基于差异演化的粒子群优化算法

Particle swarm optimization based on differential evolution

针对粒子群优化算法由于缺乏种群多样性而导致早熟收敛的不利因素.提出了一种把差异演化算法中的后代产生机制引入粒子群优化算法的更新规则中以保持粒子群的种群多样性和加快收敛速度的算法.这种思想能有效改善摆脱极值点的能力.基于几个高维测试函数的试验结果显示,该算法在收敛速度快和精度方面都优于粒子群优化算法.

Considering particle swarm optimization （PSO） being easily trapped in local optima because of the loss of population diversity, an algorithm that DE offspring generation scheme is introduced in the update rules of PSO in order to maintain the population diversity and accelerate the converging speed is proposed in this paper. This strategy can improve the ability of escaping the local optima effectively. Simulation results on a suite of benchmark functions show that the proposed algorithm is superior to original particle swarm optimization algorithm.