On Uncertainty and Robustness in Evolutionary Optimization-Based MCDM

  • Authors:

  • Daniel E. Salazar Aponte;Claudio M. Rocco S.;Blas Galván

  • Affiliations:

  • Institute SIANI, Edif. Central Pqe. Científico y Tecnológico, University of Las Palmas de Gran Canaria, Las Palmas, Spain 35017;Faculty of Engineering, Central University of Venezuela, Los Chaguaramos. Caracas, Venezuela;Institute SIANI, Edif. Central Pqe. Científico y Tecnológico, University of Las Palmas de Gran Canaria, Las Palmas, Spain 35017

  • Venue:
  • EMO '09 Proceedings of the 5th International Conference on Evolutionary Multi-Criterion Optimization
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this article we present a methodological framework entitled `Analysis of Uncertainty and Robustness in Evolutionary Optimization' or AUREO for short. This methodology was developed as a diagnosis tool to analyze the characteristics of the decision-making problems to be solved with Multi-Objective Evolutionary Algorithms (MOEA) in order to: 1) determine the mathematical program that represents best the current problem in terms of the available information, and 2) to help the design or adaptation of the MOEA meant to solve the mathematical program. Regarding the first point, the different versions of decision-making problems in the presence of uncertainty are reduced to a few classes, while for the second point possible configurations of MOEA are suggested in terms of the type of uncertainty and the theory used to represent it. Finally, the AUREO has been introduced and tested successfully in different applications in [1].