surrogate-assisted multi-objective evolutionaryalgorithms have become increasingly popular for solving computationally expensive problems, profiting from surrogate modeling and infill approaches to reduce the time co...
详细信息
surrogate-assisted multi-objective evolutionaryalgorithms have become increasingly popular for solving computationally expensive problems, profiting from surrogate modeling and infill approaches to reduce the time cost of optimization. Most existing algorithms have specified the type of surrogate model before a run and keep the type static during the optimization process. However, a sole surrogate model may not consistently perform well for all problems without any prior knowledge. In this context, this paper proposes an adaptive technique for surrogate models with multiple radial basis functions (RBFs), as the technique can dynamically establish the most promising RBF for each objective, thereby enhancing the reliability of surrogate prediction. Moreover, multi -objective evolutionaryalgorithms (MOEAs) that are employed as optimizers for infilling criteria can highly affect the search behavior of a surrogate-assistedevolutionaryalgorithm. The proposed infill technique develops a crowding distance-based prescreening operator to embed various MOEAs. Two techniques collaboratively promote the convergence, coverage, and diversity of the predicted Pareto front. Representative benchmark problems and a structural optimization problem are given to show the effectiveness of the algorithm that em-ploys these techniques. Empirical experiments demonstrate that the proposed algorithm significantly out-performs other state-of-the-art algorithms in most cases.
Simulation technique is an increasingly focused method for conveniently evaluating a solution or scenario in the field of groundwater. However, traditional evolutionaryalgorithms require at least thousands of simulat...
详细信息
Simulation technique is an increasingly focused method for conveniently evaluating a solution or scenario in the field of groundwater. However, traditional evolutionaryalgorithms require at least thousands of simulation executions when addressing groundwater simulation-based optimization problems to find reasonable solutions. Intensive simulations usually yield a prohibitive computational burden if the simulation involved is time-consuming. To defeat the issue, this paper proposes a multiobjective ensemble surrogate-based optimization algorithm named MESOA for groundwater optimization designs. surrogate models can reduce the continual usage of expensive-cost models in a way that approximates objective functions. Unlike existing surrogate-assistedevolutionaryalgorithms, MESOA employs surrogates with various basis functions (RBFs) and Kriging as available surrogates, and presents an adaptive switching technique to construct surrogate models in an online way. In addition, MESOA involves three sample infill criteria and a novel population filter. With the assistance of these techniques, MESOA can fully depict the outline of the true Pareto front, although the times of invoking simu-lation are limited. Some representative benchmark cases are provided to test the applicability and effectiveness of the proposed algorithm at first. Afterward, MESOA is applied to solve some practical groundwater multi -objective optimization designs, such as groundwater remediation and requirement optimization. All empirical results indicate that the proposed algorithm obtains more availability and effectiveness than other algorithms and has wide universality for groundwater optimization designs.
暂无评论