A Study of the Combination of Variation Operators in the NSGA-II Algorithm
Multi-objective evolutionary algorithms rely on the use of variation operators as their basic mechanism to carry out the evolutionary process. These operators are usually fixed and applied in the same way during algorithm execution, e.g., the mutation probability in genetic algorithms. This paper analyses whether a more dynamic approach combining different operators with variable application rate along the search process allows to improve the static classical behavior. This way, we explore the combined use of three different operators (simulated binary crossover, differential evolution’s operator, and polynomial mutation) in the NSGA-II algorithm. We have considered two strategies for selecting the operators: random and adaptive. The resulting variants have been tested on a set of 19 complex problems, and our results indicate that both schemes significantly improve the performance of the original NSGA-II algorithm, achieving the random and adaptive variants the best overall results in the bi- and three-objective considered problems, respectively.
KeywordsMultiobjective Optimization Evolutionary Algorithms Variation Operators Adaptation
Unable to display preview. Download preview PDF.
- 2.Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE TEVC 6(2), 182–197 (2002)Google Scholar
- 3.Deb, K., Sinha, A., Kukkonen, S.: Multi-objective test problems, linkages, and evolutionary methodologies. In: GECCO 2006, pp. 1141–1148 (2006)Google Scholar
- 5.Huang, V.L., Qin, A.K., Suganthan, P.N., Tasgetiren, M.F.: Multi-objective optimization based on self-adaptive differential evolution algorithm. In: Proceedings of the 2007 IEEE CEC, pp. 3601–3608 (2007)Google Scholar
- 6.Huang, V.L., Zhao, S.Z., Mallipeddi, R., Suganthan, P.N.: Multi-objective optimization using self-adaptive differential evolution algorithm. In: Proceedings of the 2009 IEEE CEC, pp. 190–194 (2009)Google Scholar
- 7.Iorio, A.W., Li, X.: Solving rotated multi-objective optimization problems using differential evolution. In: Australian Conference on Artificial Intelligence, pp. 861–872 (2004)Google Scholar
- 8.Knowles, J., Thiele, L., Zitzler, E.: A Tutorial on the Performance Assessment of Stochastic Multiobjective Optimizers. Technical Report 214, Computer Engineering and Networks Laboratory (TIK), ETH Zurich (2006)Google Scholar
- 9.Li, H., Zhang, Q.: Multiobjective optimization problems with complicated pareto sets, MOEA/D and NSGA-II. IEEE TEVC 2(12), 284–302 (2009)Google Scholar
- 10.Toscano Pulido, G., Coello Coello, C.A.: The micro genetic algorithm 2: Towards online adaptation in evolutionary multiobjective optimization. In: Fonseca, C.M., Fleming, P.J., Zitzler, E., Deb, K., Thiele, L. (eds.) EMO 2003. LNCS, vol. 2632, pp. 252–266. Springer, Heidelberg (2003)CrossRefGoogle Scholar
- 12.Zhang, Q., Suganthan, P.N.: Special session on performance assessment of multiobjective optimization algorithms/cec 09 moea competition (May 2009)Google Scholar
- 13.Zhang, Q., Zou, A., Zhao, S., Suganthan, P.N., Liu, W., Tivari, S.: Multiobjective optimization test instances for the cec 2009 special session and competition. Technical Report CES-491, School of CS & EE, University of Essex (April 2009)Google Scholar
- 14.Zitzler, E., Thiele, L.: Multiobjective evolutionary algorithms: a comparative case study and the strength pareto approach. IEEE TEVC 3(4), 257–271 (1999)Google Scholar