Balancing the computation effort in genetic algorithms

It is usually difficult to find a balance among some of the important parameters when using an evolutionary algorithm (EA) (number of runs, population size and generations) and at the same time saving computing time. Recently, some papers have dealt with population size and optimal numbers of populations, while others have instead focused on a different couple of parameters, and scarcely the three parameters have been considered simultaneously. In this paper we consider simultaneously all of them. Computing effort is used through experimental results section to evaluate the proposed alternatives. Experimental results confirm some conclusions obtained on previous works with only two parameters and also give some guidelines on the way of distributing efficiently resources when designing parallel implementations of EAs.