An Approach for Generating Test Problems of Constrained Global Optimization

In the present paper, a novel approach to the constructing of the test global optimization problems with non-convex constraints is considered. The proposed approach is featured by a capability to construct the sets of such problems for carrying out multiple computational experiments in order to obtain a reliable evaluation of the efficiency of the optimization algorithms. When generating the test problems, the necessary number of constraints and desired fraction of the feasible domain relative to the whole global search domain can be specified. The locations of the global minimizers in the generated problems are known a priori that simplifies the evaluation of the results of the computational experiments essentially. A demonstration of the developed approach in the application to well-known index method for solving complex multiextremal optimization problems with non-convex constraints is presented.