A model for parallel evolutionary search
A. Gog, Dumitru Dumitrescu · 2005
A parallel search technique for improving evolutionary algorithms is proposed. The method is based on a new philosophy of applying search operators. Two search operators compete for being applied. One is a hybrid operator (recombination plus mutation) and the other is pure mutation operator. The aim of the proposed technique is to maintain a good equilibrium between the exploration and the exploitation of the search space. Experimental results prove that the parallel search outperforms the standard way of applying search operators. A new quality measure for search operators is also proposed.