Adaptive Neighborhoods for Cellular Genetic Algorithms

Cellular genetic algorithms (cGAs) are a kind of genetic algorithms (GAs) with decentralized population in which interactions among individuals are restricted to close ones. The use of decentralized populations in GAs allows to keep the population diversity for longer, usually resulting in a better exploration of the search space and, therefore in a better performance of the algorithm. However, the use of decentralized populations supposes the need of several new parameters that have a major impact on the behavior of the algorithm. In the case of cGAs, these parameters are the population and neighborhood shapes. Hence, we propose in this work two new adaptive techniques that allow removing the neighborhood to use from the algorithm´s configuration. As a result, one of the new adaptive cGAs outperform the compared cGAs with fixed neighborhoods in the continuous and combinatorial domains.