基于Tent映射的改进型人工蜂群算法

Modified Artificial Bee Colony Algorithm based on Tent Mapping

人工蜂群(Artificial Bee Colony,ABC)算法是受蜜蜂的觅食行为启发而提出的群体智能算法,其利于解决高维连续函数的寻优问题。针对ABC算法的不足,分别对其种群个体初始化方式和更新机制进行改进。采用混沌映射和反向学习机制初始化种群个体位置,益于保持种群多样性;将新型惯性权值引入个体位置更新机制,以提高算法的收敛精度和平衡其探索能力与开发能力。通过13个基准测试函数验证,结果表明:相比于原始ABC算法,改进的ABC算法在9个函数上表现出良好的收敛精度和解的质量。

Artificial Bee Colony(ABC)is a kind of swarm intelligence algorithm inspired by the foraging behavior of honeybees,which is beneficial to solve the optimization problem of high-dimensional continuous function.Aiming at the shortcomings of ABC algorithm,this paper proposes to modify the initialization method and update mechanism of population individuals.The chaotic mapping and reverse learning mechanism are used to initialize individual positions,which is good for maintaining population diversity.The novel inertia weight is introduced in the individual position update mechanism to improve the convergence accuracy and balance its exploration and development ability.Through 13 benchmark functions verification,the experiment results show that compare with the conventional artificial bee colony algorithm,the modified artificial bee colony(MABC)algorithm represents better convergence accuracy and solution quality on 9 functions.