiment on the model of the regenerating process, of the value of the controlled parameter that delivers the true maximum to the investigated functional. Based on the transition to the Lagrangian, the solution to the constrained optimization problem is reduced to an unconstrained optimization problem. Analytical expressions are obtained to assess the optimal distribution of regeneration cycles. It is shown that the simulation model with the included search engine optimization algorithm provides solutions that are quite effective in terms of computational costs. As a result, a method is proposed for a simple extension of the developed simulation models by including a search optimization algorithm, which makes it possible to move from modeling the system to optimizing its objective function on a given area of controlled parameters.