Varying the Topology and Probability of Re-Initialization in Particle Swarm Optimization (original) (raw)
Related papers
Dynamic Particle Swarm Optimization with Any Irregular Initial Small-World Topology
International Journal of Swarm Intelligence Research, 2015
It is realized that the topological structure of the particle swarm optimization (PSO) algorithm has a great influence on its optimization ability. This paper presents a new dynamic small-world neighborhood PSO (D-SWPSO) algorithm whose neighbourhood structure can be constructed with any irregular initial networks. The choice of the learning exemplar is not only based upon the big clustering coefficient and the average shortest distance for a regular network, but also based upon the eigenvalues of Laplacian matrix for irregular networks. Therefore, the D-SWPSO is a PSO algorithm based on small-world topological neighbourhood with universal significance. The proposed algorithm is tested by some typical benchmark test functions, and the results confirm that there is a significant improvement over the basic PSO algorithm. Finally, the algorithm is applied to a real-world optimization problem, the economic dispatch on the IEEE30 system with wind farms. The results demonstrate that the p...
Particle Swarm Optimisation with Gradually Increasing Directed Neighbourhoods
Particle swarm optimisation (PSO) is an intelligent random search algorithm, and the key to success is to effectively balance between the exploration of the solution space in the early stages and the exploitation of the solution space in the late stages. This paper presents a new dynamic topology called "gradually increasing di- rected neighbourhoods (GIDN)" that provides an effective way to balance between exploration and exploitation in the entire iteration process. In our model, each particle begins with a small number of connections and there are many small isolated swarms that im- prove the exploration ability. At each iteration, we gradually add a number of new connections between particles which improves the ability of exploitation gradually. Furthermore, these connections among particles are created randomly and have directions. We for- malise this topology using random graph representations. Experi- ments are conducted on 31 benchmark test functions to validate our proposed topology. The results show that the PSO with GIDN per- forms much better than a number of the state of the art algorithms on almost all of the 31 functions.
Network-Structured Particle Swarm Optimizer with Small-World Topology
Proc. of Int. Symposium on Nonlinear …, 2009
This study proposes Network-Structured Particle Swarm Optimizer (NS-PSO) with Small-World topology. All particles are connected to adjacent particles depending on the small-world network. The directly connected particles share their own best position. Each particle is updated depending on the neighborhood distance on the network between it and a winner, whose function value is best among all particles. We apply NS-PSO with smallworld topology to various optimization problems and confirm the effectiveness of the proposed model.
Global and Local Neighborhood Based Particle Swarm Optimization
Harmony Search and Nature Inspired Optimization Algorithms, 2018
The particle swarm optimization (PSO) is one of the popular and simple to implement swarm intelligence based algorithms. To some extent, PSO dominates other optimization algorithms but prematurely converging to local optima and stagnation in later generations are some pitfalls. The reason for these problems is the unbalancing of the diversification and convergence abilities of the population during the solution search process. In this paper, a novel position update process is developed and incorporated in PSO by adopting the concept of the neighborhood topologies for each particle. Statistical analysis over 15 complex benchmark functions shows that performance of propounded PSO version is much better than standard PSO (PSO 2011) algorithm while maintaining the cost-effectiveness in terms of function evaluations.
A Statistical Study of the Effects of Neighborhood Topologies in Particle Swarm Optimization
Studies in Computational Intelligence, 2011
The behavior of modern meta-heuristics is directed by both, the variation operators, and the values selected for the parameters of the approach. Particle swarm optimization (PSO) is a meta-heuristic which has been found to be very successful in a wide variety of optimization tasks. In PSO, a swarm of particles fly through hyper-dimensional search space being attracted by both, their personal best position and the best position found so far within a neighborhood. In this paper, we perform a statistical study in order to analyze whether the neighborhood topology promotes a convergence acceleration in four PSO-based algorithms: the basic PSO, the Bare-bones PSO, an extension of BBPSO and the Bare-bones Differential Evolution. Our results indicate that the convergence rate of a PSO-based approach has a strongly dependence of the topology used. We also found that the topology most widely used is not necessarily the best topology for every PSO-based algorithm.
Randomized directed neighborhoods with edge migration in particle swarm optimization
Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753)
A key feature of Particle Swarm Optimization algorithms is that fitness information is shared with individuals in a particle's neighborhood. The kind of neighborhood structure that is used affects the rate at which information is disseminated throughout the population. Existing work has studied global and simple local topologies, as well as more complex, but fixed neighborhood structures. This paper looks at randomly generated, directed graph structures in which information flows in one direction only, and also outgoing edges randomly migrate from one source node to another. Experimental evidence indicates that this random dynamic topology, when used with an inertia weight PSO, performs competitively with some existing methods and outperforms others.
Hierarchical dynamic neighborhood based Particle Swarm Optimization for global optimization
… Computation (CEC), 2011 …, 2011
Particle Swarm Optimization (PSO) is arguably one of the most popular nature-inspired algorithms for real parameter optimization at present. In this article, we introduce a new variant of PSO referred to as Hierarchical D-LPSO (Dynamic Local Neighborhood based Particle Swarm Optimization). In this new variant of PSO the particles are arranged following a dynamic hierarchy. Within each hierarchy the particles search for better solution using dynamically varying sub-swarms i.e. these sub-swarms are regrouped frequently and information is exchanged among them. Whether a particle will move up or down the hierarchy depends on the quality of its so-far bestfound result. The swarm is largely influenced by the good particles that move up in the hierarchy. The performance of Hierarchical D-LPSO is tested on the set of 25 numerical benchmark functions taken from the competition and special session on real parameter optimization held under IEEE Congress on Evolutionary Computation (CEC) 2005. The results have been compared to those obtained with a few best-known variants of PSO as well as a few significant existing evolutionary algorithms.
Dispersed particle swarm optimization
Information Processing Letters, 2008
In particle swarm optimization (PSO) literatures, the published social coefficient settings are all centralized control manner aiming to increase the search density around the swarm memory. However, few concerns the useful information inside the particles' memories. Thus, to improve the convergence speed, we propose a new setting about social coefficient by introducing an explicit selection pressure, in which each particle decides its search direction toward the personal memory or swarm memory. Due to different adaptation, this setting adopts a dispersed manner associated with its adaptive ability. Furthermore, a mutation strategy is designed to avoid premature convergence. Simulation results show the proposed strategy is effective and efficient.
International Journal of Advanced Trends in Computer Science and Engineering, 2019
In this paper, a novel approach is considered, based on Particle Swarm Optimization (PSO) technique, using two concepts: evolutionary neighborhood topology associated to parallel computation for complex optimization problems. The idea behind using dynamic neighborhood topology is to overcome premature convergence of PSO algorithm, by well exploring and exploiting the search space for a better solution quality. Parallel computation is used to accelerate calculations especially for complex optimization problems. The simulation results demonstrate good performance of the proposed algorithm in solving a series of significant benchmark test functions.
A generalized theoretical deterministic particle swarm model
2014
A number of theoretical studies of particle swarm optimization (PSO) have been done to gain a better understanding of the dynamics of the algorithm and the behaviour of the particles under different conditions. These theoretical analyses have been performed for both the deterministic PSO model, and more recently for the stochastic model. However, all current theoretical analyses of the PSO algorithm were based on the stagnation assumption, in some form or another. The analysis done under the stagnation assumption is one where the personal best and neighborhood best positions are assumed to be non-changing. While analysis under the stagnation assumption is very informative, it could never provide a complete description of a PSO's behavior. Furthermore, the assumption implicitly removes the notion of a social network structure from the analysis. This paper presents a generalisation to the theoretical deterministic PSO model. Under the generalised model, conditions for particle convergence to a point are derived. The model used in this paper greatly weakens the stagnation assumption, by instead assuming that each particle's personal best and neighborhood best can occupy an arbitrarily large number of unique positions. It was found that the conditions derived in previous theoretical deterministic PSO research could be obtained as a specialisation of the new generalised model proposed. Empirical results are presented to support the theoretical findings.