量子粒子群优化的人工蜂群算法

摘要

针对传统的人工蜂群算法在求解函数优化问题中具有收敛速度慢、局部搜索能力低的缺点,将量子粒子群优化算法中粒子位移的更新方法引入到跟随蜂的局部搜索策略中,使人工蜂群具有更高的局部搜索能力.6个标准测试函数的仿真实验结果表明:与传统的人工蜂群算法相比,改进后的人工蜂群算法在收敛速度和寻优精度上大幅提高.%To improve the traditional artificial bee colony algorithm(ABCA)which has the problem of slow convergence speed and low local search ability,put forward an ABCA based on quantum particle swarm optimization(QPSO).The local search ability remarkably improved by introducing the updating method of particle displacement in QPSO to the local search strategy of employed bees and onlooker bees.The simulation results of six standard test functions indicate that compared with the traditional ABCA the improved ABCA improves greatly in the rate of convergence speed and the optimization precision.