Sequential approximate optimization in the problem solving environment WBCSim

This paper presents a data driven, surrogate based optimization algorithm that uses a sequential approximate optimization (SAO) framework and a statistical sampling approach. The biggest concern in using the SAO framework based on statistical sampling is the generation of the required database. A data driven approach is proposed to tackle this situation, where the trick is to run the expensive simulation if and only if a nearby data point does not exist in the cumulatively growing database. Results show that the proposed methodology dramatically reduces the total number of calls to the expensive simulation runs during the optimization process. Utilizing parallel or distributed computing for generating the required database can further reduce the optimization time, as can a high performance parallel computing back-end for each single simulation run.