Authors: Jiuyuan Huo; Yaonan Zhang; Hongxing Zhao
Addresses: School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou, 730070 China; Cold and Arid Regions Environmental and Engineering Research Institute, Chinese Academy of Sciences, Lanzhou, 730000, China ' Cold and Arid Regions Environmental and Engineering Research Institute, Chinese Academy of Sciences, Lanzhou, 730000, China ' School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou, 730070, China
Abstract: The artificial bee colony (ABC) algorithm is an important branch of evolutionary algorithms and has been shown to be competitive with other algorithms for solving optimisation problems. However, there are always some insufficiencies in ABC algorithm such as lower convergence speed and easily get trapped in the local optima. To increase depth search capabilities of onlooker bees and ensure scout bees do not discard the current optimal solution, we proposed a modified ABC algorithm (denoted as ORABC) based on the optimisation strategy and retained strategy of the best individual in this paper. Compared with ABC algorithm, ABC* (added retained strategy to ABC) and ORABC algorithm, experiments are conducted on a set of numerical benchmark functions. The numerical simulation results demonstrate that ORABC algorithm improves the convergence characteristics of ABC algorithm and provides very remarkable performance in solving complex numerical optimisation problems compared to original algorithm.
Keywords: artificial bee colony algorithm; ABC; optimisation strategy; retained strategy; numerical functions; numerical simulation.
International Journal of Reasoning-based Intelligent Systems, 2015 Vol.7 No.3/4, pp.200 - 208
Received: 25 Nov 2014
Accepted: 18 Jan 2015
Published online: 09 Nov 2015 *