In many real-world problems there is often the requirement to optimise multiple conflicting objectives in an efficient manner. In such problems there can be the requirement to optimise a mixture of continuous and discrete variables. Herein, we propose a new multi-objective algorithm capable of optimising both continuous and discrete bounded variables in an efficient manner. The algorithm utilises Gaussian processes as surrogates in combination with a novel distance metric based upon Gower similarity. The MVMOO algorithm was compared to an existing mixed variable implementation of NSGA-II and random sampling for three test problems. MVMOO shows competitive performance on all proposed problems with efficient data acquisition and approximation of the Pareto fronts for the selected test problems.

在许多实际问题中，通常需要以有效的方式优化多个相互冲突的目标。在此类问题中，可能需要优化连续变量和离散变量的混合。在这里，我们提出了一种新的多目标算法，能够以有效的方式优化连续和离散有界变量。该算法利用高斯过程作为替代，结合基于高尔相似度的新距离度量。MVMOO 算法与 NSGA-II 的现有混合变量实现和三个测试问题的随机抽样进行了比较。MVMOO 在所有提出的问题上表现出具有竞争力的性能，具有高效的数据采集和对所选测试问题的帕累托前沿的逼近。