Enhancing PSO methods for global optimization

Parameter estimation of nonlinear econometric models using particle swarm optimization

“…One possible solution is to apply a local optimization when local optima are suspected, or when the search begins to stagnate. Since local techniques generally require fewer iterations, excessive computation time would not be expended exploring these local optima (see Wachowiak et al (2004), Tsoulos and Stavrakoudis (2010)). …”

“…However, a drawback of this technique is the high number of iterations required for convergence, which affects overall efficiency. Although the focus in the current work is the quality of the solutions obtained (which is of primary performance, as it is not helpful to converge quickly to a bad solution), there exist several efficiency enhancements that can be easily incorporated (see Tsoulos and Stavrakoudis, 2010). Furthermore, as indicated earlier, PSO is an inherently parallel population-based technique, and can greatly benefit from low-cost multicore and GPU hardware.…”

Velocity based artificial bee colony algorithm for high dimensional continuous optimization problems

“…The best solutions in the current population are very useful sources that can be used to improve the convergence. There are a few algorithms developed to improve the exploitation of the ABC algorithm (Banharnsakun et al, 2011;Luo et al, 2013;Tsoulos and Stavrakoudis, 2010;Xiang and An, 2013;Zhu and Kwong, 2010). In GABC (Zhu and Kwong, 2010), the solution search equation is modified as follows by applying the global best solution to guide the search of new candidate solutions:…”

Chaotic catfish particle swarm optimization for solving global numerical optimization problems

“…All of the empirical experiments for the different methods were carried out with a population size of 40 in 50 trial runs in [43]. The same conditions were used to com- Table 13 Performance of C-CatfishPSO, CenterPSO [10], FuzzyPSO [29] and CatfishPSO [19]. [17], FuzzyPSO [20], CatfishPSO and C-CatfishPSO were also compared by means of the best fitness values and the standard deviation under the same parameter settings.…”

“…The master swarm is enhanced by the social knowledge of the master swarm itself and that of the slave swarms [28]. For promoting any PSO variants, Loannis et al proposed a stopping rule and similarity check in order to enhance the speed of all PSO variants [29]. These PSO variants propose interesting strategies in terms of how to avoid premature convergence for sustaining the variety amongst individuals, and also contain properties that ultimately evolve a population towards a higher fitness (global optimization or local optima).…”