In recent years, a number of recombination operators have been proposed for multiobjective evolutionary algorithms (MOEAs). One kind of recombination operators is designed based on the Gaussian process model. However, this approach only uses one standard Gaussian process model with fixed variance, which may not work well for solving various multiobjective optimization problems (MOPs). To alleviate this problem, this paper introduces a decomposition-based multiobjective evolutionary optimization with adaptive multiple Gaussian process models, aiming to provide a more effective heuristic search for various MOPs. For selecting a more suitable Gaussian process model, an adaptive selection strategy is designed by using the performance enhancements on a number of decomposed subproblems. In this way, our proposed algorithm owns more search patterns and is able to produce more diversified solutions. The performance of our algorithm is validated when solving some well-known F, UF, and WFG test instances, and the experiments confirm that our algorithm shows some superiorities over six competitive MOEAs.
Decomposition-Based Multiobjective Evolutionary Optimization with Adaptive Multiple Gaussian Process Models
