Abstract—Firefly algorithm is one of the evolutionary optimization algorithms, and is inspired by fireflies behavior in nature. Each firefly movement is based on absorption of the other one. In this paper to stabilize firefly’s movement, it is proposed a new behavior to direct fireflies movement to global best if there was no any better solution around them. In addition to increase convergence speed it is proposed to use Gaussian distribution to move all fireflies to global best in each iteration. Proposed algorithm was tested on five standard functions that have ever used for testing the static optimization algorithms. Experimental results show better performance and more accuracy than standard Firefly algorithm.
Index Terms—Algorithm, optimization, Global search, Local search.
Sh. M. Farahani, A. A. Abshouri, B. Nasiri and M. R. Meybodi are with the Department of electronic, Computer and IT, Islamic Azad University, Iran, Qazvin. (e-mail: sh.farahani@qiau.ac.ir;a_amin@qiau.ac.ir; Nasiri.babak@qiau.ac.ir; mmeybodi@aut.ac.ir)
Cite: Sh. M. Farahani, A. A. Abshouri, B. Nasiri, and M. R. Meybodi, "A Gaussian Firefly Algorithm," International Journal of Machine Learning and Computing vol. 1, no. 5, pp.448-453, 2011.