On the performance significance of boundary strategies for Firefly algorithm

Abstract

In this paper, a comparison of a few selected boundary strategies are presented for popular optimization Firefly Algorithm (FA). The problem of boundary constrained optimization was already extensively studied for well-known heuristic optimization Particle Swarm Optimization (PSO). This suggesting importance for similar research for other swarm-based algorithms, like FA. Also, the simple measurement on the tendency of FA particle to violate defined boundaries is presented as well. The recent CEC'17 benchmark suite is used for the performance comparison of the methods and the results are compared and tested for statistical significance.