Group-based differential evolution for numerical optimization problems
MF Han, Chin‐Teng Lin, Jy Chang, DL Li · 2013
Abstract. This paper proposes a group-based differential evolution (GDE) algorithm for numerical optimization problems. The proposed GDE algorithm provides a new pro-cess using two mutation strategies to effectively enhance the search for the globally optimal solution. Initially, all individuals in the population are partitioned into an elite group and an inferior group based on their tness value. In the elite group, individuals with a better tness value employ the local mutation operation to search for better solutions near the current best individual. The inferior group, which is composed of individuals with worse tness values, uses a global mutation operation to search for potential solu-tions and to increase the diversity of the population. Subsequently, the GDE algorithm employs crossover and selection operations to produce offspring for the next generation. This paper also proposes two parameter-tuning strategies for the robustness of the GDE algorithm in the evolution process. To validate the performance of the GDE algorithm, 13 well-known numerical benchmark functions were tested on low- and high-dimensional problems. The simulation results indicate that our approach is efficient.