Author: Jingbo Su
North China University of Technology
Meta-heuristic algorithms have gained remarkable success in solving complex and large-scale problems. However, as the dimension of the problem increases, their elaborate implementations may lead to lower convergence speed and struggle with local optima easily. In this paper, a parallel Gannet Optimization Algorithm (GOA) with two novel communication strategies is proposed, and comparisons with the original GOA on 13 100-dimension benchmark functions are committed. Comprehensive experimental results indicate that the improved algorithm outperforms the original algorithm in not only better escaping local optima but also shorter running time.
Gannet Optimization Algorithm, Parallel, Communication Strategies.