International Journal of Computer Theory and Engineering

Abstract

Most research in evolutionary computation focuses on optimization of static, non-changing problems. Many real-world optimization problems, however, are dynamic, and optimization methods are needed that are capable of continuously adapting the solution to a changing environment. In this paper we describe a novel algorithm, which we have called Cellular-DPSABC, and show that it can be applied to dynamic optimization problems. The core of this algorithm is using PSO to optimize the fitness value of population in ABC. Cellular automata make up of cells like points in a lattice or like squares of checker boards and it follows a simple rule. Colonies are distributed randomly among the cells of the cellular automaton that each colony is allocated to one cell. The cells exchange their best solutions to the others in greedy manner and with this strategy they try to find the best solution in the dynamic environment. Experimental results on various dynamic environments modeled by the moving peaks benchmark show that the proposed algorithm outperforms other algorithms, like CABC, CPSO, mQSO, adaptive mQSO and RPSO.