COMBINING MODEL-BASED AND GENETICS-BASED OFFSPRING GENERATION FOR MULTI-OBJECTIVE OPTIMIZATION USING CONVERGENCE CRITERION

摘要

PPROBLEM TO BE SOLVED: To provide a new population-based algorithm for solving a multi-objective optimization problem. PSOLUTION: In a method for multi-objective optimization (MOO), a computer executes the following steps for: providing an initial population of solutions (310); partitioning the population into a number of clusters (320); calculating a convergence ratio () for each cluster (330); checking whether the convergence ratio () is larger than a given threshold (340); generating a model composed of a deterministic part and a stochastic part and generating an offspring by sampling the model (350) when the convergence ratio () is smaller than or equal to the given threshold (), and generating the offspring using mutation and crossover in other cases (360); merging parents and the offspring (370); and creating a new parent population using a Pareto-based selection method (370). PCOPYRIGHT: (C)2007,JPO&INPIT