Multi-swarm Particle Swarm Optimization Research Articles

Multiswarm Particle Swarm Optimization with Transfer of the Best Particle

We propose an improved algorithm, for a multiswarm particle swarm optimization with transfer of the best particle called BMPSO. In the proposed algorithm, we introduce parasitism into the standard particle swarm algorithm (PSO) in order to balance exploration and exploitation, as well as enhancing the capacity for global search to solve nonlinear optimization problems. First, the best particle guides other particles to prevent them from being trapped by local optima. We provide a detailed description of BMPSO. We also present a diversity analysis of the proposed BMPSO, which is explained based on the Sphere function. Finally, we tested the performance of the proposed algorithm with six standard test functions and an engineering problem. Compared with some other algorithms, the results showed that the proposed BMPSO performed better when applied to the test functions and the engineering problem. Furthermore, the proposed BMPSO can be applied to other nonlinear optimization problems.

The Inertia Weight Updating Strategies in Particle Swarm Optimisation Based on the Beta Distribution

The presented paper deals with the comparison of selected random updating strategies of inertia weight in particle swarm optimisation. Six versions of particle swarm optimization were analysed on 28 benchmark functions, prepared for the Special Session on Real-Parameter Single Objective Optimisation at CEC2013. The random components of tested inertia weight were generated from Beta distribution with different values of shape parameters. The best analysed PSO version is the multiswarm PSO, which combines two strategies of updating the inertia weight. The first is driven by the temporally varying shape parameters, while the second is based on random control of shape parameters of Beta distribution.

アダプティブ探索トポロジーを備えた多粒子群最適化(MSPSO)に関する研究

アダプティブ探索トポロジーを備えた多粒子群最適化(MSPSO)に関する研究

OptiFel: A Convergent Heterogeneous Particle Swarm Optimization Algorithm for Takagi–Sugeno Fuzzy Modeling

Data-driven design of accurate and reliable Takagi-Sugeno (T-S) fuzzy systems has attracted a lot of attention, where the model structures and parameters are important and often solved in an optimization framework. The particle swarm optimization (PSO) algorithm is widely applied in the field. However, the classical PSO suffers from premature convergence, and it is trapped easily into local optima, which will significantly affect the model accuracy. To overcome these drawbacks, we have developed a new T-S fuzzy system parameters searching strategy called OptiFel with a heterogeneous multiswarm PSO (MsPSO) to enhance the searching performance. MsPSO groups the whole population into multiple cooperative subswarms, which perform different search behaviors for the potential solutions. We have found that the multiple subswarms strategy proposed in this paper is greatly helpful for finding the optimal parameters suitable for the subspaces of the T-S fuzzy model. Our theoretical proof has also demonstrated that the cooperation among the subswarms can maintain a balance between exploration and exploitation to ensure the particles converge to stable points. Experimental results show that MsPSO performs significantly better than traditional PSO algorithms on six benchmark functions. With the improved MsPSO, OptiFel can generate a good fuzzy system model with high accuracy and strong generalization ability.

Exploration/exploitation of a hybrid‐enhanced MPSO‐GA algorithm on a fused CPU‐GPU architecture

SummaryRecent work in metaheuristic algorithms has shown that solution quality may be improved by composing algorithms with orthogonal characteristics. At the same time, fused CPU‐GPU systems have emerged as a unique platform on which to study these algorithms. Using metaheuristic algorithms requires striking a balance between local and global exploration. There are no governing rules, however, to balance these. In this paper, we study two population‐based metaheuristic algorithms: multi‐swarm particle swarm optimization (MPSO) and genetic algorithms (GAs). We investigate parallel MPSO variants with genetic operators to increase quality: crossover, mutation, swapping, and all three. We develop a hybrid parallel algorithm that combines a slower convergent algorithm (GA) with a faster one (MPSO). The hybrid achieves significant initial improvement in solution quality but no significant difference in the final average fitness. Executing the GA on the GPU requires approximately an order of magnitude less time (0.07–0.18 s) than on the CPU. Our platform is the AMD A8‐3530MX accelerated processing unit that packs four ×86 CPU cores and 80 very long instruction word GPU processing elements. We make effective use of the hierarchical memory structure on the accelerated processing unit, four‐way very long instruction word vectorization, and zero‐copy buffers. Copyright © 2014 John Wiley & Sons, Ltd.

Reverse Search Particle Swarm Optimization to Deal with Dynamic Optimization Problems

Multiswarm approaches are used in many literatures to deal with dynamic optimization problems (DOPs). Each swarm tries to find promising areas where usually peaks lie and many good results have been obtained. However, steep peaks are difficult to be found with multiswarm approaches , which hinders the performance of the algorithm to be improved furtherly. Aiming at the bottleneck, the paper introduces the idea of sequential niche technique to traditional multiswarm approach and thus proposes a novel algorithm called reverse space search multiswarm particle swarm optimization (RSPSO) for DOPs. RSPSO uses the information of the peaks found by coarse search of traditional multiswarm approach to modify the original fitness function. A newly generated subswarm - reverse search subswarm evolves with the modified fitness function, at the same time, other subswarms using traditional mltiswarm approach still evolve. Two kinds of subswarm evolve in cooperation. Reverse search subswarm tends to find much steeper peak and so more promising area where peaks lie is explored. Elaborated experiments on MPB show the introduction of reverse search enhances the ability of finding peaks , the performance of RSPSO significantly outperforms traditional multiswarm approaches and it has better robustness to adapt to dynamic environment with wider-range change severity.

Modified Multiobjective Dynamic Multi-Swarm Particle Swarm Optimization for Mineral Grinding Process

The mineral grinding process is a typical constrained multi-objective optimization problem for its two main goals are quality and quantity. This paper established a similarity criterion mathematical model and combined Multi-objective Dynamic Multi-Swarm Particle Swarm Optimization with modified feasibility rule to optimize the two goals. The simulation results showed that the results of high quality were achieved and the Pareto frontier was evenly distributed and the proposed approach is efficient to solve the multi-objective problem for the mineral grinding process.

AHPS2: An optimizer using adaptive heterogeneous particle swarms

Particle swarm optimization (PSO) has suffered from premature convergence and lacked diversity for complex problems since its inception. An emerging advancement in PSO is multi-swarm PSO (MS-PSO) which is designed to increase the diversity of swarms. However, most MS-PSOs were developed for particular problems so their search capability on diverse landscapes is still less than satisfactory. Moreover, research on MS-PSO has so far treated the sub-swarms as cooperative groups with minimum competition (if not none). In addition, the size of each sub-swarm is set to be fixed which may encounter excessive computational cost. To address these issues, a novel optimizer using Adaptive Heterogeneous Particle SwarmS (AHPS2) is developed in this research. In AHPS2, multiple heterogeneous swarms, each consisting of a group of homogenous particles having similar learning strategy, are introduced. Two complementary search techniques, comprehensive learning and a subgradient method, are studied. To best take advantage of the heterogeneous learning strategies, an adaptive competition strategy is proposed so the size of each swarm can be dynamically adjusted based on its group performance. The analyses of the swarm heterogeneity and the competition models are presented to validate the effectiveness. Furthermore, comparisons between AHPS2 and state-of-the-art algorithms are grouped into three categories: 36 regular benchmark functions (30-dimensional), 20 large-scale benchmark functions (1000-dimensional) and 3 real-world problems. Experimental results show that AHPS2 displays a better or comparable performance compared to the other swarm-based or evolutionary algorithms in terms of solution accuracy and statistical tests.

Multi-Swarm Particle Swarm Optimization Using Opposition-Based Learning and Application in Coverage Optimization of Wireless Sensor Network

Multi-Swarm Particle Swarm Optimization Using Opposition-Based Learning and Application in Coverage Optimization of Wireless Sensor Network

A MULTISWARM COMPETITIVE PARTICLE SWARM ALGORITHM FOR OPTIMIZATION CONTROL OF AN ETHYLENE CRACKING FURNACE

A fuzzy C-means (FCM) multiswarm competitive particle swarm optimization (FCMCPSO) algorithm is proposed, in which FCM clustering is used to divide swarms adaptively into different clusters. The large-scale swarms are according to the standard particle swarm optimization (PSO) algorithm, whereas the small-scale swarms search randomly in the neighborhood of the optimal solution to increase the probability of jumping out of the local optimization point. Within every cluster, the adaptive value gained by competitive learning is respectively found and arranged in order. Swarms of small adaptive value were integrated with the neighboring swarms of large adaptive value to search the optimal solution competitively by the swarms. The algorithm's validity was tested by benchmark functions and compared with other PSO algorithms. Furthermore, an integrated FCMCPSO-radial basis function neural network was studied for nonlinear system modeling and intelligent optimization control of cracking depth of an ethylene cracking furnace application in a chemical process.

Comparison of Three Different Curves Used in Path Planning Problems Based on Particle Swarm Optimizer

In path planning problems, the most important task is to find a suitable collision-free path which satisfies some certain criteria (the shortest path length, security, feasibility, smoothness, and so on), so defining a suitable curve to describe path is essential. Three different commonly used curves are compared and discussed based on their performance on solving a set of path planning problems. Dynamic multiswarm particle swarm optimizer is employed to optimize the necessary parameters for these curves. The results show that Bezier curve is the most suitable curve for producing path for the certain path planning problems discussed in this paper. Safety criterion is considered as a constrained condition. A new constraint handling method is proposed and compared with other two constraint handling methods. The results show that the new method has a better characteristic to improve the performance of algorithm.

Ventricular activity cancellation in electrograms during atrial fibrillation with constraints on residuals’ power

During atrial fibrillation (AF), cancellation of ventricular activity from atrial electrograms (AEG) is commonly performed by template matching and subtraction (TMS): a running template, built in correspondence of QRSs, is subtracted from the AEG to uncover atrial activity (AA). However, TMS can produce poor cancellation, leaving high-power residues. In this study, we propose to modulate the templates before subtraction, in order to make the residuals as similar as possible to the nearby atrial activity, avoiding high-power ones. The coefficients used to modulate the template are estimated by maximizing, via Multi-swarm Particle Swarm Optimization, a fitness function. The modulated TMS method (mTMS) was tested on synthetic and real AEGs. Cancellation performances were assessed using: normalized mean squared error (NMSE, computed on simulated data only), reduction of ventricular activity (VDR), and percentage of segments (PP) whose power was outside the standard range of the atrial power. All testings suggested that mTMS is an improvement over TMS alone, being, on simulated data, NMSE and PP significantly decreased while VDR significantly increased. Similar results were obtained on real electrograms (median values of CS1 recordings PP: 2.44 vs. 0.38 p<0.001; VDR: 6.71 vs. 8.15 p<0.001).

Intelligent damage identification method for large structures based on strain modal parameters

Early damage detection not only improves the safety and reliability of structures but also reduces maintenance cost. However, damage detection is difficult to implement in large structures under ambient excitation because of the limitation of sensors, the uncertainty of ambient excitation, and the global properties of modal frequencies and displacement modes. This paper proposes a new damage detection method that employs the real encoding multi-swarm particle swarm optimization algorithm and fitness functions evolved from strain modes to find the optimal match between measured and simulated modal parameters and to determine the actual condition of structures. The proposed method requires low-frequency modes and incomplete modes and does not require mass normalization of parameters, thus making the method suitable for nondestructive dynamic damage detection of large structures under ambient excitation. Taking a concrete guide wall structure as an example, this paper studied the global searching performance and the sensitivity of the proposed method. The efficiency of the proposed method was analyzed by using different noise levels and sensor numbers. Results show that the proposed method is effective and can be applied in many types of large structures.

A Multi-Swarm Particle Swarm Optimization to Solve DNA Encoding in DNA Computation

A Multi-Swarm Particle Swarm Optimization to Solve DNA Encoding in DNA Computation

Parallel Multi-Swarm PSO Based on K-Medoids and Uniform Design

PAM (Partitioning around Medoid) is introduced to divide the swarm into several different sub-populations. PAM is one of <em>k</em>-medoids clustering algorithms based on partitioning methods. It attempts to divide <em>n</em> objects into <em>k</em> partitions. This algorithm overcomes the drawbacks of being sensitive to the initial partitions in <em>k</em>-means algorithm. In the parallel PSO algorithms, the swarm needs to be divided into several different smaller swarms. This study can be excellently completed by PAM. The aim of clustering is that particles within the same sub-population are relative concentrative, so that they can be relatively easy to learn. The purposes of this strategy are that the limited time will be spent on the most effective search; therefore, the search efficiency can also be significantly improved. In order to explore the whole solution space evenly, uniform design is introduced to generate an initial population, in which the population members are scattered uniformly over the feasible solution space. In evolution, uniform design is also introduced to replace some worse individuals. Based on abovementioned these technologies, a novel algorithm, parallel multi-swarm PSO based on k-medoids and uniform design, is proposed. A difference between the proposed algorithm and the others is that PAM and uniform design are both firstly introduced to parallel PSO algorithms.

Multiple Populations for Multiple Objectives: A Coevolutionary Technique for Solving Multiobjective Optimization Problems

Traditional multiobjective evolutionary algorithms (MOEAs) consider multiple objectives as a whole when solving multiobjective optimization problems (MOPs). However, this consideration may cause difficulty to assign fitness to individuals because different objectives often conflict with each other. In order to avoid this difficulty, this paper proposes a novel coevolutionary technique named multiple populations for multiple objectives (MPMO) when developing MOEAs. The novelty of MPMO is that it provides a simple and straightforward way to solve MOPs by letting each population correspond with only one objective. This way, the fitness assignment problem can be addressed because the individuals' fitness in each population can be assigned by the corresponding objective. MPMO is a general technique that each population can use existing optimization algorithms. In this paper, particle swarm optimization (PSO) is adopted for each population, and coevolutionary multiswarm PSO (CMPSO) is developed based on the MPMO technique. Furthermore, CMPSO is novel and effective by using an external shared archive for different populations to exchange search information and by using two novel designs to enhance the performance. One design is to modify the velocity update equation to use the search information found by different populations to approximate the whole Pareto front (PF) fast. The other design is to use an elitist learning strategy for the archive update to bring in diversity to avoid local PFs. CMPSO is comprehensively tested on different sets of benchmark problems with different characteristics and is compared with some state-of-the-art algorithms. The results show that CMPSO has superior performance in solving these different sets of MOPs.

Optimal multiaxial sensor placement for modal identification of large structures

SUMMARY Research on optimal sensor placement has become a very important topic because of the need to obtain effective testing results with limited testing resources in modal identification and structural health monitoring. An integer-encoding multi-swarm particle swarm optimisation (IMPSO) algorithm is proposed to place multiaxial sensors optimally on large structures for modal identification. The concepts of grade evaluation and migration strategy and the mutation operators of genetic algorithm are introduced into the integer-encoding particle swarm optimisation algorithm. Three different fitness functions for optimal multiaxial sensor placement (OMSP) are investigated. The second fitness function considers spatial correlation based on Moran's I to solve the information redundancy of multiaxial sensor placement, whereas the other two functions evolve from the existing methods for comparison with the second fitness function. The novel algorithm and three fitness functions are further applied to the Laxiwa arch dam for verifications. The results show that the proposed IMPSO outperforms two existing algorithms in its global optimisation capability. The results also prove that the second fitness function has advantages in sensor distribution and ensuring the well-conditioned information matrix and observability of multidimensional modal shapes. The multiaxial sensor placement scheme determined by the proposed method is applied to the modal test of the Laxiwa arch dam under simulative ambient excitation. The results show that the scheme determined by the second fitness function can identify the frequencies and multidimensional mode shapes accurately, indicating that this method may be used to provide guidance for OMSP in various types of large structures. Copyright © 2013 John Wiley & Sons, Ltd.

Intelligent financial time series forecasting: A complex neuro-fuzzy approach with multi-swarm intelligence

Financial investors often face an urgent need to predict the future. Accurate forecasting may allow investors to be aware of changes in financial markets in the future, so that they can reduce the risk of investment. In this paper, we present an intelligent computing paradigm, called the Complex Neuro-Fuzzy System (CNFS), applied to the problem of financial time series forecasting. The CNFS is an adaptive system, which is designed using Complex Fuzzy Sets (CFSs) whose membership functions are complex-valued and characterized within the unit disc of the complex plane. The application of CFSs to the CNFS can augment the adaptive capability of nonlinear functional mapping, which is valuable for nonlinear forecasting. Moreover, to optimize the CNFS for accurate forecasting, we devised a new hybrid learning method, called the HMSPSO-RLSE, which integrates in a hybrid way the so-called Hierarchical Multi-Swarm PSO (HMSPSO) and the wellknown Recursive Least Squares Estimator (RLSE). Three examples of financial time series are used to test the proposed approach, whose experimental results outperform those of other methods.

A competitive clustering particle swarm optimizer for dynamic optimization problems

Optimization in dynamic optimization problems (DOPs) requires the optimization algorithms not only to locate, but also to continuously track the moving optima. Particle swarm optimization (PSO) is a population-based optimization algorithm, originally developed for static problems. Recently, several researchers have proposed variants of PSO for optimization in DOPs. This paper presents a novel multi-swarm PSO algorithm, namely competitive clustering PSO (CCPSO), designed specially for DOPs. Employing a multi-stage clustering procedure, CCPSO splits the particles of the main swarm over a number of sub-swarms based on the particles positions and on their objective function values. The algorithm automatically adjusts the number of sub-swarms and the corresponding region of each sub-swarm. In addition to the sub-swarms, there is also a group of free particles that explore the environment to locate new emerging optima or exploit the current optima which are not followed by any sub-swarm. The adaptive search strategy adopted by the sub-swarms improves both the exploitation and tracking characteristics of CCPSO. A set of experiments is conducted to study the behavior of the proposed algorithm in different DOPs and to provide guidelines for setting the algorithm’s parameters in different problems. The results of CCPSO on a variety of moving peaks benchmark (MPB) functions are compared with those of several state-of-the-art PSO algorithms, indicating the efficiency of the proposed model.

Multi-Swarm Particle Swarm Optimization with an Adaptive Type Selection for Restarting Particles

Multi-Swarm Particle Swarm Optimization with an Adaptive Type Selection for Restarting Particles