Adaptive Firefly Optimization Algorithm Based on Stochastic Inertia Weight

Abstract

Firefly Algorithm (FA) originates from the swarm behavior which is inspired by natural fireflies through the fluorescence to exchange information. As a novel bionic swarm intelligent optimization algorithm, it has advantages of simple operation, high calculation efficiency, less parameters and so on, but it also exists defects of slow convergence speed and low optimization accuracy. In order to solve the above problems, this paper proposes the adaptive firefly optimization algorithm based on stochastic inertia weight (AFA). The improved optimization algorithm has feasibility and superiority. The results of the test consisting of five functions' optimization and PID parameters tuning further show that the algorithm optimization ability is better than the original FA and the genetic algorithm (GA).

A new firefly algorithm with mean condition partial attraction

“…So compared with FA, mcFA has lower computation complexity. It can prevent the algorithm from converging too slowly [34,35].…”