Hybrid simulation models for complex decision-making problems with partial uncertainty

Abstract

Specific features of application of hybrid simulation and control models in information systems and system support for decision-making in solving practical problems under conditions of uncertainty, vagueness, inaccuracy, stochasticity of processes of subject areas are considered. To obtain reliable data, it is necessary to use poorly formalized operational and long-term data on the state of the object of control, expert knowledge, application of mathematical programming methods with stochastic or fuzzy constraints, as well as many cause-and-effect relations between processes that may be presented in the form of production rules: “condition–action”. Based on research and analysis of complex decision-making problems using hybrid simulation-control models in conditions of partial uncertainty, an estimate of their complexity in terms of practical implementations, which did not exceed the quadratic dependence on the number of operations is obtained. The peculiarities of their use in real developments are determined, which allowed us to increase the reliability of decisions in information systems, to reduce development time to 12% in the conditions of fuzzy, stochastic character of researched processes of real objects. The results that confirm their effective use in solving practical problems: an example of solving situational analysis using hybrid simulation-control models in the information-analytical decision support system, are presented.