Ma Haiping, Simon Dan, Fei Minrui
Department of Electrical Engineering, Shaoxing University, Shaoxing, Zhejiang, 312000, China; Shanghai Key Laboratory of Power Station Automation Technology, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, 200444, China
Department of Electrical and Computer Engineering, Cleveland State University, Cleveland, Ohio 44115, USA
Evol Comput. 2016 Fall;24(3):427-58. doi: 10.1162/EVCO_a_00160. Epub 2015 Jul 14.
Biogeography-based optimization (BBO) is an evolutionary algorithm inspired by biogeography, which is the study of the migration of species between habitats. This paper derives a mathematical description of the dynamics of BBO based on ideas from statistical mechanics. Rather than trying to exactly predict the evolution of the population, statistical mechanics methods describe the evolution of statistical properties of the population fitness. This paper uses the one-max problem, which has only one optimum and whose fitness function is the number of 1s in a binary string, to derive equations that predict the statistical properties of BBO each generation in terms of those of the previous generation. These equations reveal the effect of migration and mutation on the population fitness dynamics of BBO. The results obtained in this paper are similar to those for the simple genetic algorithm with selection and mutation. The paper also derives equations for the population fitness dynamics of general separable functions, and we find that the results obtained for separable functions are the same as those for the one-max problem. The statistical mechanics theory of BBO is shown to be in good agreement with simulation.
基于生物地理学的优化算法(BBO)是一种受生物地理学启发的进化算法,生物地理学是研究物种在栖息地之间迁移的学科。本文基于统计力学的思想推导了BBO动态过程的数学描述。统计力学方法并不试图精确预测种群的进化,而是描述种群适应度统计特性的进化。本文使用单目标问题(该问题只有一个最优解,其适应度函数是二进制字符串中1的数量)来推导方程,这些方程根据上一代的统计特性预测BBO每一代的统计特性。这些方程揭示了迁移和变异对BBO种群适应度动态的影响。本文得到的结果与具有选择和变异的简单遗传算法的结果相似。本文还推导了一般可分离函数的种群适应度动态方程,并且我们发现可分离函数得到的结果与单目标问题的结果相同。结果表明,BBO的统计力学理论与模拟结果吻合良好。