在对传统演化算法分析的基础上,提出了一种基于蜂王交配的求解复杂优化问题的演化算法(QMSGA)。它的特点在于:模拟自然界中蜂王的交配方法,并引入均匀杂交和平均矢量偏差变异因子策略来达到种群分布的多样性,最终求出复杂优化问题的全局最优解。实验结果表明,对于求解复杂的多峰优化、陡峭函数优化等问题,该算法比传统的演化算法具有更好的精确度和收敛速度。
Through an analysis of the traditional evolutionary algorithm, a new evolutionary algorithm based-on a queen-bee mating evolutionary algorithm (QMSGA) was proposed. This new algorithm greatly improves the traditional evolutionary algorithm and has many good features. It simulates the queen-bee's method of mating in nature. What's more, aiming at enhancing the diversity of population and ultimately getting the global solution, QMSGA also introduces the strategy of Guo's algorithm, uniform recombination as well as the average vector deviation mutation factor. In numerical experiments, this algorithm was used to solve some complex single-objective optimization problems such as multi-peaks functions and steep functions, which the traditional evolutionary algorithm had trouble to solve. Comparing with the traditional evolutionary algorithm, QMSGA has better performance in realizing global optimization and promoting evolution efficiency, and can lead to higher precise solutions.