一种求解连续对象优化问题的改进蚁群算法

蚁群算法在搜索过程中容易陷入局部最优解，且不适用于连续对象优化问题。文章针对这些问题．采用信息量变异、引入微粒群操作等方法进行改进，提出了一种引入微粒群操作的改进蚁群算法，并应用于求解连续对象优化问题。对几个典型复杂连续函数优化问题的测试研究表明，该改进算法不仅跳出局部最优解的能力更强．而且能较快地收敛到全局最优解，表明了算法的有效性。     

旅行商问题的改进差分进化方法

TSP(Traveling Salesman Problem)旅行商问题是一类典型的NP完全问题,目前大多采用遗传算法求解.差分进化算法(Differential Evolution Algorithm, DE)作为一种新型的进化算法,与遗传算法有很多相似之处.提出用改进的差分进化算法解决TSP问题.采用基于整数序规范的辅助算子解决变异问题,并引入刘海交叉算子.实验结果表明该方法有效地提高了算法的收敛速度与寻优质量,表现出了良好的特性.     

OFDM多用户系统中一种改进的自适应资源分配算法

针对正交频分复用(OFDM)多用户系统中一些智能算法存在收敛速度较慢且精度不高的问题,研究了把差分进化算法的变异与交叉行为引入人工鱼群算法中,以改进其随机行为。在此基础上,提出了一种改进的OFDM自适应资源分配算法。该算法先在公平度门限下分配子载波,再通过改进的人工鱼群算法进行功率分配。仿真结果表明,所提算法达到最优解时迭代次数有较大减少,同时搜索精度有所提高,在保证用户公平度的同时,提高了系统容量。     

雷达干扰资源的粒子群分配技术研究

粒子群算法是一种群智能的优化算法,其理论来源于人工生命和演化计算理论.该论文建立了雷达干扰资源分配的数学模型,基于粒子群算法,采用了交叉策略.为了避免陷入局部最优,该论文还采用了进化策略,从而改进了粒子群分配技术.最后,仿真实现了干扰资源的优化分配并详细分析了仿真结果.     

基于粒子群优化算法的可再生能源功率预测模型设计

为了降低可再生能源机组波动性对电网运行的影响,基于模型预测的思想对当前应用于功率预测的自适应小波网络（AWNN）参数迭代求解方法进行了优化。使用与差分进化相融合的改进粒子群算法PSO-DE来替代传统梯度下降算法,优化了AWNN网络的迭代方式。PSO-DE算法一方面借助差分进化算法中的遗传、变异及交叉机制提升了粒子种群间的信息流通效率;另一方面则通过惯性权重因子和束缚机制将粒子束缚在指定区间内波动,从而避免了算法在优化求解时陷入局部最优解的情况。基于广东某地区的光伏发电数据集进行了算法仿真,结果表明在引入PSO-DE算法后模型的主要性能指标显著提升,有效提高了可再生能源的功率预测精度。     

基于粒子群算法的软件可靠性分配问题研究

针对软件可靠性分配中不易求解全局最优解这一问题,将可靠性指标分配到每个模块中,并利用改进的粒子群优化算法来搜索模型的最优解.实验结果表明,改进的粒子群优化算法在求解软件可靠性分配问题时的效果优于遗传算法等其他智能优化算法.     

基于GIS和差分进化粒子群的变电站选址方法

文中提出了一种基于地理信息系统(GIS)和差分进化改进粒子群的配电网变电站优化选址方法。该方法利用GIS确定变电站数量,基于变电站投资运行费用建立有约束条件的目标函数,采用粒子群算法进行变电站选址优化。针对粒子群算法易陷入局部最优且收敛速度慢的问题,借助差分进化引入两个变异因子,在提升粒子群算法收敛速度的同时,避免其陷入局部最优。算例分析结果表明,该方法具有较好的寻优能力和收敛特性,能够有效实现变电站选址优化。     

一种求解约束优化问题的自适应差分进化算法

自适应算子选择方式已被用于差分进化算法求解全局优化问题及多目标优化问题,然而在求解约束优化时难于为自适应算子选择方式找到一种方式来恰当分配信用。为此,本文提出了一种基于混合种群的自适应适应值方式来对约束优化问题中变异策略进行信用分配并采用概率匹配方法自适应选择差分变异策略,同时对算法变异缩放因子与交叉率进行自适应设置提高算法的成功率。实验结果表明算法在求解约束优化问题相比于CODEA／OED, ATMES,εBBO-dm,COMDE 以及εDE算法有较高的收敛精度及收敛速度,同时验证了自适应方式的有效性。该算法可用于预报、质量控制、会计过程等科学和工程应用领域。     

基于差分进化算法的多用户OFDM自适应资源分配

针对多用户正交频分复用系统自适应资源分配问题,提出一种改进的子载波和基于差分进化算法的功率自适应分配算法.该算法首先在均等功率下进行子载波分配,然后通过添加约束条件检测改进步骤,改进差分进化算法,并采用该算法根据设置的兼顾用户公平性与系统容量的目标函数,全局寻优实现用户间的功率分配.仿真结果表明,算法在低算法复杂度及兼顾用户公平性的情况下实现了较高的系统容量提升,证明其有效性.     

多种群协方差学习差分进化算法

种群多样性与交叉算子在差分进化(DE)算法求解全局优化问题中具有重要作用,该文提出一种多种群协方差学习差分进化(MCDE)算法。首先,采用多种群机制的种群结构,利用每一子种群结合相应的变异策略保证进化过程个体多样性。然后,通过种群间的协方差学习,为交叉操作建立一个适当旋转的坐标系统;同时,使用自适应控制参数来平衡种群的勘测与收敛能力。最后,在单峰函数、多峰函数、偏移函数和高维函数的25个基准测试函数上进行测试,并同其他先进的进化算法对比,实验结果表明该文算法相较于其他算法在求解全局优化问题上达到最优效果。     

一种精英反向学习的粒子群优化算法

为解决传统粒子群优化算法易出现早熟的不足,提出了精英反向学习策略,引入精英粒子,采用反向学习生成其反向解,扩大搜索区域的范围,可增强算法的全局勘探能力.同时,为避免最优粒子陷入局部最优而导致整个群体出现搜索停滞,提出了差分演化变异策略,采用差分演化算法搜索最优粒子的邻域空间,可增强算法的局部开采能力.在14个测试函数上将本文算法与多种知名的PSO算法进行对比,实验结果表明本文算法在解的精度与收敛速度上更优.     

Synthesis of linear antenna arrays using Jaya,self-adaptive Jaya and chaotic Jaya algorithms

This work aims to show the effectiveness of a recently proposed population-based optimization algorithm known as Jaya algorithm and its variants named as self-adaptive Jaya algorithm (SJaya) and Chaotic-Jaya (CJaya) algorithm to synthesize linear antenna arrays which are widely used in the communication systems. Three case studies of synthesis of linear antenna arrays are formulated by considering different topologies. In addition, two case studies of synthesis of dipole antenna arrays are formulated and all the case studies are solved using Jaya, SJaya and CJaya algorithms. The results of Jaya, SJaya and CJaya algorithms are compared with those of cat swarm optimization (CSO) algorithm, particle swarm optimization (PSO), Cauchy mutated cat swarm optimization (CMCSO) algorithm, harmony search based differential evolution algorithm (HSDEA), dynamic differential evolution algorithm (DDE), improved genetic algorithm (IGA), modified real genetic algorithm (MGA) and accelerated particle swarm optimization (APSO) algorithm. The Jaya, SJaya and CJaya algorithms achieved a better side lobe level suppression as compared to the other optimization algorithms while maintaining the vital antenna parameters within permissible limits.     

Design of very thin wide band absorbers using modified local best particle swarm optimization

A method of using particle swarm optimization (PSO) algorithm to design electromagnetic absorber is presented. To demonstrate effectiveness of the PSO algorithm three different design cases are optimized. To reduce the local minimum traps, a modified local search strategy is employed. Each design problem is optimized using genetic algorithm (GA) and four variants of PSO algorithms, namely global PSO (gbest), local PSO (lbest), comprehensive learning PSO (CLPSO), and modified local PSO (MLPSO). The results clearly show that the MLPSO is a robust, fast, and useful optimization tool for designing absorbers. A seven-layer absorber achieved by this method has reflection coefficient below 18.7 dB from VHF to 20 GHz.     

Craziness based particle swarm optimization algorithm for IIR system identification problem

In this paper a variant of particle swarm optimization (PSO), called craziness based particle swarm optimization (CRPSO) technique is applied to the infinite impulse response (IIR) system identification problem. A modified version of PSO, called CRPSO adopts a number of random variables for having better and faster exploration and exploitation in multidimensional search space. Incorporation of craziness factor in the basic velocity expression of PSO not only brings diversity in particles but also ensures convergence to optimal solution. The proposed CRPSO based system identification approach has alleviated from the inherent drawbacks of premature convergence and stagnation, unlike real coded genetic algorithm (RGA), particle swarm optimization (PSO) and differential evolution (DE). The simulation results obtained for some well known benchmark examples justify the efficacy of the proposed system identification approach using CRPSO over RGA, PSO and DE in terms of convergence speed, unknown plant coefficients and mean square error (MSE) values produced for both the same order and reduced order models of adaptive IIR filters.     

Multi-objective test case prioritization based on multi-population cooperative particle swarm optimization

Test case prioritization (TCP) technique is an efficient approach to improve regression testing activities. With the continuous improvement of industrial testing requirements, traditional single-objective TCP is limited greatly, and multi-objective test case prioritization (MOTCP) technique becomes one of the hot topics in the field of software testing in recent years. Considering the problems of traditional genetic algorithm (GA) and swarm intelligence algorithm in solving MOTCP problems, such as falling into local optimum quickly and weak stability of the algorithm, a MOTCP algorithm based on multi-population cooperative particle swarm optimization (MPPSO) was proposed in this paper. Empirical studies were conducted to study the influence of iteration times on the proposed MOTCP algorithm, and compare the performances of MOTCP based on single-population particle swarm optimization (PSO) and MOTCP based on non-dominated sorting genetic algorithm II (NSGA-II) with the MOTCP algorithm proposed in this paper. The results of experiments show that the test case prioritization algorithm based on MPPSO has stronger global optimization ability, is not easy to fall into local optimum, and can solve the MOTCP problem better than test case prioritization algorithm based on the single-population PSO and NSGA-II.     

基于混合PSO算法的加速度计快速标定

针对粒子群优化算法(PSO)在加速度计标定中存在早熟及陷入局部最优的不足,提出了基于差分进化(DE)的双种群信息共享及并行进化的混合PSO算法,并将该算法应用于加速度计快速标定。为提高混合算法的优化性能,提出了一种平衡DE算法全局探索和局部开发能力的加权变异算子,将Logistic函数的非线性特性引入到PSO算法惯性权重和DE算法加权系数的动态调整中。基准测试函数仿真表明所提出的混合算法在收敛速度、收敛精度、全局搜索性能和鲁棒性等方面明显优于PSO、DE算法;加速度计标定仿真结果表明,提出的混合算法能有效提高加速度计的标定精度。     

基于PPSO-GRADS算法的盲信号分离

该文将联姻策略应用在粒子群算法中,提出一种并行分阶段的基于粒子群优化算法的盲信号分离方法(PPSO-GRADS)。该算法具有收敛速度快,分离精度高的特点。通过仿真证明该算法比未使用联姻策略的粒子群算法有更好的性能,在收敛速度和分离效果上比传统的梯度算法,遗传算法都有较明显的改善。     

An effective parameter extraction method based on memetic differential evolution algorithm

This paper provides an effective method for parameter extraction of microelectronic devices and elements. A novel method, memetic differential evolution (MDE) algorithm, is proposed in this paper. By combining differential evolution (DE) algorithm, mutations in immune algorithm (IA), and special operators for parameter extraction, MDE possesses characteristics of high accuracy, stability, generality, and efficiency. The effectiveness of the method has been shown by two typical examples, including small-signal equivalent circuit models for an AlGaN/GaN HEMT device up to 40 GHz, as well as an equivalent circuit model for on-chip differential spiral inductors. In both cases, the initial values and parameter ranges of the elements in the equivalent circuits are hard to determine in optimization. The results and comparisons with Levenberg-Marquardt (LM) algorithm, genetic algorithm (GA), particle swarm optimization (PSO) algorithm and canonical DE algorithm, demonstrate the superiority of MDE in terms of accuracy and generality.     

无人机三维路径规划的粒子群混合算法

路径规划是无人机控制过程中的重要环节之一,现有基于粒子群等算法的传统路径规划方法存在容易陷入局部最优等问题,无法适应现实场景中复杂环境及高搜索速度的要求。针对已有方法的缺陷,提出了一种无人机路径规划的高性能细菌觅食-遗传-粒子群混合算法,以传统粒子群优化算法为基础,引入细菌觅食算法及遗传算法思想,提高算法计算速度与能力,同时考虑实际场景中无人机的运行约束,进一步提高了方法的可用性。最后,利用仿真实验验证了所提方法的有效性,并通过与传统方法对比证明了所提方法在运行时间、规划航程等方面的优越性。     

一种基于粒子群优化方法的改进量子遗传算法及应用

本文采用粒子群优化(PSO)方法代替量子门来更新量子比特状态,得到一种改进的量子遗传算法(QGA)——PSQGA,并根据QGA自身概率特性,引入了最优解方差函数来评价该算法的稳定性能.利用四种典型连续函数寻优问题和0/1背包问题,分别对PSQGA和改进的使用量子门的量子遗传算法(IQGA)进行了测试;并将它们应用到图像稀疏分解的实例中.结果表明,PSQGA算法的寻优能力及稳定性均优于IQGA,且具有更好的收敛性以及更强的连续空间搜索能力,适合于求解复杂优化问题.