全局较优解引导的人工蜂群算法

人工蜂群算法(ABC)是一种模拟蜜蜂群体寻找优良蜜源的群体智能优化算法.针对人工蜂群算法收敛速度较慢、探索能力较强而开发能力偏弱等问题,提出一种改进的蜂群算法.算法利用更多的较优蜜源位置的信息来引导采蜜蜂和跟随蜂的搜索行为.为了提高算法的全局收敛速度,通过基于混沌策略的方式生成初始化种群,并且在每一代侦察蜂阶段后对全部新蜜源进行反向再搜索.另外,每次蜜蜂邻域搜索之后,采用比较新旧蜜源的花蜜值(而非适应度值)的方法来更新蜜源位置.通过对14个标准测试函数进行仿真实验,结果表明所提出的算法能有效加快收敛速度,提高开发能力和解的精度.     

Synchronous and asynchronous Pareto-based multi-objective Artificial Bee Colony algorithms

Pareto-based multi-objective optimization algorithms prefer non-dominated solutions over dominated solutions and maintain as much as possible diversity in the Pareto optimal set to represent the whole Pareto-front. This paper proposes three multi-objective Artificial Bee Colony (ABC) algorithms based on synchronous and asynchronous models using Pareto-dominance and non-dominated sorting: asynchronous multi-objective ABC using only Pareto-dominance rule (A-MOABC/PD), asynchronous multi-objective ABC using non-dominated sorting procedure (A-MOABC/NS) and synchronous multi-objective ABC using non-dominated sorting procedure (S-MOABC/NS). These algorithms were investigated in terms of the inverted generational distance, hypervolume and spread performance metrics, running time, approximation to whole Pareto-front and Pareto-solutions spaces. It was shown that S-MOABC/NS is more scalable and efficient compared to its asynchronous counterpart and more efficient and robust than A-MOABC/PD. An investigation on parameter sensitivity of S-MOABC/NS was presented to relate the behavior of the algorithm to the values of the control parameters. The results of S-MOABC/NS were compared to some state-of-the art algorithms. Results show that S-MOABC/NS can provide good approximations to well distributed and high quality non-dominated fronts and can be used as a promising alternative tool to solve multi-objective problems with the advantage of being simple and employing a few control parameters.     

0-1背包问题的蜂群优化算法

在项目决策与规划、资源分配、货物装载、预算控制等工作中,提出了0-1背包问题.0-1背包问题是组合优化中的典型NP难题,根据群集智能原理,给出一种基于蜂群寻优思想的新算法—蜂群算法,并针对0-1背包问题进行求解.经实验仿真并与蚁群算法计算结果作对比,验证了算法在0-1背包问题求解上的有效性和更快的收敛速度.     

基于多蜂群模型的多目标人工蜂群算法研究

提出了一种基于多蜂群模型的新颖多目标人工蜂群算法(MCMOABC,).算法使用外部档案存储非支配解,运用自适应网格对档案进行维护.在MCMOABC算法中存在3个搜索域各不相同的蜂群,其中2个称为基本蜂群,第3个为综合蜂群.选择4个常用的性能指标,将MCMOABC与其他主流算法在CEC2009测试集上进行比较,实验结果显示了算法的优越性.     

一种自适应人工蜂群算法求解U型顺序相依拆卸线平衡问题

产品拆卸过程中零部件之间会相互干扰影响任务作业时间,基于该情形构建了多目标U型SDDLBP优化模型,并提出一种自适应ABC算法。所提算法设计了自适应动态邻域搜索方法,以提高局部开发能力;采用了轮盘赌与锦标赛法结合的分段选择法,以有效评价并选择蜜源进行深度开发;建立了基于当前最优解的变异操作,以提高全局探索能力快速跳出局部最优。最后,通过算例测试和实例分析验证算法的高效性。     

基于人工蜂群算法的非线性系统模型参数估计

将人工蜂群算法用于非线性系统模型的参数估计,通过对谷氨酸菌体生长模型的参数估计进行验证,并与人工神经网络、遗传算法和微粒群算法的优化结果进行了比较.仿真试验结果表明:人工蜂群算法对非线性系统模型的参数估计精度高于人工神经网络、遗传算法和微粒群算法的参数估计精度,为非线性系统模型参数估计提供了一种有效的途径.     

基于人工蜂群算法的配送中心选址问题求解

采用人工蜂群算法对配送中心选址问题进行求解,给出食物源的编码方法,通过整数规范化,使算法能在整数空间内对问题进行求解.应用算法进行了仿真实验,并将结果与其它一些启发式算法进行了比较和分析.计算结果表明人工蜂群算法可以有效求解配送中心选址问题,同时也为算法求解其它一些组合优化问题提供了有益思路.     

云计算环境下人工蜂群作业调度算法设计

针对云计算环境下作业调度优化问题,提出了一种基于人工蜂群的调度算法.分析人工蜂群算法的求解组合优化问题过程,建立了收益度函数和蜜源位置更新公式,最后论述了利用该算法求解的具体步骤.并通过实验分析了该算法的性能.     

改进GA机制融合的二进制蜂群算法研究

为了克服人工蜂群算法蜜源更新过程中的随机性并保留蜜源中个体序列合理的组合形式,通过分析基本蜂群算法更新公式的机理,提出一种改进GA(Genetic A1gorithm)机制融合的二进制蜂群算法.算法以二进制编码,首先依概率对任意两蜜源进行"去同存异"操作后随机排列,将排列结果放入到其中某个体中形成新个体.然后依概率进行二进制个体的"翻转"操作,上述两种操作从其本质上相当于GA的类交叉和类变异操作;其次利用GA机制收敛性的证明方式在理论上证明算法是收敛的.最后通过应用不同特性的多维基准函数和算法之间的比较验证改进蜂群算法具有良好的收敛能力和鲁棒性.     

求解混合流水线调度问题的离散人工蜂群算法

本文给出了一种离散的人工蜂群算法(HDABC)用于求解混合流水车间调度(HFS)问题。采用工件排序的编码方式,并设计了四种邻域结构。雇佣蜂依次分派到解集中每个解,采用结合问题特征的局部搜索策略完成挖掘搜索工作。跟随蜂随机选择两个解并挑选较优者作为当前解,完成进一步的探优过程。侦察蜂采用三种策略跳出局部极小。通过34个同构并行机HFS问题和2个异构并行机HFS实际调度问题的实验,并与当前文献中的典型算法对比,验证了本文提出的算法无论在算法时间还是在求解质量上,都具备良好的性能。     

A comparative study of Artificial Bee Colony algorithm

Artificial Bee Colony (ABC) algorithm is one of the most recently introduced swarm-based algorithms. ABC simulates the intelligent foraging behaviour of a honeybee swarm. In this work, ABC is used for optimizing a large set of numerical test functions and the results produced by ABC algorithm are compared with the results obtained by genetic algorithm, particle swarm optimization algorithm, differential evolution algorithm and evolution strategies. Results show that the performance of the ABC is better than or similar to those of other population-based algorithms with the advantage of employing fewer control parameters.     

嵌入差分进化算子的混合蜂群算法及其在VRPSDP的应用

针对人工蜂群算法进化速度慢、容易陷入搜索停滞的问题,通过嵌入差分进化算子,提出了一种混合蜂群算法(Hybrid Artificial Bee Colony algorithm, HABC).基本思想是:在迭代中嵌入差分进化算子,充分利用差分算法全局收敛性和鲁棒性强的特点,寻求全局最优蜜源;此外,在标准蜂群算方法基础上进行两点改进:在采蜜蜂阶段搜索策略中加入最优位置引导,提高搜索的效率;对超边界的个体重新进行变异,以增强种群的多样性.将混合算法应用于带同时送取货的车辆路径问题(VRPSDP),计算结果表明了混合算法的有效性.     

元胞人工蜂群算法及其在0-1规划问题中的应用

针对人工蜂群算法早熟收敛问题,基于元胞自动机原理和人工蜂群算法,提出一种元胞人工蜂群算法.该算法将元胞演化和人工蜂群搜索相结合,利用元胞及其邻居的演化提高了种群多样性,避免陷入局部最优解.经一系列典型0-1规划问题实例的仿真实验和与其他算法对比,验证了本算法的效果和效率,获得了满意的结果.     

一类齐次多项式优化问题的一个全局优化算法

对图像与信号处理中遇到的一类齐次多项式优化问题,本文首先借助平移技术将目标函数转化为凸函数,然后结合初始点技术提出了求解该类问题的一个全局优化算法.与求解该类问题的幂方法相比,本文给出的方法不但能在一般情形下保证算法的全局收敛性,而且数值结果表明在多数情况下可以得到问题的一个全局最优值解.     

积分——水平集求全局最优的遗传算法实现

Chew Soo Hong,Zheng Q uan提出了一个积分——水平集求全局最优的概念性算法及M on te-C ar-lo随机投点的实现途径,并在很多实际问题中得到了很好的应用,但这一实现算法的收敛性是个未解决的问题.利用近年来广泛应用的遗传算法,给出了这一算法的另一种实现途径,并从理论和数值两个方面验证了算法的可行性.     

Protein Structure Prediction Using Bee Colony Optimization Metaheuristic

Predicting the native structure of proteins is one of the most challenging problems in molecular biology. The goal is to determine the three-dimensional structure from the one-dimensional amino acid sequence. De novo prediction algorithms seek to do this by developing a representation of the proteins structure, an energy potential and some optimization algorithm that finds the structure with minimal energy. Bee Colony Optimization (BCO) is a relatively new approach to solving optimization problems based on the foraging behaviour of bees. Several variants of BCO have been suggested in the literature. We have devised a new variant that unifies the existing and is much more flexible with respect to replacing the various elements of the BCO. In particular, this applies to the choice of the local search as well as the method for generating scout locations and performing the waggle dance. We apply our BCO method to generate good solutions to the protein structure prediction problem. The results show that BCO generally finds better solutions than simulated annealing which so far has been the metaheuristic of choice for this problem.     

Artificial Bee Colony training of neural networks: comparison with back-propagation

The Artificial Bee Colony (ABC) is a swarm intelligence algorithm for optimization that has previously been applied to the training of neural networks. This paper examines more carefully the performance of the ABC algorithm for optimizing the connection weights of feed-forward neural networks for classification tasks, and presents a more rigorous comparison with the traditional Back-Propagation (BP) training algorithm. The empirical results for benchmark problems demonstrate that using the standard “stopping early” approach with optimized learning parameters leads to improved BP performance over the previous comparative study, and that a simple variation of the ABC approach provides improved ABC performance too. With both improvements applied, the ABC approach does perform very well on small problems, but the generalization performances achieved are only significantly better than standard BP on one out of six datasets, and the training times increase rapidly as the size of the problem grows. If different, evolutionary optimized, BP learning rates are allowed for the two layers of the neural network, BP is significantly better than the ABC on two of the six datasets, and not significantly different on the other four.     

多目标0-1规划问题的蜂群算法

针对多目标0-1规划问题,本文给出一种新型的智能优化算法——蜂群算法进行求解,并通过实例验证,与遗传算法、蚁群算法和元胞蚁群算法作了相应比较。就多目标0-1规划问题而言,蜂群算法能得到更多的Pareto解,说明了蜂群算法在解决该类问题上的有效性。     

蜂群算法求解支持模糊QoS约束的电子采购模型

基于Web的电子物流采购是电子商务的热点.通过将模糊量化的QoS约束加入到Web电子物流采购模型,构造一种带有QoS约束的Web电子物流采购模型,并设计一种改进的人工蜂群算法进行求解.模型基于现有Web采购系统的采购模式,融合了非功能性Web服务评价理论,着重将带QoS约束的电子物流采购选择过程与人工蜂群算法求解过程相结合,从而能快速准确地获得使整体利益最大的解.经仿真计算,验证了模型的有效性.     

A Trust-Region Algorithm for Global Optimization

We consider the global minimization of a bound-constrained function with a so-called funnel structure. We develop a two-phase procedure that uses sampling, local optimization, and Gaussian smoothing to construct a smooth model of the underlying funnel. The procedure is embedded in a trust-region framework that avoids the pitfalls of a fixed sampling radius. We present a numerical comparison to three popular methods and show that the new algorithm is robust and uses up to 20 times fewer local minimizations steps.