An Improved Biology Migration Algorithm with Von Neumann Structure

摘要

Biology migration algorithm (BMA) is a newly developed metaheuristic algorithm inspired by the biology migration phenomenon. The paramount challenge in BMA is that it is prone to stagnation in local optima and premature convergence. To solve these issues, this paper proposed an improved biology migration algorithm with Von Neumann structure to help BMA balance exploration and exploitation better, which named BMAVI. First, non-linear initial weights are introduced into BMA to balance exploration and exploitation. Second, the Von Neumann structure was introduced into the BMA to construct the neighbors of each individual, increasing information exchange and enriching population diversity. Finally, the proposed BMAVI has also been evaluated on CEC2017 test set compared with the classic and other novel evolutionary algorithms to confirm the performance of BMAVI. Experimental results show that the performance of the proposed BMAVI algorithm is better than other selected algorithms.