scispace - formally typeset
Search or ask a question

Showing papers on "Particle swarm optimization published in 2001"


Proceedings ArticleDOI
Eberhart1, Yuhui Shi
27 May 2001
TL;DR: Developments in the particle swarm algorithm since its origin in 1995 are reviewed and brief discussions of constriction factors, inertia weights, and tracking dynamic systems are included.
Abstract: This paper focuses on the engineering and computer science aspects of developments, applications, and resources related to particle swarm optimization. Developments in the particle swarm algorithm since its origin in 1995 are reviewed. Included are brief discussions of constriction factors, inertia weights, and tracking dynamic systems. Applications, both those already developed, and promising future application areas, are reviewed. Finally, resources related to particle swarm optimization are listed, including books, Web sites, and software. A particle swarm optimization bibliography is at the end of the paper.

4,041 citations


Proceedings ArticleDOI
27 May 2001
TL;DR: The experimental results illustrate that the fuzzy adaptive PSO is a promising optimization method, which is especially useful for optimization problems with a dynamic environment.
Abstract: A fuzzy system is implemented to dynamically adapt the inertia weight of the particle swarm optimization algorithm (PSO). Three benchmark functions with asymmetric initial range settings are selected as the test functions. The same fuzzy system has been applied to all three test functions with different dimensions. The experimental results illustrate that the fuzzy adaptive PSO is a promising optimization method, which is especially useful for optimization problems with a dynamic environment.

1,132 citations


Proceedings ArticleDOI
27 May 2001
TL;DR: Three kinds of dynamic systems are defined for the purposes of this paper and one of them is chosen for preliminary analysis using the particle swarm on the parabolic benchmark function.
Abstract: Using particle swarms to track and optimize dynamic systems is described. Issues related to tracking and optimizing dynamic systems are briefly reviewed. Three kinds of dynamic systems are defined for the purposes of this paper. One of them is chosen for preliminary analysis using the particle swarm on the parabolic benchmark function. Successful tracking of a 10-dimensional parabolic function with a severity of up to 1.0 is demonstrated. A number of issues related to tracking and optimizing dynamic systems with particle swarms are identified. Directions for future research and applications are suggested.

959 citations


Proceedings Article
07 Jul 2001
TL;DR: Two hybrid PSOs combine the traditional velocity and position update rules with the ideas of breeding and subpopulations are presented to illustrate that PSOs with breeding strategies have the potential to achieve faster convergence and to find a better solution.
Abstract: In this paper we present two hybrid Particle Swarm Optimisers combining the idea of the particle swarm with concepts from Evolutionary Algorithms. The hybrid PSOs combine the traditional velocity and position update rules with the ideas of breeding and subpopulations. Both hybrid models were tested and compared with the standard PSO and standard GA models. This is done to illustrate that PSOs with breeding strategies have the potential to achieve faster convergence and the potential to find a better solution. The objective of this paper is to describe how to make the hybrids benefit from genetic methods and to test their potential and competetiveness on function optimisation.

504 citations


01 Jan 2001
TL;DR: These preliminary results suggest that these two modifications of the particle swarm optimizer allow PSO to search in both static and dynamic environments.
Abstract: In this paper the authors propose a method for adapting the particle swarm optimizer for dynamic environments. The process consists of causing each particle to reset its record of its best position as the environment changes, to avoid making direction and velocity decisions on the basis of outdated information. Two methods for initiating this process are examined: periodic resetting, based on the iteration count, and triggered resetting, based on the magnitude of the change in the environment. These preliminary results suggest that these two modifications allow PSO to search in both static and dynamic

268 citations


Proceedings ArticleDOI
28 Jan 2001
TL;DR: In this paper, a hybrid particle swarm optimization (HPSO) method is proposed to estimate load and distributed generation output values at each node by minimizing the difference between measured and calculated state variables.
Abstract: This paper proposes a practical distribution system state estimation method using a hybrid particle swarm optimization. The proposed method considers nonlinear characteristics of the practical equipment and actual measurements in distribution systems. The method can estimate load and distributed generation output values at each node by minimizing the difference between measured and calculated state variables. The feasibility of the proposed method is demonstrated and compared with the original PSO on practical distribution system models. The results indicate the applicability of the proposed state estimation method to practical distribution systems.

188 citations


01 Jan 2001
TL;DR: The performance of the recently proposed Particle Swarm optimization method in the presence of noisy and continuously changing environments is studied.
Abstract: In this paper we study the performance of the recently proposed Particle Swarm optimization method in the presence of noisy and continuously changing environments. Experimental results for well known and widely used optimization test functions are given and discussed. Conclusions for its ability to cope with such environments as well as real– life applications are also derived.

165 citations


Proceedings ArticleDOI
27 May 2001
TL;DR: The proposed method expands the original PSO to handle a MINLP and determines an RPVC strategy with continuous and discrete control variables such as automatic voltage regulator operating values of generators, tap positions of on-load tap changer of transformers, and the amount of reactive power compensation equipment.
Abstract: This paper presents a particle swarm optimization (PSO) for reactive power and voltage control (RPVC) in electric power systems. RPVC can be formulated as a mixed-integer nonlinear optimization problem (MINLP). The proposed method expands the original PSO to handle a MINLP and determines an RPVC strategy with continuous and discrete control variables such as automatic voltage regulator (AVR) operating values of generators, tap positions of on-load tap changer (OLTC) of transformers, and the amount of reactive power compensation equipment (RPCE). The feasibility of the proposed method is demonstrated and compared with reactive tabu search (RTS) and the enumeration method on practical power system models with promising results.

159 citations


Book ChapterDOI
TL;DR: The particle swarm algorithm is discussed in terms of social and cognitive behavior, though it is widely used as a problem solving method in engineering and computer science.
Abstract: Publisher Summary This chapter introduces the particle swarm in its binary and real-numbered forms. The particle swarm algorithm is discussed in terms of social and cognitive behavior, though it is widely used as a problem solving method in engineering and computer science. The chapter presents more commonly used version, which operates in a space of real numbers. The process of cultural adaptation comprises a high-level component, seen in the formation of patterns across individuals and the ability to solve problems, a low-level component, the actual and probably universal behaviors of individuals, which can be summarized in terms of three principles: evaluation, comparison, and imitation. These three principles may be combined, even in simplified social beings in computer programs, enabling them to adapt to complex environmental challenges, solving extremely hard problems. The progression of ideas has been from a purely qualitative social optimization algorithm—the Adaptive Culture Model—to a model that can be interpreted as qualitative or quantitative—the binary particle swarm. The kind of decision processes instantiated in both the binary and real-valued particle swarm algorithms exemplify a tendency that is widely regarded as a flaw or error when seen in human cognition.

156 citations


Proceedings Article
07 Jul 2001
TL;DR: The effect of swarm size on the Cooperative Particle Swarm Optimiser is investigated, showing that the CPSO does not exhibit the same general trend as the original PSO.
Abstract: Particle Swarm Optimisation is a stochastic global optimisation technique making use of a population of particles, where each particle represents a solution to the problem being optimised. The Cooperative Particle Swarm Optimiser (CPSO) is a variant of the original Particle Swarm Optimiser (PSO). This technique splits the solution vector into smaller vectors, where each sub-vector is optimised using a separate PSO. This paper investigates the effect of swarm size on the CPSO, showing that the CPSO does not exhibit the same general trend as the original PSO.

140 citations


Proceedings ArticleDOI
15 Jul 2001
TL;DR: The paper investigates the influence that the number of swarms used (also called the split factor) has on the training performance of a product unit neural network.
Abstract: The cooperative particle swarm optimiser (CPSO) is a variant of the particle swarm optimiser (PSO) that splits the problem vector, for example a neural network weight vector, across several swarms. The paper investigates the influence that the number of swarms used (also called the split factor) has on the training performance of a product unit neural network. Results are presented, comparing the training performance of the two algorithms, PSO and CPSO, as applied to the task of training the weight vector of a product unit neural network.

Book ChapterDOI
01 Jan 2001
TL;DR: The Particle Swarm Optimization method is modified in order to locate and evaluate all the global minima of an objective function and separates the swarm properly when a candidate minimizer is detected.
Abstract: In many optimization applications, escaping from the local minima as well as computing all the global minima of an objective function is of vital importance. In this paper the Particle Swarm Optimization method is modified in order to locate and evaluate all the global minima of an objective function. The new approach separates the swarm properly when a candidate minimizer is detected. This technique can also be used for escaping from the local minima which is very important in neural network training.

Proceedings ArticleDOI
15 Jul 2001
TL;DR: In this paper, a novel evolutionary algorithm based approach to optimal design of multimachine power system stabilizers (PSSss) is proposed, which develops and employs particle swarm optimization (PSO) technique to search for optimal settings of PSS parameters.
Abstract: In this paper, a novel evolutionary algorithm based approach to optimal design of multimachine power system stabilizers (PSSs) is proposed. The proposed approach develops and employs particle swarm optimization (PSO) technique to search for optimal settings of PSS parameters. Two eigenvalue-based objective functions to enhance system damping of electromechanical modes are considered. The robustness of the proposed approach to the initial guess is demonstrated. The performance of the proposed PSO based PSS (PSOPSS) under different disturbances and loading conditions is tested and examined. Eigenvalue analysis and nonlinear simulation results show the effectiveness of the proposed PSOPSSs to damp out the electromechanical oscillations and work effectively over a wide range of loading conditions.

01 Jan 2001
TL;DR: In this article, a novel evolutionary algorithm based approach to optimal design of multimachine Power System Stabilizers (PSSS) is proposed, which develops and employs Particle Swarm Optimization (PSO) technique to search for optimal settings of PSS parameters.
Abstract: i In this paper, a novel evolutionary algorithm based approach to optimal design of multimachine Power System Stabilizers (PSSS)is proposed. The proposed approach develops and employs Particle Swarm Optimization (PSO) technique to search for optimal settings of PSS parameters. Two eigenvalue-based objective functions to enhance system damping of electromechanical modes are considered. The robustness of the proposed approach to the initial guess is demonstrated. The performance of the proposed PSO based PSS (PSOPSS) under different disturbances and loading conditions is tested and examined. Eigenvalue analysis and nonlinear simulation results show the effectiveness of the proposed PSOPSSS to damp out the electromechanical oscillations and work effectivelyover a wide range of loading conditions.

Book ChapterDOI
04 Jun 2001
TL;DR: It is shown that the combined algorithm out performs both of the component algorithms under most conditions, in both absolute and computational load weighted terms.
Abstract: An algorithm that is a combination of the particle swarm and differential evolution algorithms is introduced. The results of testing this on a graduated set of trial problems is given. It is shown that the combined algorithm out performs both of the component algorithms under most conditions, in both absolute and computational load weighted terms.

Proceedings ArticleDOI
29 Oct 2001
TL;DR: A clustering algorithm based on swarm intelligence is systematically proposed, derived from a basic model interpreting ant colony organization of cemeteries, with good performance.
Abstract: This paper focuses on swarm intelligence based clustering algorithm. A clustering algorithm based on swarm intelligence is systematically proposed. It derived from a basic model interpreting ant colony organization of cemeteries. Some important concepts, such as swarm similarity, swarm similarity coefficient and probability conversion function are also proposed. A simplified probability conversion function is given for simplifying adaptation of parameters, meanwhile the importance of swarm similarity coefficient for the algorithm is analyzed. Experimental results show the good performance of the clustering algorithm.

Proceedings ArticleDOI
13 May 2001
TL;DR: In this paper, a modified particle swarm optimizer (PSO) was proposed to solve the economic power dispatch problem with piecewise quadratic cost function, where the operating conditions of many generating units require that the cost function be segmented as piecewise-quadratic functions instead of using one convex function for each generator.
Abstract: The paper presents a modified particle swarm optimizer (PSO) to solve the economic power dispatch problem with piecewise quadratic cost function. Practically, operating conditions of many generating units require that the cost function be segmented as piecewise quadratic functions instead of using one convex function for each generator. The proposed technique is applied to a case study of multiple intersecting cost functions for each unit. Unlike the hierarchical method, the proposed algorithm finds combination of power generation that minimizes the total cost function while exactly satisfying the total demand.


Journal ArticleDOI
TL;DR: In this article, an optimal concurrent design approach based upon a previously developed distributed product development life-cycle modeling method is introduced, where the product realization process alternatives and relevant activities are modeled at different locations that are connected through the Internet Relations among these alternative activities are described by an AND/OR graph.
Abstract: This research introduces an optimal concurrent design approach based upon a previously developed distributed product development life-cycle modeling method In this approach, the product realization process alternatives and relevant activities are modeled at different locations that are connected through the Internet Relations among these alternative activities are described by an AND/OR graph The optimal product realization process alternative and its parameter values are identified using a multi-level optimization method Genetic programming (GP) and particle swarm optimization (PSO) are employed for identifying the optimal product realization process alternative and the optimal parameter values of the feasible alternatives, respectively

Proceedings ArticleDOI
13 May 2001
TL;DR: The paper presents the particle swarm optimization technique (PSO) to train multi layer neural network for discrimination between magnetizing inrush current and internal fault current in power transformers.
Abstract: The paper presents the particle swarm optimization technique (PSO) to train multi layer neural network for discrimination between magnetizing inrush current and internal fault current in power transformers. The discrimination process relies on the harmonic components of both inrush and fault currents. The features were extracted from the wave of the differential current by using the fast Fourier transform (FFT). The output of the neural network is trained to respond "high" or "1" for fault current (trip command of the differential relay) and "low" or "0" for inrush current (no trip command). Compared to the back propagation (BP) training method, neural networks using the particle swarm optimization technique is more accurate (in terms of sum square errors) and also faster (in terms of number of iterations).

Proceedings ArticleDOI
28 Jan 2001
TL;DR: In this article, the authors present a practical distribution state estimation (DSE) method and an optimal setting method for voltage regulators in distribution systems using modern heuristic techniques, and demonstrate the feasibility of the proposed methods on practical distribution system models.
Abstract: This paper presents a practical distribution state estimation (DSE) method and an optimal setting method for voltage regulators in distribution systems using modern heuristic techniques. The proposed DSE method utilizes hybrid particle swarm optimization (HPSO) and handles nonlinear characteristics of the practical equipment and actual measurements in distribution systems. The proposed optimal setting method for voltage regulators utilizes reactive tabu search (RTS) and enumeration method, and handles variation of load flow by introduction of distributed generation. The feasibility of the proposed methods is demonstrated on practical distribution system models.

Proceedings ArticleDOI
23 Oct 2001
TL;DR: A new methodology for Emergent System Identification is introduced that is concerned with combining the methodologies of self-organizing functional networks, Particle Swarm Optimization, and Genetic Programming that can be used to identify overlapping internal structural models.
Abstract: Complex Adaptive Structures can be viewed as a combination of Complex Adaptive Systems and fully integrated autonomous Smart Structures. Traditionally when designing a structure, one combines rules of thumb with theoretical results to develop an acceptable solution. This methodology will have to be extended for Complex Adaptive Structures, since they, by definition, will participate in their own design. In this paper we introduce a new methodology for Emergent System Identification that is concerned with combining the methodologies of self-organizing functional networks (GMDH - Alexy G. Ivakhnenko), Particle Swarm Optimization (PSO - James Kennedy and Russell C. Eberhart) and Genetic Programming (GP - John Koza). This paper will concentrate on the utilization of Particle Swarm Optimization in this effort and discuss how Particle Swarm Optimization relates to our ultimate goal of emergent self-organizing functional networks that can be used to identify overlapping internal structural models. The ability for Complex Adaptive Structures to identify emerging internal models will be a key component for their success.

Book ChapterDOI
TL;DR: The chapter presents a new methodology using particle swarm optimization for evolving neural network weights and simultaneously indirectly evolving network architecture and describes the application of particle Swarm optimization to evolve a neural network that classifies human tremor versus normal subjects.
Abstract: Publisher Summary This chapter presents the practical world of engineering and shows some applications of particle swarm optimization. Evolutionary computation methodologies have generally been applied to three main attributes of neural networks: network connection weights, network architecture, and network learning algorithms. The chapter summarizes some of the advantages and disadvantages that have been discussed in the literature and experienced with respect to the use of evolutionary computation techniques with artificial neural networks. It highlights the successes and examines issues that should be addressed in order to make further progress. The performance of each particle is measured according to a predefined fitness function, which is related to the problem to be solved. The chapter presents a new methodology using particle swarm optimization for evolving neural network weights and simultaneously indirectly evolving network architecture. . This chapter also describes the application of particle swarm optimization to evolve a neural network that classifies human tremor (Parkinson's disease or essential tremor) versus normal subjects. . The relatively small size of the data set indicates the need for further testing and development.

Book ChapterDOI
TL;DR: This chapter reviews the arguments and proposes some speculative conclusions about the particle swarm paradigm, a kind of framework for social-psychological theory, as a set of tools for engineering and computer science.
Abstract: This chapter reviews the arguments and proposes some speculative conclusions. These include directions for further research, observations about the work itself and its place in the scientific endeavor. . The particle swarm paradigm provides a kind of framework for social-psychological theory, as well as a set of tools for engineering and computer science. The spread of adaptive behaviors through population results in clustering or convergence of individuals within a region of the problem space. Particle swarms can be used in many machine adaptation applications, such as evolving fuzzy expert systems, a process that relies on nonprogrammed emergent behavior to evolve fuzzy rule sets. Fuzzy expert system is a powerful tool for control, diagnosis, classification, and optimization. Evolving a system using particle swarm methodology can yield compact systems that degrade gracefully. The particle swarm theoretical view suggests that the effects of individual learning and social influence can maximize cognitive consistency.

Journal ArticleDOI
TL;DR: In this paper, the time-dependent statistical distributions of charged-particle swarms exposed to external fields (both electrostatic and flow) are examined using state-of-the-art flow/particle visualization and animation techniques.
Abstract: Using state-of-the-art flow/particle visualization and animation techniques, the time-dependent statistical distributions of charged-particle “swarms” exposed to external fields (both electrostatic and flow) are examined. We found that interparticle interaction and drag forces mainly influenced swarm dispersion in a Lagrangian reference frame, whereas the average particle trajectory was affected primarily by the external electric and flow fields.

Proceedings ArticleDOI
12 Jul 2001
TL;DR: Genetic programming and particle swarm optimization are employed for identifying the optimal product realization process alternative and the optimal parameter values of the feasible alternatives, respectively.
Abstract: An optimal concurrent design approach is introduced in this research using a previously developed distributed product development life-cycle database modeling method. In this approach, product realization process alternatives and relevant activities are modeled at different locations that are connected through the Internet. Genetic programming (GP) and particle swarm optimization (PSO) are employed for identifying the optimal product realization process alternative and the optimal parameter values of the feasible alternatives, respectively.

Book ChapterDOI
TL;DR: This chapter compares versions of the particle swarm paradigm that include experiments in which selection is added to the particle Swarm paradigm, comparisons of the inertia weight, and constriction factor approaches, and a test in which particle swarms are initialized asymmetrically with respect to the global optimum.
Abstract: This chapter explores implementations of the particle swarm paradigm, shows some variations of the algorithm, discusses whether the particle swarm is an evolutionary algorithm, and compares the performance of various versions of particle swarms for optimization. Approaches include limiting the maximum allowed particle velocity, including a constriction coefficient and an inertia weight. It considers a new way to look at evolution, focusing on the role of self-organization. The chapter also examines crossover and mutation processes, and population topology as they relate to particle swarms. Moreover , this chapter compares versions of the particle swarm paradigm that include experiments in which selection is added to the particle swarm paradigm, comparisons of the inertia weight, and constriction factor approaches, and a test in which particle swarms are initialized asymmetrically with respect to the global optimum. The effectiveness of the particle swarm algorithm comes from the interactions of particles with their neighbors. The sociometry of the particle population interacts significantly with function. Evolutionary and social algorithms have much in common and their fusion seems inevitable. Some evolutionary operations are analogous to particle swarm methods, but the differences between approaches are considerable.