Evolutionary approach to multi-objective problems using adaptive genetic algorithms

Bingul Z. , Sekmen A., Zein-Sabatto S.

IEEE International Conference on Systems, Man and Cybernetics, Tennessee, United States Of America, 8 - 11 October 2000, pp.1923-1927 identifier

  • Publication Type: Conference Paper / Full Text
  • City: Tennessee
  • Country: United States Of America
  • Page Numbers: pp.1923-1927


This paper describes an adaptive genetic algorithm used to achieve multi-objectives such as minimizing the territory loses and maximizing enemy air loses by finding the optimum distribution of air-crafts fighting in a war scenario simulated by the THUNDER software. The adaptive genetic algorithm developed in this research changes the mutation and crossover rates adaptively to provide a fast convergence to the optimum possible solutions. According the population of the fitness values obtained for each generation, three distribution properties (the mean, the variance and the best fitness value) are determined and used as input to a fuzzy-logic system for modifying the mutation and crossover rates to obtain the individuals of the next generation. This enables maintaining a fast and smooth convergence to the best possible solutions.