Adaptive strategies for Evolutionary Algorithm monitoring

摘要: Parameter tuning in Evolutionary Algorithms (EA), is a great obstacle that can become the key to success. Good parameter settings yield optimal solutions, while bad may trap EA, thus removing chances of finding solutions. Therefore, it vital an set parameters configuration chosen. It common practice have human expert analyzes such and modifies them accordingly. Such process inefficient expensive, since requires time subject fatigue; even becomes impractical if environment dynamic. This work proposes 2 adaptive strategies tune parameters: One Step Variation Fuzzy Logic Controller. A ranking scheme modeling introduced evaluate strategies. Results show be possible EA for achieving better results, without need expert.