Multi-objective optimization with Proper Orthogonal Decomposition and Gaussian predictive distribution

A numerical study of multi-objective optimization with Proper Orthogonal Decomposition (POD) and Gaussian predictive distribution on the well known ZDT and DLZT benchmark set, is presented and discussed. Based on the algorithm, design optimization of the Global Trajectory Optimization Problems (GTOP) database based on trajectory models of real-world interplanetary space mission, Cassini is presented. The trajectory models are formulated as nonlinear optimization problems and are known to be difficult to solve. In this contribution, for part of the standard ZDT and DTLZ series problems, the proposed algorithm is able to solve these benchmarks to their optimal solutions within 20 generations.