A fuzzy stop criterion for genetic algorithms using performance estimation

This article presents a new approach for analyzing the solution performance of genetic algorithms (GAs). An adaptive filtering algorithm is combined with a predicting algorithm and memory data from previous GA iterations to estimate the value of the GA´s “optimal” solution. If the current GA iteration value is above a certain user-defined acceptance level, the iteration process is stopped and the GA calculates a belief and uncertainty estimations of the found solution. Results indicate this new approach is preferable to the traditional GA iteration approach, in terms of cost/performance and in decreasing the amount of time the GA searches for acceptable solutions