Article ID: | iaor19952287 |
Country: | United States |
Volume: | 64 |
Issue: | 6 |
Start Page Number: | 399 |
End Page Number: | 406 |
Publication Date: | Jun 1995 |
Journal: | ACM SIGPLAN Notices |
Authors: | Fogel David B. |
Keywords: | metaheuristics |
Evolutionary programming and genetic algorithms are compared on two constrained optimization problems. The constrained problems are redesigned as related unconstrained problems by the appliction of penalty functions. The experiments indicate that evolutionary programming outperforms the genetic algorithm. The results are statistically significant under nonparametric hypothesis testing. The results also indicate potential difficulties in the design of suitable penalty functions for constrained optimization problems. A discussion is offered regarding the suitability of different methods of evolutionary computation for such problems.