基于Nelder-Mead单纯形法的改进量子行为粒子群算法

针对PSO算法搜索精度较低,并且在复杂多模态函数优化中,容易陷入局部极值的问题,提出了一种改进的量子行为粒子群优化算法。研究了该算法的基本原理、给出了算法流程并采用正交试验的方式获得了一套通用性较强的算法参数。并以CEC’13的28个测试函数作为测试集,采用Wilcoxon符号秩检验将NM-QPSO算法分别与PSO算法和QPSO算法的误差进行比较试验。试验表明:NM-QPSO算法在统计意义上优于传统的PSO算法和QPSO算法,并且在高维函数优化中,具有显著优势。     

基于微粒群算法的虚拟仪器参数自适应配置方法

提出了一种利用微粒群算法优化虚拟仪器参数设置的方法。微粒群算法通过模拟鸟类社会性运动的规律,利用群体智能解决组合优化问题,该算法能够迅速有效地进行最优化搜索。将其用于解决仪器参数设置中的多维空间优化问题,具有概念简单,应用方便,计算复杂性低和运算速度快的特点。     

动态环境下分布式自适应粒子群优化算法

针对现有粒子群算法的不足,提出一种基于微粒自身信息的环境变化检测方法,同时采用分布式处理模式,通过激活粒子群中的停滞粒子适应环境变化,不仅降低了的算法复杂度,而且提高了算法对复杂环境的自适应能力.对于有界连续函数,证明新算法能依概率收敛于全局极小点.应用抛物线函数和Rastrigin函数构造的复杂动态环境对该算法进行验证,并同APSO、D-PSO算法进行了对比.实验结果表明,在复杂的动态环境中,DAPSO算法具有更好的适应性.     

求解连续空间优化问题的量子差分混合优化算法

借鉴量子计算的相关原理和差分进化思想,提出一种用于连续空间优化问题的量子差分混合优化算法。算法的核心是构造由决策向量的分量和量子位概率幅为等位基因的实数编码染色体;采用依据染色体的具体形式设计的互补变异进化部分优秀个体,以加快算法的收敛速度;利用差分进化思想进化部分随机选取个体,以保持算法的全局搜索能力和鲁棒性。对Benchmark函数测试表明,该算法具有寻优能力强、搜索精度高和稳定性好的特点。应用该算法求解路基沉降预测模型参数估计问题,能够有效提高实测沉降数据的拟合精度.     

函数优化的量子蚂蚁算法

借鉴蚁群算法的进化思想,提出一种求解连续空间优化问题的量子蚂蚁算法.该算法主要包括全局搜索、局部搜索和信息素强度更新规则.在全局搜索过程中,利用信息素强度和启发式函数确定蚂蚁移动方向.在局部搜索过程中,提出了基于Delta势阱的量子搜索,以改善寻优性能,加快收敛速率.通过实例验证表明了该算法的有效性.     

基于免疫蛙跳算法的梯级水库群优化调度

针对混洗蛙跳算法存在的问题,结合克隆选择算法和混洗蛙跳算法各自优势,提出了一种免疫蛙跳算法(ISFLA),并将其应用于梯级水库群优化调度中. ISFLA将克隆选择算法嵌入到混洗蛙跳算法框架中,对整个群体循环进行分组进化与混合,在混合之后构造子群体执行克隆选择操作, 以提高算法的局部搜索能力.通过实际工程验证了该算法的可行性与高效性,从而为梯级水库群发电调度问题的求解提供了一种新的途径.     

基于Bloch球面搜索的混沌量子免疫算法

目前大多数量子智能优化算法的个体均采用基于平面单位圆描述的量子比特编码,由于量子比特只有一个可调参数,量子特性没有得到充分体现,从而限制了优化能力的进一步提高。针对这一问题提出一种基于Bloch球面搜索的混沌量子免疫算法。该方法采用Bloch球面描述的量子比特对抗体进行编码,用泡利矩阵建立旋转轴,用量子比特在Bloch球面上的绕轴旋转实现优良抗体的克隆,通过在旋转角度中引入混沌变量动态改变转角大小实现局部搜索;用Hadamard门实现较差抗体的变异,实现全局搜索。仿真结果表明,提出的方法在搜索能力和优化效率两方面均比其他量子智能优化算法有所提高。     

基于自适应相位旋转的Grover量子搜索算法

在使用Grover量子搜索算法对给定规模的无序数据库搜索时,随着搜索目标数的增加,获得正确结果的概率大幅度下降.分析了出现这种现象的原因,研究了算法中的Grover叠代过程,提出了一种新的自适应相位旋转策略.应用这一策略,当搜索目标数超过目标总数的(3-√5)/8时,只需两步搜索;当搜索目标数超过目标总数的1/4时,只需一步搜索,即可获得恒等于1的成功概率.实验表明新相位旋转策略是有效的.     

基于自适应网格的多目标粒子群优化算法

针对现有多目标进化算法计算复杂度高,搜索效率低等缺点,提出了基于自适应网格的多目标粒子群优化(AGA-MOPSO)算法,其特点包括:评估非劣解集中粒子密度估计信息的自适应网格算法;能够平衡全局和局部搜索能力的基于AGA的Pareto最优解搜索技术;删除非劣解集集中品质差的多余粒子以维持非劣解集在一定规模的基于AGA的非劣解集截断技术.仿真计算表明,和文献中典型的多目标进化算法比较,AGA-MOPSO算法在求解复杂大规模优化问题方面表现了良好的性能.     

函数优化的量子蝙蝠算法

基于量子进化算法和蝙蝠算法,提出一种新型优化算法——量子蝙蝠算法。该算法采用量子位对蝙蝠的位置进行编码,用量子旋转门实现对蝙蝠最优位置的搜索,用量子非门实现蝙蝠的变异以避免早熟收敛。通过对典型复杂函数的实验和与其他算法的比较,结果表明,该算法能够有效避免局部最优,全局寻优能力强。     

Membrane-inspired quantum shuffled frog leaping algorithm for spectrum allocation

To solve discrete optimization difficulty of the spectrum allocation problem,a membrane-inspired quantum shuffled frog leaping(MQSFL) algorithm is proposed.The proposed MQSFL algorithm applies the theory of membrane computing and quantum computing to the shuffled frog leaping algorithm,which is an effective discrete optimization algorithm.Then the proposed MQSFL algorithm is used to solve the spectrum allocation problem of cognitive radio systems.By hybridizing the quantum frog colony optimization and membrane computing,the quantum state and observation state of the quantum frogs can be well evolved within the membrane structure.The novel spectrum allocation algorithm can search the global optimal solution within a reasonable computation time.Simulation results for three utility functions of a cognitive radio system are provided to show that the MQSFL spectrum allocation method is superior to some previous spectrum allocation algorithms based on intelligence computing.     

Enhanced minimum attribute reduction based on quantum-inspired shuffled frog leaping algorithm

Attribute reduction in the rough set theory is an important feature selection method,but finding a minimum attribute reduction has been proven to be a non-deterministic polynomial(NP)-hard problem.Therefore,it is necessary to investigate some fast and effective approximate algorithms.A novel and enhanced quantum-inspired shuffled frog leaping based minimum attribute reduction algorithm(QSFLAR) is proposed.Evolutionary frogs are represented by multi-state quantum bits,and both quantum rotation gate and quantum mutation operators are used to exploit the mechanisms of frog population diversity and convergence to the global optimum.The decomposed attribute subsets are co-evolved by the elitist frogs with a quantum-inspired shuffled frog leaping algorithm.The experimental results validate the better feasibility and effectiveness of QSFLAR,comparing with some representative algorithms.Therefore,QSFLAR can be considered as a more competitive algorithm on the efficiency and accuracy for minimum attribute reduction.     

基于并行云变异蛙跳算法的梯级水库优化调度研究

本文针对混合蛙跳算法(shuffled frog leaping algorithm,SFLA)早熟收敛的问题,将云模型算法融合于SFLA算法中,形成一种云变异蛙跳算法(normal cloud mutation SFLA,NCM-SFLA),弥补混合蛙跳算法后期容易陷入局部最优的不足.同时利用算法易于并行的特点,在多核环境下基于.NET4的并行拓展库(parallel extensions)进行算法的并行优化.将其应用于梯级水库优化调度中,实例计算表明,与多维动态规划算法(MDP)相比,NCM-SFLA方法具有更好的全局寻优能力和较快的收敛速度,在现有的计算条件下该并行算法能有效缩短程序运行时间,求解梯级水库优化调度问题是合理、有效的.     

Novel multi-objective optimization algorithm

Many multi-objective evolutionary algorithms （MOEAs） can converge to the Pareto optimal front and work well on two or three objectives, but they deteriorate when faced with manyobjective problems. Indicator-based MOEAs, which adopt various indicators to evaluate the fitness values （instead of the Paretodominance relation to select candidate solutions）, have been regarded as promising schemes that yield more satisfactory results than well-known algorithms, such as non-dominated sort- ing genetic algorithm （NSGA-II） and strength Pareto evolutionary algorithm （SPEA2）. However, they can suffer from having a slow convergence speed. This paper proposes a new indicatorbased multi-objective optimization algorithm, namely, the multi- objective shuffled frog leaping algorithm based on the ε indicator （ε-MOSFLA）. This algorithm adopts a memetic meta-heuristic, namely, the SFLA, which is characterized by the powerful capability of global search and quick convergence as an evolutionary strategy and a simple and effective E-indicator as a fitness assignment scheme to conduct the search procedure. Experimental results, in comparison with other representative indicator-based MOEAs and traditional Pareto-based MOEAs on several standard test problems with up to 50 objectives, show that ε-MOSFLA is the best algorithm for solving many-objective optimization problems in terms of the solution quality as well as the speed of convergence.     

基于SFLA-Kriging算法的三维地质建模

Kriging方法可对离散数据点进行内插和外推,近年来在地质、测绘各方面得到了普遍应用,但Kriging方法中变异函数理论模型的选择和实验变异函数参数的设定大部分依赖于地质工作人员的专业技能,具有一定的客观性. 引入混合蛙跳算法,对Kriging实验变异函数进行优化,提出SFLA-Kriging算法并结合某露天矿钻孔数据进行三维建模. 实验结果标明,SFLA-Kriging算法与传统Kriging方法相比,克服了一般方法的局限性,误差降低27.89%、三维地质模型精度更高.     

A ε-indicator-based shuffled frog leaping algorithm for many-objective optimization problems

Many-objective optimization problems take challenges to multi-objective evolutionary algorithms. A number of non-dominated solutions in population cause a difficult selection towards the Pareto front. To tackle this issue, a series of indicatorbased multi-objective evolutionary algorithms(MOEAs) have been proposed to guide the evolution progress and shown promising performance. This paper proposes an indicator-based manyobjective evolutionary algorithm called ε-indicator-based shuffled frog leap...     

基于分群粒子群优化的传感器调度方法

对面向目标跟踪任务的多传感器多任务调度问题进行研究。考虑到探测目标的运动特性,采用扩展卡尔曼滤波法实施目标跟踪,以成功调度任务的综合优先权、目标跟踪精度以及传感器网络的能源消耗为指标,建立了多传感器多任务调度的混合整数规划模型。提出一种基于分群机制的分群粒子群算法对模型进行求解,该方法通过粒子分群,提高对问题域的全局搜索能力,避免算法过快收敛和发生早熟。实验结果表明,该方法用于传感器调度问题,具有较好的求解性能。     

Grover quantum searching algorithm based on weighted targets

The current Grover quantum searching algorithm cannot identify the difference in importance of the search targets when it is applied to an unsorted quantum database, and the probability for each search target is equal. To solve this problem, a Grover searching algorithm based on weighted targets is proposed. First, each target is endowed a weight coefficient according to its importance. Applying these different weight coefficients, the targets are represented as quantum superposition states. Second, the novel Grover searching algorithm based on the quantum superposition of the weighted targets is constructed. Using this algorithm, the probability of getting each target can be approximated to the corresponding weight coefficient, which shows the flexibility of this algorithm. Finally, the validity of the algorithm is proved by a simple searching example.