Artificial Neural Network Metamodels of Stochastic Computer Simulations
Final rept. 25 Jun 1990-10 Aug 1994
PITTSBURGH UNIV PA DEPT OF INDUSTRIAL ENGINEERING
Pagination or Media Count:
A computer simulation model can be thought of as a relation that connects input parameters to output measures. Since these models can become computationally expensive in terms of processing time andor memory requirements, there are many reasons why it would be beneficial to be able to approximate these models in a computationally expedient manner. This research examines the use of artificial neural networks ANN, to develop a metamodel of computer simulations. The development and use of the Baseline ANN Metamodel Approach is provided and is shown to outperform traditional regression approaches. The results provide a solid foundation and methodological direction for developing ANN metamodels to perform complex tasks such as simulation optimization, sensitivity analysis, and simulation aggregationreduction. Artificial Neural Networks, Computer Simulation Metamodel, Regression, Response Surface Methods, Simulation Optimization.
- Computer Programming and Software