Statistical Analysis of the Performance of Modified Genetic Algorithms for Automated Compilation of a Multilevel University Scheduling

The construction of a class schedule of an educational institution and, especially, a multilevel higher education institution, combining in its organizational and pedagogical structures several levels of education, including professional, secondary vocational and higher education, as well as training of scientific and pedagogical staff of higher qualification, is a time-consuming task. The study considers a computerized approach to the process of building a model of its optimization. The study uses the methods of system analysis and modification of genetic algorithms (GA), substantiates the structure of initial data for the task of compiling and optimizing training schedules using the method of penalty functions to account for resource and other constraints. A statistical approach is proposed, and a statistics collection and visualization module is implemented, which allows for the operative correction of hyperparameters and the mathematical model of the GA. The examples are provided to illustrate the problem of creating schedules for a multilevel university using GA. The developed computer program provides the creating of the schedule of academic classes of a multilevel university, effective according to the integral quality criterion substantiated taking into account the limitations.