简单高效耦合策略的粒子群混合算法

建立了评判耦合策略优劣的定量分析方法,发现了现有带中间启动局部搜索(local search,LS)的粒子群混合算法的不足,进而提出一种简单高效的耦合策略.基于该策略,在全局性能优异的综合学习粒子群(comprehensive learning particle swarm optimizer,CLPSO)算法中引入具有快速收敛性能的传统LS方法,提出了带LS的CLPSO混合算法(CLPSO hybrid algorithm with LS,CLPSO-LS).以10维、30维和50维的11个标准函数,对基于不同LS方法的4种混合算法的性能进行大量测试.结果表明,4种CLPSO-LS混合算法的性能均优于CLPSO算法,验证了混合算法的有效性.其中,基于BFGS拟牛顿方法的混合算法的综合性能最优.最后,与8种先进粒子群算法的对比,结果表明CLPSO-LS混合算法作为一种改进CLPSO算法,其性能优于包括已有CLPSO改进算法在内的对比算法,进一步验证了其优越性.     

Adaptive fuzzy particle swarm optimization for global optimization of multimodal functions

This paper proposes an adaptive fuzzy PSO (AFPSO) algorithm, based on the standard particle swarm optimization (SPSO) algorithm. The proposed AFPSO utilizes fuzzy set theory to adjust PSO acceleration coefficients adaptively, and is thereby able to improve the accuracy and efficiency of searches. Incorporating this algorithm with quadratic interpolation and crossover operator further enhances the global searching capability to form a new variant, called AFPSO-QI. We compared the proposed AFPSO and its variant AFPSO-QI with SPSO, quadratic interpolation PSO (QIPSO), unified PSO (UPSO), fully informed particle swarm (FIPS), dynamic multi-swarm PSO (DMSPSO), and comprehensive learning PSO (CLPSO) across sixteen benchmark functions. The proposed algorithms performed well when applied to minimization problems for most of the multimodal functions considered.     

Adaptive comprehensive learning particle swarm optimization with cooperative archive

Comprehensive learning particle swarm optimization (CLPSO) enhances its exploration capability by exploiting all other particles’ historical information to update each particle’s velocity. However, CLPSO adopts a set of fixed comprehensive learning (CL) probabilities to learn from other particles, which may impair its performance on complex optimization problems. To improve the performance and adaptability of CLPSO, an adaptive mechanism for adjusting CL probability and a cooperative archive (CA) are combined with CLPSO, and the resultant algorithm is referred to as adaptive comprehensive learning particle swarm optimization with cooperative archive (ACLPSO-CA). The adaptive mechanism dividing the CL probability into three levels and adjusting the individual particle’s CL probability level dynamically according to the performance of the particles during the optimization process. The cooperative archive is employed to provide additional promising information for ACLPO-CA and itself is updated by the cooperative operation of the current swarm and archive. To evaluate the performance of ACLPSO-CA, ACLPSO-CA is tested on CEC2013 test suite and CEC2017 test suite and compared with seven popular PSO variants. The test results show that ACLPSO-CA outperforms other comparative PSO variants on the two CEC test suites. ACLPSO-CA achieves high performance on different types of benchmark functions and exhibits high adaptability as well. In the end, ACLPSO-CA is further applied to a radar system design problem to demonstrate its potential in real-life optimization.     

Distributed learning particle swarm optimizer for global optimization of multimodal problems

Particle swarm optimizer (PSO) is an effective tool for solving many optimization problems. However, it may easily get trapped into local optimumwhen solving complex multimodal nonseparable problems. This paper presents a novel algorithm called distributed learning particle swarm optimizer (DLPSO) to solve multimodal nonseparable problems. The strategy for DLPSO is to extract good vector information from local vectors which are distributed around the search space and then to form a new vector which can jump out of local optima and will be optimized further. Experimental studies on a set of test functions show that DLPSO exhibits better performance in solving optimization problems with few interactions between variables than several other peer algorithms.     

Comprehensive learning particle swarm optimizer for solving multiobjective optimization problems

This article presents an approach to integrate a Pareto dominance concept into a comprehensive learning particle swarm optimizer (CLPSO) to handle multiple objective optimization problems. The multiobjective comprehensive learning particle swarm optimizer (MOCLPSO) also integrates an external archive technique. Simulation results (obtained using the codes made available on the Web at http://www.ntu.edu.sg/home/EPNSugan) on six test problems show that the proposed MOCLPSO, for most problems, is able to find a much better spread of solutions and faster convergence to the true Pareto‐optimal front compared to two other multiobjective optimization evolutionary algorithms. © 2006 Wiley Periodicals, Inc. Int J Int Syst 21: 209–226, 2006.     

Group counseling optimization

In this paper, a new population-based optimization algorithm – which we call a group counseling optimizer (GCO) – is developed. Instead of mimicking the behavior of living organisms such as birds, fish, ants, and bees, we emulate the behavior of human beings in life problem solving through counseling within a group. This is motivated by the fact that the human's thinking is often predicted to be the most reasonable and influential. The inspiration radiates from the various striking points of analogy between group counseling and population-based optimization which we have discovered, as elucidated in Section 2. The algorithm is tested using seven unrotated benchmark functions and five rotated ones. Further, a comparison is made with the comprehensive learning particle swarm optimizer (CLPSO) which outperforms many other variants of the particle swarm optimizer. Using new eight composition benchmark functions, another comparison is made with the BI-population covariance matrix adaptation evolution strategy with alternative restart strategy (NBIPOP-_aCMA-ES) which is the winner of the competition on real-parameter single objective optimization at IEEE CEC-2013. The results are all highly promising, demonstrating the soundness and efficacy of the proposed approach. GCO is applied to real-world application which is spacecraft trajectory design problem. Also, the results show that GCO outperforms well-known optimizers.     

基于竞争学习的粒子群优化算法设计及应用

针对传统PSO算法容易陷入局部最优的问题,提出一种基于竞争学习的粒子群优化算法(CLPSO);在CLPSO中,首先通过动态计算粒子的适应度值将种群分成优选、合理和疏离3个子群;其次,根据3个子群中粒子的进化特性,为3个子群分别设计了不同的更新变异方式;然后,利用12个基准测试函数对算法的性能进行了验证;实验结果表明,所提的竞争学习策略能够有效克服经典PSO算法在处理复杂多峰问题时容易陷入局部最优的缺陷;最后,利用CLPSO算法优化模糊神经网络的参数设计CLPSO-FNN算法,并利用其建立出水氨氮软测量模型,实验表明,CLPSO-FNN软测量模型能够更精确、更实时地测量出水氨氮浓度.     

Couple-based particle swarm optimization for short-term hydrothermal scheduling

A novel couple-based particle swarm optimization (CPSO) is presented in this paper, and applied to solve the short-term hydrothermal scheduling (STHS) problem. In CPSO, three improvements are proposed compared to the canonical particle swarm optimization, aimed at overcoming the premature convergence problem. Dynamic particle couples, a unique sub-group structure in maintaining population diversity, is adopted as the population topology, in which every two particles compose a particle couple randomly in each iteration. Based on this topology, an intersectional learning strategy using the partner learning information of last iteration is employed in every particle couple, which can automatically reveal useful history information and reduce the overly rapid evolution speed. Meanwhile, the coefficients of each particle in a particle couple are set as distinct so that the particle movement patterns can be described and controlled more precisely. In order to demonstrate the effectiveness of our proposed CPSO, the algorithm is firstly tested with four multimodal benchmark functions, and then applied to solve an engineering multimodal problem known as STHS, in which two typical test systems with four different cases are tested, and the results are compared with those of other evolutionary methods published in the literature.     

Particle Swarm Optimization with Chaos-based Initialization for Numerical Optimization

Particle swarm optimization (PSO) is a population based swarm intelligence algorithm that has been deeply studied and widely applied to a variety of problems. However, it is easily trapped into the local optima and premature convergence appears when solving complex multimodal problems. To address these issues, we present a new particle swarm optimization by introducing chaotic maps (Tent and Logistic) and Gaussian mutation mechanism as well as a local re-initialization strategy into the standard PSO algorithm. On one hand, the chaotic map is utilized to generate uniformly distributed particles to improve the quality of the initial population. On the other hand, Gaussian mutation as well as the local re-initialization strategy based on the maximal focus distance is exploited to help the algorithm escape from the local optima and make the particles proceed with searching in other regions of the solution space. In addition, an auxiliary velocity-position update strategy is exclusively used for the global best particle, which can effectively guarantee the convergence of the proposed particle swarm optimization. Extensive experiments on eight well-known benchmark functions with different dimensions demonstrate that the proposed PSO is superior or highly competitive to several state-of-the-art PSO variants in dealing with complex multimodal problems.     

Comprehensive learning particle swarm optimization for reactive power dispatch

Reactive power dispatch (RPD) is an optimization problem that reduces grid congestion by minimizing the active power losses for a fixed economic power dispatch. RPD reduces power system losses by adjusting the reactive power control variables such as generator voltages, transformer tap-settings and other sources of reactive power such as capacitor banks and provides better system voltage control, resulting in an improved voltage profile, system security, power transfer capability and over all system operation. In this paper, RPD problem is solved using particle swarm optimization (PSO). To overcome the drawback of premature convergence in PSO, a learning strategy is introduced in PSO, and this approach called, comprehensive learning particle swarm optimization (CLPSO) is also applied to this problem and a comparison of results is made between these two. Three different test cases have been studied such as minimization of real power losses, improvement of voltage profile and enhancement of voltage stability through a standard IEEE 30-bus and 118-bus test systems and their results have been reported. The study results show that the approaches developed are feasible and efficient.     

A self-learning particle swarm optimizer for global optimization problems

Particle swarm optimization (PSO) has been shown as an effective tool for solving global optimization problems. So far, most PSO algorithms use a single learning pattern for all particles, which means that all particles in a swarm use the same strategy. This monotonic learning pattern may cause the lack of intelligence for a particular particle, which makes it unable to deal with different complex situations. This paper presents a novel algorithm, called self-learning particle swarm optimizer (SLPSO), for global optimization problems. In SLPSO, each particle has a set of four strategies to cope with different situations in the search space. The cooperation of the four strategies is implemented by an adaptive learning framework at the individual level, which can enable a particle to choose the optimal strategy according to its own local fitness landscape. The experimental study on a set of 45 test functions and two real-world problems show that SLPSO has a superior performance in comparison with several other peer algorithms.     

一种快速多种群的粒子群多模优化算法

针对粒子群多模优化问题中存在的易早熟、收敛速度慢及寻优精度低等问题,提出了一种快速多种群的粒子群多模优化算法。首先采用动态半径及种群划分策略,避免了多种群区域重叠问题;然后引入拓扑机制,使种群内粒子在速度上保持同步,以群落为单位在解空间上飞行,加快进化速度;同时增加种群之间的交流,在多样性和快速收敛之间达到平衡;最后采用随机权重、异步变化因子及种群淘汰策略,提高算法的搜索能力和学习能力。通过几个典型测试函数的实验结果表明,该算法具有较好的多模态寻优率,在收敛速度和精度等方面均有提高。     

基于动态种群和广义学习的粒子群算法及应用

为了提升粒子跳出局部最优解的能力,本文提出一种动态种群和广义学习粒子群算法(DCPSO).在算法运行过程中,引入种群增加策略和减少策略以提升种群的多样性,进而提升粒子跳出局部最优解的能力;同时引入广义学习策略以增加粒子飞向全局最优位置的概率.在基准函数的测试中,结果显示DCPSO算法比其它PSO算法有更好的性能;在实际...     

一种求解复杂多峰问题的新型粒子群优化算法研究

为提升标准粒子群算法在求解多峰复杂问题时收敛速度慢和极易陷入局部最优解等缺点, 提出一种基于球形坐标的分类学习策略粒子群算法(CLPSO-HC)。该算法给出种群运行较差粒子的确定方法, 将运行较差的粒子进行分类, 并对每类粒子给出相应的学习策略, 保证种群跳出局部最优解的能力。为减少外界扰动, 将粒子速度和位置的更新在球形坐标中进行, 提升了种群向最优解飞行的概率。对三个典型测试函数进行仿真实验, 所得结果表明CLPSO-HC相比其他几种算法有较好的收敛性。因此, CLPSO-HC可以作为求解复杂多峰问题的有效算法。     

随机微粒群优化算法

微粒群优化算法是继蚁群算法之后又一种新的基于群体智能的启发式全局优化算法,其概念简单、易于实现,而且具有良好的优化性能,目前已在许多领域得到应用。但在求解高维多峰函数寻优问题时,算法易陷入局部最优。该文结合模拟退火算法的思想,提出了一种改进的微粒群优化算法——随机微粒群优化算法,该算法在运行初期具有更强的探索能力,可以避免群体过早陷入局部极值点。基于典型高维复杂函数的仿真结果表明,与基本微粒群优化算法相比,该混合算法具有更好的优化性能。     

Comprehensive learning particle swarm optimization based memetic algorithm for model selection in short-term load forecasting using support vector regression

BackgroundShort-term load forecasting is an important issue that has been widely explored and examined with respect to the operation of power systems and commercial transactions in electricity markets. Of the existing forecasting models, support vector regression (SVR) has attracted much attention. While model selection, including feature selection and parameter optimization, plays an important role in short-term load forecasting using SVR, most previous studies have considered feature selection and parameter optimization as two separate tasks, which is detrimental to prediction performance.ObjectiveBy evolving feature selection and parameter optimization simultaneously, the main aims of this study are to make practitioners aware of the benefits of applying unified model selection in STLF using SVR and to provide one solution for model selection in the framework of memetic algorithm (MA).MethodsThis study proposes a comprehensive learning particle swarm optimization (CLPSO)-based memetic algorithm (CLPSO-MA) that evolves feature selection and parameter optimization simultaneously. In the proposed CLPSO-MA algorithm, CLPSO is applied to explore the solution space, while a problem-specific local search is proposed for conducting individual learning, thereby enhancing the exploitation of CLPSO.ResultsCompared with other well-established counterparts, benefits of the proposed unified model selection problem and the proposed CLPSO-MA for model selection are verified using two real-world electricity load datasets, which indicates the SVR equipped with CLPSO-MA can be a promising alternative for short-term load forecasting.     

Integrated Learning Particle Swarm Optimizer for global optimization

This study proposes a novel Integrated Learning Particle Swarm Optimizer (ILPSO), for optimizing complex multimodal functions. The algorithm modifies the learning strategy of basic PSO to enhance the convergence and quality of solution. The ILPSO approach finds the diverged particles and accelerates them towards optimal solution. This novel study also introduces the particle’s updating strategy based on hyperspherical coordinates system. This is especially helpful in handling evenly distributed multiple minima. The proposed technique is integrated with comprehensive learning strategy to explore the solution effectively. The performance comparison is carried out against different high quality PSO variants on the set of standard benchmark functions with and without coordinate rotation and with asymmetric initialization. Proposed ILPSO algorithm is efficient in terms of convergence rate, solution accuracy, standard deviation, and computation time compared with other PSO variants. Friedman non-parametric statistical test followed by Dunn post analysis results indicate that the proposed ILPSO algorithm is an effective technique to optimize complex multimodal functions of higher dimension.     

Adaptive cooperative particle swarm optimizer

An Adaptive Cooperative Particle Swarm Optimizer (ACPSO) is introduced in this paper, which facilitates cooperation technique through the usage of the Learning Automata (LA) algorithm. The cooperative strategy of ACPSO optimizes the problem collaboratively and evaluates it in different contexts. In the ACPSO algorithm, a set of learning automata associated with dimensions of the problem are trying to find the correlated variables of the search space and optimize the problem intelligently. This collective behavior of ACPSO will fulfill the task of adaptive selection of swarm members. Simulations were conducted on four types of benchmark suites which contain three state-of-the-art numerical optimization benchmark functions in addition to one new set of active coordinate rotated test functions. The results demonstrate the learning ability of ACPSO in finding correlated variables of the search space and also describe how efficiently it can optimize the coordinate rotated multimodal problems, composition functions and high-dimensional multimodal problems.     

基于食物链机制的动态多物种粒子群算法

针对粒子群优化(PSO)算法在解决多峰函数时容易陷入局部最优的问题,提出了一种基于食物链机制的动态多物种粒子群(DSPSO)算法。受生物界的启发,引入食物链机制来保证种群的多样性,并结合繁殖机制使得算法具有良好的优化性能。食物链机制中,整个标榜群被分为几个子种群,每个子种群都能够捕食另外一个子种群。通过一定概率发生的捕食现象使得标榜群得以进化,剔除对种群贡献小的粒子,并通过繁殖策略生成新的粒子。种群通过不断地进化保证了种群的多样性,同时通过剔除较差粒子的误导作用使算法的进化更有效率。为了验证算法的有效性,选择了包括偏移函数、旋转函数在内的10个测试函数来测试DSPSO算法的性能。实验结果表明DSPSO算法有着良好的寻优性能。与PSO、局部版本的粒子群(LPSO)算法、动态多群粒子群(DMS-PSO)算法和全面学习粒子群(CLPSO)算法相比,DSPSO算法不仅能够得到较高精度的解,而且还具有较高的可信度。     

引入多级扰动的混合型粒子群优化算法

为解决粒子群优化算法易陷入局部最优值的问题,提出一种引入多级扰动的混合型粒子群优化算法.该算法结合两种经典改进粒子群优化算法的优点,即带惯性参数的标准粒子群优化算法和带收缩因子的粒子群优化算法,在此基础上,引入多级扰动机制：在更新粒子位置时,引入一级扰动,使粒子对解空间的遍历能力得到加强;若优化过程陷入“局部最优”的情况,则引入二级扰动,使得优化过程继续,从而摆脱局部最优值.使用了6个测试函数——Sphere函数、Ackley函数、Rastrigin函数、Styblinski-Tang函数、Duadric函数及Rosenbrock函数来对所提出的混合型粒子群优化算法进行仿真运算和对比验证.模拟运算的结果表明：所提出的混合型粒子群优化算法在对测试函数进行仿真时,其收敛精度和收敛速度都优于另外两种经典的改进粒子群优化算法;另外,在处理多峰函数时,本算法不易被局部最优值所限制.