MULTI-OBJECTIVE OPTIMIZATION USING PARALLEL COMPUTATIONS

Applied optimization in process design or optimal control frequently is a multi-criteria problem. There are several approaches to the solution of multi-criteria problems, but the main approach is oriented to construct the Pareto set of the considered problem. In case of nonlinear models this problem is difficult especially if the objective functions are multimodal. Therefore application of parallel methods to solution of this problem is urgent. In the present paper efficiency of several evolutionary algorithms is compared taking into account their parallelization using multi-start model and implementation perspectives on computational grids.