New selection operators based on genetic relatedness for evolutionary algorithms
Anca Andreica, Dan Andrei Dumitrescu, Béat Hirsbrunner · 2007
One of the most important decisions that influence the performance of evolutionary algorithms is the way individuals are selected for recombination. Two new selection operators that explore more promising regions of the search space are proposed in order to avoid the search becoming trapped into a local optimum. The first operator is a variant of the proportional selection and the second a variant of the tournament selection - both of them using information about the best ancestor of each individual within the population. In order to prove the efficiency of the proposed operators, several instances of the travelling salesman problem are considered. Experimental results show an acceleration of the search process when using the proposed selection schemes, compared to the most popular existing selection operators. While the first operator performs better only in the first stages of the algorithm, the second outperforms the other selection operators in all its stages.