Comparing nonlinear inertia weights and constriction factors in particle swarm optimization

Article type: Research Article

Authors: Tuppadung, Yutthapong | Kurutach, Werasak^{; *}

Affiliations: Faculty of Information Sciences, Nakhonratchasima College, Nakhonratchasima, 30000, Thailand

Correspondence: [*] Corresponding author: Department of Information Science and Technology, Mahanakorn University of Technology, Bangkok 10530, Thailand. E-mail: yutt_t@pea.co.th and werasak@mut.ac.th

Abstract: In this paper, we empirically study the performance of particle swarm optimization (PSO) using a nonlinear inertia weight compared with the performance using a constriction factor. Adjusting the parameters of nonlinear inertia weight directly affects the performance of PSO. Five benchmark functions are used for evaluation. Under all testing functions, the PSO with nonlinear inertia weights consistently converges faster than the PSO with constriction factors.

Keywords: Nonlinear inertia weight, particle swarm optimization, constriction factor, PSO, nonlinear decreasing inertia weight

DOI: 10.3233/KES-2010-0211

Journal: International Journal of Knowledge-based and Intelligent Engineering Systems, vol. 15, no. 2, pp. 65-70, 2011