Parallel Enhanced Hybrid Evolutionary Algorithm for Continuous Function Optimization

Efficient algorithms include the one that finds high quality solutions, with reasonable computational speed. This paper presents an adaptation to a parallel computer architecture based on estimation of distribution and genetic algorithms (EDAs and GAs) hybridization. In this master-slave topology, the master selects portions of the search space, and slaves perform, in parallel and independently, a GA that solves the problem on the portion of the search space they have been assigned. The master´s work is divided into 4 phases which progressively narrow the areas explored by the slave´s GAs, using parallel dynamic K-means clustering to determine the basins of attraction of the search space.. The improvement of solution quality and comparative reduction in computation time reveal the effectiveness of our proposed algorithm.