Multi-agent based evolutionary algorithm in dynamic environment
Hongfeng Wang · Journal of systems engineering · 2010
In this paper,a multi-agent based evolutionary algorithm(MAEA) is presented to solve dynamic optimization problems.The agents simulate living organism features and cooperate to find the optimum.All agents live in a lattice like environment.In order to increase their energy,agents can compete with their neighbors and acquire knowledge based on statistic information.In order to maintain the diversity of the population,the random immigrants and the adaptive dual mapping schemes are used.Simulation experiments on a set of dynamic benchmark problems show that MAEA can obtain a better performance in dynamic environments in comparison with several existing genetic algorithms.