Using Empirical Knowledge for Adaptive Selection of Reduplicate Simulation Times in Simulation Optimization

Simulation optimization studies the optimization problem of simulation-based objectives in the foundation of mature modern optimization theory system. In order to improve the disadvantages of current selection of reduplicate simulation times in simulation optimization, this paper presents an adaptive selection of reduplicate simulation times in simulation optimization by using empirical knowledge. The method is based on the empirical knowledge from simulation optimization practice. Empirical knowledge from simulation optimization studies is an important source for the creation of accurate simulation models. This paper focuses on the use of empirical knowledge for the development and calibration of simulation models. At first, the author summarizes some empirical knowledge from simulation optimization studies. At second, the author describes the method of this paper in detail. The method of this paper mainly consists of three steps: complexity estimation to the optimization problem, classified operation of trial point and adaptive selection of the reduplicate simulation times. At third, the author uses two numerical examples to testify the validity of this method. From the computing result of numerical examples, we can see that, through the adaptive selection of reduplicate simulation times to the different trial points, the computing time is decreasing and the global optimization solution is improving in the given computing precision. In conclusion, the method of this paper is feasible, correct and valid. Finally, the conclusions of this study are drawn with possible directions for subsequent studies.