Cellular particle swarm optimization

This paper proposes a cellular particle swarm optimization (CPSO), hybridizing cellular automata (CA) and particle swarm optimization (PSO) for function optimization. In the proposed CPSO, a mechanism of CA is integrated in the velocity update to modify the trajectories of particles to avoid being trapped in the local optimum. With two different ways of integration of CA and PSO, two versions of CPSO, i.e. CPSO-inner and CPSO-outer, have been discussed. For the former, we devised three typical lattice structures of CA used as neighborhood, enabling particles to interact inside the swarm; and for the latter, a novel CA strategy based on “smart-cell” is designed, and particles employ the information from outside the swarm. Theoretical studies are made to analyze the convergence of CPSO, and numerical experiments are conducted to compare the proposed algorithm with different variants of PSO. According to the experimental results, the proposed method performs better than other variants of PSO on benchmark test functions.     

A parameter selection strategy for particle swarm optimization based on particle positions

In this study, we found that engineering experience can be used to determine the parameters of an optimization algorithm. We came to this conclusion by analyzing the dynamic characteristics of PSO through a large number of experiments. We constructed a relationship between the dynamic process of particle swarm optimization and the transition process of a control system. A novel parameter strategy for PSO was proven in this paper using the overshoot and the peak time of a transition process. This strategy not only provides a series of flexible parameters for PSO but it also provides a new way to analyze particle trajectories that incorporates engineering practices. In order to validate the new strategy, we compared it with published results from three previous reports, which are consistent or approximately consistent with our new strategy, using a suite of well-known benchmark optimization functions. The experimental results show that the proposed strategy is effective and easy to implement. Moreover, the new strategy was applied to equally spaced linear array synthesis examples and compared with other optimization methods. Experimental results show that it performed well in pattern synthesis.     

利用粒子群算法优化SVM分类器的超参数

利用粒子群算法在求解组合优化问题时具有的全局搜索特性,设计并实现了支持向量机分类器中超参数的优选粒子群算法,扼要地叙述了算法实现中个体编码和适应度函数,通过在国际标准数据集上的实验验证了算法的有效性和高效性,最后列举了一些在上述工作基础上可开展的深入性工作。     

Non-parametric particle swarm optimization for global optimization

In recent years, particle swarm optimization (PSO) has extensively applied in various optimization problems because of its simple structure. Although the PSO may find local optima or exhibit slow convergence speed when solving complex multimodal problems. Also, the algorithm requires setting several parameters, and tuning the parameters is a challenging for some optimization problems. To address these issues, an improved PSO scheme is proposed in this study. The algorithm, called non-parametric particle swarm optimization (NP-PSO) enhances the global exploration and the local exploitation in PSO without tuning any algorithmic parameter. NP-PSO combines local and global topologies with two quadratic interpolation operations to increase the search ability. Nineteen (19) unimodal and multimodal nonlinear benchmark functions are selected to compare the performance of NP-PSO with several well-known PSO algorithms. The experimental results showed that the proposed method considerably enhances the efficiency of PSO algorithm in terms of solution accuracy, convergence speed, global optimality, and algorithm reliability.     

一种基于栅格的动态粒子数微粒群算法

微粒群算法的全局搜索性能容易受到局部极值点的影响,对此,提出一种基于栅格的动态粒子数微粒群算法(GB-DPPPSO).通过设计栅格信息更新策略、粒子产生策略和粒子消灭策略,可以根据种群搜索情况动态控制粒子数变化,以保持种群多样性,提高全局搜索性能,通过对4个典型数学验证函数的仿真实验,表明了该算法相对于DPPPSO)在全局搜索成功率和搜索效率两方面均有明显改进.     

求解高维函数优化的动态粒子群算法

针对基本粒子群优化算法对高维函数优化时搜索精度不高的缺陷,提出了一种动态粒子群优化算法。该算法采用了通过调节阈值对粒子运动轨迹进行动态改变的策略,使得粒子对周围环境的适应能力不受进化代数的影响,从而保证了算法在迭代后期仍具有较强的搜索能力。实验结果表明,与文献算法相比,该算法在处理高维函数优化时具有更强的寻优能力和更高的搜索精度。     

Stochastic convergence analysis and parameter selection of the standard particle swarm optimization algorithm

This letter presents a formal stochastic convergence analysis of the standard particle swarm optimization (PSO) algorithm, which involves with randomness. By regarding each particle's position on each evolutionary step as a stochastic vector, the standard PSO algorithm determined by non-negative real parameter tuple {ω,c₁,c₂} is analyzed using stochastic process theory. The stochastic convergent condition of the particle swarm system and corresponding parameter selection guidelines are derived.     

改进的粒子群算法

为改善基本粒子群算法的搜索性能,针对粒子群算法随机性较强、收敛较慢的问题,利用数学中的外推技巧给出了两个新的粒子位置更新公式,由此构造出一种新的算法--强引导型粒子群算法.新算法对粒子位置更新加以引导,试图减少算法的随机性以提高搜索效率.用4个基准函数对新算法进行试验,结果表明,新算法在稳定性和收敛性上优于基本粒子群算法.     

多目标微粒群优化算法

通过设计一种Pareto解集过滤器,并在此基础上给出多目标优化条件下的微粒群算法群体停滞判断准则,基于该准则提出了一种多目标微粒群优化算法。算法利用Pareto解集过滤器提高了候选解的多样性,并使用图形法将所提算法与经典的多目标优化进化算法在一组标准测试函数上进行了比较,结果表明算法具有更好的搜索效率。     

A study of particle swarm optimization particle trajectories

Particle swarm optimization (PSO) has shown to be an efficient, robust and simple optimization algorithm. Most of the PSO studies are empirical, with only a few theoretical analyses that concentrate on understanding particle trajectories. These theoretical studies concentrate mainly on simplified PSO systems. This paper overviews current theoretical studies, and extend these studies to investigate particle trajectories for general swarms to include the influence of the inertia term. The paper also provides a formal proof that each particle converges to a stable point. An empirical analysis of multi-dimensional stochastic particles is also presented. Experimental results are provided to support the conclusions drawn from the theoretical findings.     

混沌粒子群优化算法

将混沌融入到传统粒子群提出了混沌粒子群算法。该方法利用了混沌运动的遍历性、随机性以及对初值的敏感性等特性,根据早熟判断机制,在基本粒子群算法陷入早熟时,进行群体的混沌搜索．数值仿真结果表明该方法能跳出局部最优,进一步提高了计算精度和收敛速度,以及全局寻优能力。     

Detecting particle swarm optimization

Here, we propose a detecting particle swarm optimization (DPSO). In DPSO, we define several detecting particles that are randomly selected from the population. The detecting particles use the newly proposed velocity formula to search the adjacent domains of a settled position in approximate spiral trajectories. In addition, we define the particles that use the canonical velocity updating formula as common particles. In each iteration, the common particles use the canonical velocity updating formula to update their velocities and positions, and then the detecting particles do search in approximate spiral trajectories created by the new velocity updating formula in order to find better solutions. As a whole, the detecting particles and common particles would do the high‐performance search. DPSO implements the common particles' swarm search behavior and the detecting particles' individual search behavior, thereby trying to improve PSO's performance on swarm diversity, the ability of quick convergence and jumping out the local optimum. The experimental results from several benchmark functions demonstrate good performance of DPSO. Copyright © 2008 John Wiley & Sons, Ltd.     

新型粒子群优化算法

现有粒子群优化存在局部收敛、对可调参数敏感等缺点.基于此,本文提出一种新型粒子群优化算法.首先,通过分析社会个体对其环境的认知规律,简化粒子更新公式使粒子位置的更新仅与粒子自身速度及其邻域内最优粒子位置相关.其次,基于粒子速度划分提出一种优势粒子速度小概率变异、劣势速度随机赋值方法.最后,通过优化4个典型测试函数验证了本文所提方法在优化解的质量、算法收敛速度及鲁棒性等方面的优异性能.     

一种改进的粒子群优化算法

粒子群优化算法（PSO）是一种生物进化技术。依据粒子间的相互影响发现搜索空间中的最优解。通过分析基本PSO算法的进化方程,研究了一种具有更好收敛速度和全局收敛性的改进PSO算法。5个典型测试函数的仿真实验表明该改进算法是行之有效的。     

粒子群算法的改进策略述评

首先介绍了基本粒子群算法。其次分析出四类粒子群算法改进策略即混沌优化策略、调整参数取值策略、混合启发式算法策略、保持种群多样性策略;同时,对算法各种改进策略实现原理及实现方法进行介绍。第三对粒子群算法四类改进策略性能进行分析。最后对粒子群算法改进策略进行展望。     

Neutrino-like particle for particle swarm optimization

The real-world optimal problems frequently encountered by various industries are the nonlinear constrained optimization problems (NCOPs), where the constraints represent the limitations of practical resources. Many researchers have attempted to improve particle swarm optimization (PSO) in the past decades; however, in solving the NCOPs, the PSO-based approaches often cause premature convergences. The problem-specific constraints frequently generate many infeasible regions that block the movements of particles. The particles' behavior causes the exploration abilities of particles that tend to weaken along with time. The decreasing of exploration ability often comes from the particle becoming stagnant or moving unusefully. This study proposes a neutrino-like particle (NLP) with adaptive NLP hyperparameters that simulate the natural neutrino behavior. The proposed NLPs can be embedded in the PSO-based approaches for overcoming premature convergence. The experiment results demonstrate that all referenced PSO-based methods with the NLPs improved significantly compared with those without the NLPs to solve the NCOPs. All referenced PSO-based methods that embedded the NLPs also significantly outperform four recent strong algorithms in most IEEE CEC 2020 benchmark problems. Therefore, the proposed NLPs with adaptive NLP hyperparameters can effectively solve the premature convergences, reinforce the exploration ability, and maintain the exploitation capability for solving the NCOPs over the whole evolution process.     

改进的粒子群优化算法

针对基本粒子群优化算法(PSO)易陷入局部极值点,进化后期收敛慢,精度较差等缺点,提出了一种改进的粒子群优化算法.该算法用一种无约束条件的随机变异操作代替速度公式中的惯性部分,并且使邻居最优粒子有条件地对粒子行为产生影响,提高了粒子间的多样性差异,从而改善了算法能力.通过与其它算法的对比实验表明,该算法能够有效地进行全局和局部搜索,在收敛速度和收敛精度上都有显著提高.     

一种改进的粒子群算法

为了改进基本粒子群算法的搜索功能,针对粒子群算法易于陷入局部极值,进化后期的收敛速度慢和精度低等缺点,通过公式分析得到新的惯性权重调节方法,提出了一种新的改进粒子群算法。用几个经典测试函数进行实验,实验结果表明,新算法不仅具有更好的收敛精度,而且能更有效地进行全局搜索。     

粒子群优化算法的变形

分析了粒子群算法的惯性部分、个体认知部分和群体认知部分的作用,对粒子群算法迭代方程的各部分进行变形,获得了三种新形式的粒子群算法。用算例说明所得到的三个新的粒子群算法具有较好的优化能力。     

结合K-means的并行粒子群优化

通过给基于孤岛模型的并行粒子群算法引入K-means来进行子种群的划分。这不仅可以使一个子种群中的粒子位置相对集中,学习相对容易,而且可以提高搜索效率,使有限的时间用在最有效的搜索上。针对并行算法的特点,对其进行改进,在满足一定条件时才进行通信,这样可以避免无效通信,减少通信所花的时间。仿真结果证实,该算法具有较高的收敛速度和收敛精度。