Bee Evolution Genetic Algorithm Based on Real Calculations

This paper presents a simple, efficient, real number encoding genetic algorithm. The algorithm has omitted the workload of encoding and selection, it adopts deterministic induced crossover and mutation operators to improve the algorithm´s ability of local convergence; And introduced foreign populations by the theory of the bee evolution genetic algorithm, which has strengthened the capacity of mining the information contained in the population optimal individual. This algorithm is not need to improve the overall fitness of the population, but using genetic algorithm processes to achieve the optimal search. We have verified the algorithm through JAVA and MATLAB, the results show that this algorithm can obtain the optimal solution within certain accuracy in 10 generations.