A new hybrid algorithm based on Firefly Algorithm and cellular learning automata

In this paper, a new evolutionary optimization model, called CLA-FA, is proposed. This new model is a combination of a model called cellular learning automata (CLA) and the Firefly Algorithm (FA). In the proposed algorithm, at first we modify the firefly algorithm to improve the efficiency of this algorithm then we use this algorithm with CLA. in the proposed algorithm, each dimension of search space is assigned to one cell of cellular learning automata and in each cell a swarm of fireflies are located which have the optimization duty of that specific dimension. The learning automata in each cell are responsible for making diversity in fireflies´ swarm of that dimension and adapting the FA parameters for equivalence between global search and local search processes. In order to evaluate the proposed algorithm, we used five well known benchmark function, including: Sphere, Ackly Rastrigin, Xin-she yang and Step functions in 10, 20 and 30 dimensional spaces. The experimental results show that our proposed method can be effective to find the global optima and can improve the global search and the exploration rate of the standard firefly algorithm.