Performance Improvement of Krill Herd Algorithm Using Asynchronous Structure and Effect of Best Positions
Paper ID : 1122-ICTCK (R1)
1مصطفی مشکات *, 2مهدی یعقوبی
1Department of Artificial Intelligence, Mashhad Branch, Islamic Azad University, Mashhad, Iran
2کمیته علمی
The Krill Herd (KH) algorithm was inspired by the hunting behavior of the krill for finding solutions to optimization problems. Although the KH algorithm usually performs well, it sometimes cannot achieve appropriate global search results as it fully relies on randomness. In this study, for provide better balance between the global search and local search of KH algorithm, an asynchronous KH structure was used along with the effect of best positions mechanism (EBP) in order to improve the performance of the KH algorithm. Integration of the two techniques further balances the global and local search results, resulting in increased accuracy of the algorithm for finding the best optimum solution. The performance of the proposed algorithm was evaluated on a set of benchmark functions. Comparison of the experimental results show that the proposed algorithm improves performance the KH algorithm as well as the most recent optimization methods studied in this research.
Optimization methods, Global optimization problem, Nature-inspired optimization methods, Krill herd algorithm
Status : Paper Accepted