双精英协同进化遗传算法

针对传统遗传算法早熟收敛和收敛速度慢的问题,提出一种双精英协同进化遗传算法(double elite coevolutionary genetic algorithm,简称DECGA).该算法借鉴了精英策略和协同进化的思想,选择两个相异的、高适应度的个体(精英个体)作为进化操作的核心,两个精英个体分别按照不同的评价函数来选择个体,组成各自的进化子种群.两个子种群分别采用不同的进化策略,以平衡算法的勘探和搜索能力.理论分析证明,该算法具有全局收敛性.通过对测试函数的实验,其结果表明,该算法能搜索到几乎所有测试函数的最优解,同时能够有效地保持种群的多样性.与已有算法相比,该算法在收敛速度和搜索全局最优解上都有了较大的改进和提高.     

基于多精英协同进化遗传算法的云资源调度

传统的遗传算法(GA)在解决云资源调度问题时会随着问题规模的增大而出现早熟收敛、搜索效率低下、寻优能力差等现象.为了克服这些缺陷,提出一种基于多精英协同进化的遗传算法(MECGA).该算法通过多精英保留技术将适应度值大的个体选入精英子种群,通过与普通子种群进行协同交叉操作,可引导整个种群向最优解的方向移动;通过定义个体评价策略,将差异度高的个体也选入到精英子种群,这些个体又能够保证种群的多样性,使种群更容易跳出局部最优解.实验结果表明,ME C GA相较其他GA具有求解效率高、收敛速度快和寻优能力强等特点.     

一种基于双精英种群的协同进化算法研究

针对传统带精英策略的多目标进化算法种群收敛分布不够均匀,全局搜索能力不足的缺点,提出一种基于双精英种群的协同进化算法DEPEA(Double Elite Populations Co-evolutionary Algorithm)。该算法借鉴了子区间划分和非支配排序思想,将整个种群划分成两个不同级别的精英种群和一个普通种群;两个精英种群结合协同进化思想分别采用不同的进化策略实现对算法的探究和探查能力的平衡,高级别的精英种群与低级别的精英种群采用协作操作,促进更优秀的个体产生;高级别的精英种群与普通种群采用引导操作,加快普通个体向精英个体逼近。通过对五个标准的测试函数进行实验,并与传统的NSGA-II算法和最新的hybird_MOEA算法结果进行比较与分析,表明该算法不仅具有更好的全局收敛性,且能够更好地保证种群的多样性。     

基于学习的进化规划算法

提出基于学习的进化规划算法，用以改进普通进化规划算法的性能，该算法－方面通过学习种群整体的进化信息用以改善种群整体性能，具有大范围快速搜索的特点，另一方面该算法强调学习种群中个体的进化信息，单一个体以当前代的最优化个体作为学习目标，用以加大当前最优解附近的搜索力度，具有局部“细搜”的特点，该进化规划算法不仅能够加快算法的收敛速度，而且能够有效地保证种群的多样性，用该方法可求解具有多个极值点的函数优化问题，计算要仿真实验结果表明该方法是非常有效的。     

基于精英种群策略的协同差分进化算法

针对差分进化算法在处理函数优化时存在的过早收敛和易陷入局部最优的问题,提出了一种基于精英种群策略的协同差分进化算法。在优化过程中,首先对种群进行适应度值评估和排序,提取前N个优秀个体组成精英种群,其余个体随机分为3个等大的子种群,每个子种群采取不同的进化策略,以此来保证种群的多样性;然后每隔一定代数,根据新的适应度值更新精英种群和其余3个子种群,这样可以有效地避免算法陷入局部最优;最后,将所提出的算法与4个先进的差分进化算法在CEC2014的30个标准测试函数上进行对比实验。实验结果表明,所提出的算法能够有效提高收敛速度,具有较高的收敛精度和较好的优化性能。     

一种改进的双精英协同进化遗传算法

提出一种改进的双精英协同进化遗传算法。在该算法中,种群被划分为两个精英小队,二者协同进化;精英是小队中的最优个体,并且两个小队的精英具有较高的差异度。精英分别与被选的个体进行交叉,增强了种群个体和全局最优解的亲和度;同时,当精英小队中的个体间的差异度下降到规定的预警值时,引入变异操作,有效地保持了种群的多样性,避免了早熟问题。算法中还给出一种δ-表现型多样性测度计算方法,使之可以对个体适应值为实数的群体多样性进行准确计算。针对参数多、大范围的复杂计算环境,算法的搜索能力明显提高。     

求解置换流水线调度问题的混合离散果蝇算法

针对置换流水线调度问题,提出了一种新颖的混合离散果蝇算法.算法每一代进化包括4个搜索阶段:嗅觉搜索、视觉搜索、协作进化和退火过程.在嗅觉搜索阶段,采用插入方式生成邻域解;在视觉搜索阶段,选择最优邻域解更新个体;在协作进化阶段,基于果蝇个体间的差分信息产生引导个体;在退火操作阶段,以一定概率接受最优引导个体从而更新种群.同时,通过试验设计方法对算法参数设置进行了分析,并确定了合适的参数组合.最后,通过基于标准测试集的仿真结果和算法比较验证了所提算法的有效性和鲁棒性.     

基于混合策略的双种群约束优化算法

提出一种基于混合策略的双种群约束优化算法.利用双种群存储机制处理约束条件,并采用约束支配更新不可行解集,同时采用混合策略进化种群:在进化前期利用Deb准则产生可行解,并保留一部分非劣不可行解参与进化,保持种群多样性;在进化后期让最优个体和次优个体参与进化,使种群快速收敛.仿真实验结果表明,所提出的算法在保证种群多样性的同时,能够较好地收敛到全局最优解,且鲁棒性较好.     

免疫协同微粒群进化算法的永磁同步电机多参数辨识模型方法

针对永磁同步电机多参数辨识问题,提出一种基于免疫协同微粒群进化(Immune co-evolution particle swarm optimization, ICPSO) 算 法的永磁同步电机(Permanent magnet synchronous motor, PMSM) 多参数辨识方法.算法由记忆种群与若干个普通种群构成, 在进化过程中普通种群中优秀个体进入记忆库种群.普通种群内部通过精英粒子 保留、免疫网络以及柯西变异等混合策略共同产生新个体,个体极值采用小波学习 加快收敛速度,免疫克隆选择算法对记忆库进行精细搜索,迁移机制实现了整个种群 的信息共享与协同进化.永磁同步电机参数辨识结果表明该方法不需要知道电 机设计参数先验知识,能够有效地辨识电机电阻、 dq轴电感与转子磁链,且能有效追踪该参数变化值.     

协同进化混合蛙跳算法

针对基本混合蛙跳算法收敛速度慢、求解精度低且易陷入局部最优的问题,提出了一种新的协同进化混合蛙跳算法。该算法在局部搜索策略中,对子群内最差个体的更新引入平均值的同时充分利用最优个体的优秀基因,可有效扩大搜索空间,增加种群的多样性;同时对子群内少量的较差青蛙采取交互学习策略向邻近子群的最优个体交流学习,增加子群间交互的频繁性,提高信息共享程度,有利于进化。在全局迭代过程中采取精英群自学习进化机制,以对精英空间进行精细搜索,获得更优解,进一步提升算法的全局寻优能力,正确导向算法的进化。实验结果表明,所提算法在七个测试函数中均能收敛到最优解0,成功率为100%,优于其他对比算法。所提算法可有效避免陷入早熟收敛,极大地提高了算法的收敛速度和优化精度。     

重启进化提高较大搜索规模时柔性作业解质量

种群多样性下降导致的早熟收敛限制了进化算法的求解质量与搜索效率。为应对收敛,提高较大搜索规模时的求解质量,引入随机算法中重启策略。种群收敛时,利用算法前期搜索结果（优势元素）和新产生的随机元素重新构造新种群继续进化。提高柔性作业车间调度问题解质量对实际工业生产有重要的现实意义。将重构思想应用于协同进化算法求解复杂柔性作业调度问题并跟踪种群进化状态。仿真实验结果表明,改进算法在进化过程中维持了较好的种群多样性,大幅提高了算法求解复杂柔性作业调度的搜索性能,并可以简单通过扩大搜索规模提高作业调度解质量。     

The manpower allocation problem with time windows and job-teaming constraints: A branch-and-price approach

In this paper, we consider the manpower allocation problem with time windows, job-teaming constraints and a limited number of teams (m-MAPTWTC). Given a set of teams and a set of tasks, the problem is to assign to each team a sequential order of tasks to maximize the total number of assigned tasks. Both teams and tasks may be restricted by time windows outside which operation is not possible. Some tasks require cooperation between teams, and all teams cooperating must initiate execution simultaneously. We present an integer programming model for the problem, which is decomposed using Dantzig–Wolfe decomposition. The problem is solved by column generation in a branch-and-price framework. Simultaneous execution of tasks is enforced by the branching scheme. To test the efficiency of the proposed algorithm, 12 realistic test instances are introduced. The algorithm is able to find the optimal solution in 11 of the test instances. The main contribution of this article is the addition of synchronization between teams in an exact optimization context.     

An efficient algorithm for constrained global optimization and application to mechanical engineering design: League championship algorithm (LCA)

The league championship algorithm (LCA) is a new algorithm originally proposed for unconstrained optimization which tries to metaphorically model a League championship environment wherein artificial teams play in an artificial league for several weeks (iterations). Given the league schedule, a number of individuals, as sport teams, play in pairs and their game outcome is determined given known the playing strength (fitness value) along with the team formation (solution). Modelling an artificial match analysis, each team devises the required changes in its formation (a new solution) for the next week contest and the championship goes for a number of seasons. In this paper, we adapt LCA for constrained optimization. In particular: (1) a feasibility criterion to bias the search toward feasible regions is included besides the objective value criterion; (2) generation of multiple offspring is allowed to increase the probability of an individual to generate a better solution; (3) a diversity mechanism is adopted, which allows infeasible solutions with a promising objective value precede the feasible solutions. Performance of LCA is compared with comparator algorithms on benchmark problems where the experimental results indicate that LCA is a very competitive algorithm. Performance of LCA is also evaluated on well-studied mechanical design problems and results are compared with the results of 21 constrained optimization algorithms. Computational results signify that with a smaller number of evaluations, LCA ensures finding the true optimum of these problems. These results encourage that further developments and applications of LCA would be worth investigating in the future studies.     

A set partitioning based goal programming model for the team formation problem

In this paper, we offer a multi-objective set-partitioning formulation for team formation problems using goal programming. Instead of selecting team members to teams, we select suitable teams from a set of teams. This set is generated using a heuristic algorithm that uses the social network of potential team members. We then utilize the proposed multi-objective formulation to select the desired number of teams from this set that meets the skill requirements. Therefore, we ensure that selected teams include individuals with the required skills and effective communication with each other. Two real datasets are used to test the model. The results obtained with the proposed solution are compared with two well-known approaches: weighted and lexicographic goal programming. Results reveal that weighted and lexicographic goal programming approaches generate almost identical solutions for the datasets tested. Our approach, on the other hand, mostly picks teams with lower communication costs. Even in some cases, better solutions are obtained with the proposed approach. Findings show that the developed solution approach is a promising approach to handle team formation problems.     

Prescribed teams of grammars

We consider sets of grammars (calledteams) which process strings by cooperating together; a single derivation step in a team is done in such a way that each grammar in the set rewrites a symbol in the string. A cooperating grammar system with prescribed teams (CPT) consists of a finite number of teams. In a maximal rewriting mode, a team in a CPT can take a string for rewriting whenever it can make a derivation step on it; it keeps it and rewrites as long as it can, and once a string is obtained that cannot be rewritten by the team anymore it is returned and becomes available to all other teams.In this paper we investigate the power of CPT in the maximal and other rewriting modes. We establish the relationships of CPT with other models of grammars cooperating together and with various kinds of controlled grammars. We also solve some open problems from [6] and provide alternative proofs for some results from [6].The authors are indebted to Basic Research ASMICS II Working Group for supoort; the work of the first author has been also supported by the Alexander von Humboldt Foundation     

A hybrid of genetic algorithm and particle swarm optimization for recurrent network design

An evolutionary recurrent network which automates the design of recurrent neural/fuzzy networks using a new evolutionary learning algorithm is proposed in this paper. This new evolutionary learning algorithm is based on a hybrid of genetic algorithm (GA) and particle swarm optimization (PSO), and is thus called HGAPSO. In HGAPSO, individuals in a new generation are created, not only by crossover and mutation operation as in GA, but also by PSO. The concept of elite strategy is adopted in HGAPSO, where the upper-half of the best-performing individuals in a population are regarded as elites. However, instead of being reproduced directly to the next generation, these elites are first enhanced. The group constituted by the elites is regarded as a swarm, and each elite corresponds to a particle within it. In this regard, the elites are enhanced by PSO, an operation which mimics the maturing phenomenon in nature. These enhanced elites constitute half of the population in the new generation, whereas the other half is generated by performing crossover and mutation operation on these enhanced elites. HGAPSO is applied to recurrent neural/fuzzy network design as follows. For recurrent neural network, a fully connected recurrent neural network is designed and applied to a temporal sequence production problem. For recurrent fuzzy network design, a Takagi-Sugeno-Kang-type recurrent fuzzy network is designed and applied to dynamic plant control. The performance of HGAPSO is compared to both GA and PSO in these recurrent networks design problems, demonstrating its superiority.     

Classification as clustering: a Pareto cooperative-competitive GP approach

Intuitively population based algorithms such as genetic programming provide a natural environment for supporting solutions that learn to decompose the overall task between multiple individuals, or a team. This work presents a framework for evolving teams without recourse to prespecifying the number of cooperating individuals. To do so, each individual evolves a mapping to a distribution of outcomes that, following clustering, establishes the parameterization of a (Gaussian) local membership function. This gives individuals the opportunity to represent subsets of tasks, where the overall task is that of classification under the supervised learning domain. Thus, rather than each team member representing an entire class, individuals are free to identify unique subsets of the overall classification task. The framework is supported by techniques from evolutionary multiobjective optimization (EMO) and Pareto competitive coevolution. EMO establishes the basis for encouraging individuals to provide accurate yet nonoverlaping behaviors; whereas competitive coevolution provides the mechanism for scaling to potentially large unbalanced datasets. Benchmarking is performed against recent examples of nonlinear SVM classifiers over 12 UCI datasets with between 150 and 200,000 training instances. Solutions from the proposed coevolutionary multiobjective GP framework appear to provide a good balance between classification performance and model complexity, especially as the dataset instance count increases.     

求解高维多模优化问题的正交小生境自适应差分演化算法

针对传统优化算法在求解高维多模态优化问题时存在收敛速度慢、求解精度低的问题,提出一种基于正交设计与小生境精英策略的自适应差分进化算法ONDE。首先利用正交表产生初始种群,然后采用小生境精英策略来产生小生境种群(NP),并用小生境种群更新精英个体;接着应用拥挤裁剪避免种群陷入局部搜索,最后利用自适应差分变异算子改进了差分进化(DE)算法。通过对7个benchmark函数仿真验证,实验结果表明,算法在收敛速度、求解精度和稳定性方面都有较大优势。