DocumentCode :
3005975
Title :
Exponential Type Adaptive Inertia Weighted Particle Swarm Optimization Algorithm
Author :
Jianxin Wu ; Wenzhi Liu ; Weiguo Zhao ; Qiang Li
Author_Institution :
Mech. Sch., Inner Mongolia Univ. of Technol., Hohhot
fYear :
2008
fDate :
25-26 Sept. 2008
Firstpage :
79
Lastpage :
82
Abstract :
Adaptive inertia weight is proposed to rationally balance the global exploration and local exploitation abilities for particle swarm optimization. This paper describes an adaptive strategy for tuning the inertia weight parameter of the PSO algorithm - Exponential type adaptive inertia weighted Particle Swarm Optimization (EPSO). This adaptive tuning strategy is based on the inertia weight dynamic decreased according to iterative generation increasing. The stochastic convergence of the EPSO has been analyzed with the probability density functions of objective function. EPSO algorithm is tested with a set of 5 benchmark functions and compared with standard PSO. Experimental results indicate that the EPSO algorithm improves the search performance on the benchmark functions significantly.
Keywords :
convergence; iterative methods; particle swarm optimisation; probability; search problems; stochastic processes; EPSO algorithm; adaptive tuning strategy; exponential type adaptive inertia; global search ability; iterative generation; local search ability; particle swarm optimization algorithm; probability density function; stochastic convergence; Decision support systems; Genetics; Particle swarm optimization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Genetic and Evolutionary Computing, 2008. WGEC '08. Second International Conference on
Conference_Location :
Hubei
Print_ISBN :
978-0-7695-3334-6
Type :
conf
DOI :
10.1109/WGEC.2008.20
Filename :
4637399
Link To Document :
بازگشت