Abstract
A novel approach based on three differential evolution variants to solve numerical constrained optimization problems is presented. Each variant competes to get more vectors for reproduction from the population. Such competition is based on two performance measures for convergence and solution improvement. Two of the variants adopted in this work were precisely proposed to deal with constrained search spaces. Two experiments are carried out: one to analyze the behavior of each variant with respect to the features of the problem solved and another to compare the performance of the proposed approach with respect to state-of-the-art multi-operator algorithms. The results obtained show that the specialized variants are more useful in the search, either combined or just using one of them. Finally, the final results of the proposed approach were highly competitive, and better in some cases, with respect to those of the algorithms used in the comparison.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Eiben, A., Smith, J.E.: Introduction to Evolutionary Computing. Springer (2003)
Mezura-Montes, E., Coello Coello, C.A.: Constraint-Handling in Nature-Inspired Numerical Optimization – Past, Present and Future. Swarm and Evolutionary Computation 1(4), 173–194 (2011)
Wolpert, D.H., Macready, W.G.: No Free Lunch Theorems for Optimization. IEEE Transactions on Evolutionary Computation 1(1), 67–82 (1997)
Mallipeddi, R., Suganthan, P., Pan, Q., Tasgetiren, M.: Differential Evolution Algorithm with Ensemble of Parameters and Mutation Strategies. Applied Soft Computing 11(2), 1679–1696 (2011)
Wang, Y., Cai, Z., Zhang, Q.: Differential Evolution with Composite Trial Vector Generation Strategies and Control Parameters. IEEE Transactions Evolutionary Computation 15(1), 55–66 (2011)
Elsayed, S.M., Sarker, R.A., Essam, D.L.: Multi-Operator Based Evolutionary Algorithms for Solving Constrained Optimization Problems. Computers and Operations Research 38(12), 1877–1896 (2011)
Price, K., Storn, R., Lampinen, J.: Differential Evolution – A Practical Approach to Global Optimization. Springer (2005)
Mezura-Montes, E., Velázquez-Reyes, J., Coello Coello, C.A.: Modified Differential Evolution for Constrained Optimization. In: 2006 IEEE Congress on Evolutionary Computation (CEC 2006), pp. 332–339. IEEE Press (2006)
Youyun, A., Hongqin, C.: An Adaptive Differential Evolution Algorithm to Solve Constrained Optimization Problems in Engineering Design. Engineering 2(1), 65–77 (2010)
Feoktistov, V.: Differential Evolution – In Search of Solutions. Springer (2006)
Mezura-Montes, E., Coello, C.A.C.: Identifying On-line Behavior and Some Sources of Difficulty in Two Competitive Approaches for Constrained Optimization. In: IEEE Congress on Evolutionary Computation (CEC 2005), vol. 2, pp. 1477–1484. IEEE Press (2005)
Deb, K.: An Efficient Constraint Handling Method for Genetic Algorithms. Computer Methods in Applied Mechanics and Engineering 186(2), 311–338 (2000)
Rao, R.V., Patel, V.: An Elitist Teaching-Learning-Based Optimization Algorithm for Solving Complex Constrained Optimization Problems. International Journal of Industrial Engineering Computations 3, 535–560 (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gordián-Rivera, LA., Mezura-Montes, E. (2012). A Combination of Specialized Differential Evolution Variants for Constrained Optimization. In: Pavón, J., Duque-Méndez, N.D., Fuentes-Fernández, R. (eds) Advances in Artificial Intelligence – IBERAMIA 2012. IBERAMIA 2012. Lecture Notes in Computer Science(), vol 7637. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34654-5_27
Download citation
DOI: https://doi.org/10.1007/978-3-642-34654-5_27
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-34653-8
Online ISBN: 978-3-642-34654-5
eBook Packages: Computer ScienceComputer Science (R0)