Multi-Modal Function Optimization Using High Frequency Mutation Immune Evolutionary Algorithm

Multi-modal function optimization problem is a difficult topic in numerical optimization field. This paper put forward an improved high frequency mutation based immune evolutionary algorithm. Clone selections of high frequency mutation antibody are used to enhance the diversity of the whole population. Each individual is endowed with a life span to control its growth and death, and the proliferating in population size caused by high frequency mutation. Besides, mutation factors are employed to identify the antigen speed. This algorithm overcomes the slow searching speed of clone selection algorithm, and has a better global convergence performance. Three multi-modal functions are optimized using this algorithm, standard genetic algorithm, improved genetic algorithm and fine genetic algorithm, and the comparisons of simulation results show that the proposed algorithm converges to the global optimum more quickly than the three genetic algorithms.