Randomly attracted firefly algorithm with neighborhood search and dynamic parameter adjustment mechanism

Firefly algorithm (FA) is a new swarm intelligence optimization algorithm, which has shown an effective performance on many optimization problems. However, it may suffer from premature convergence when solving complex optimization problems. In this paper, we propose a new FA variant, called NSRaFA, which employs a random attraction model and three neighborhood search strategies to obtain a trade-off between exploration and exploitation abilities. Moreover, a dynamic parameter adjustment mechanism is used to automatically adjust the control parameters. Experiments are conducted on a set of well-known benchmark functions. Results show that our approach achieves much better solutions than the standard FA and five other recently proposed FA variants.