Metamodeling Techniques For Evolutionary Optimization of Computationally Expensive Problems: Promises and Limitations

It is often the case in many problems in science and engineering that the analysis codes used are computationally very expensive. This can pose a serious impediment to the successful application of evolutionary optimization techniques. Metamodeling techniques present an enabling methodology for reducing the computational cost of such optimization problems. We present here a general framework for coupling metamodeling techniques with evolutionary algorithms to reduce the computational burden of solving this class of optimization problems. This framework aims to balance the concerns of optimization with that of design of experiments. Experiments on test problems and a practical engineering design problem serve to illustrate our arguments. The practical limitations of this approach are also outlined.