Cross-Entropy Approach for Computing a Pareto Fronts

Author

Sebaa, Karim

Author_Institution

Lab. de Rech. en Electrotech. et Autom., Univ. of Dr Yahia Fares, Medea, Algeria

fYear

2013

fDate

10-12 April 2013

Firstpage

61

Lastpage

66

Abstract

We propose in this paper an approach based on the cross-entropy method for computing Pareto Fronts. The approach is based on the cross-entropy approach for single-objective optimization. It is adapted to multi-objective optimization by defining a sorting criterion for selecting the best samples based on non-dominated sorting. The effectiveness of the approach is tested on several academic problems (e.g. Schaffer, Fonseca and Fleming). Its performances are compared with those of other multi-objective algorithm.

Keywords

Pareto optimisation; entropy; sorting; Pareto front computing; academic problem; cross-entropy approach; multiobjective algorithm; multiobjective optimization; nondominated sorting; single-objective optimization; sorting criterion; Computational modeling; Linear programming; Measurement; Monte Carlo methods; Optimization; Probability density function; Sorting; NSCE-I;Cross-Entropy; Non dominated Sorting; Rare Event Simulation (RES); Pareto-optimal solutions;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Modelling and Simulation (UKSim), 2013 UKSim 15th International Conference on

Conference_Location

Cambridge

Print_ISBN

978-1-4673-6421-8

Type

conf

DOI

10.1109/UKSim.2013.117

Filename

6527391