An Improved Adaptive Differential Evolution based on Hybrid Method for Function Optimization

In order to improve the optimum speed, crease the diversity of the population and overcome the premature convergence problem in differential evolution(DE) algorithm for solving the complex optimization problems, the chaotic optimization algorithm with powerful local searching capacity and multistrategy are introduced into the DE algorithm in order to propose an improved adaptive differential evolution(COMSIADE) algorithm in solving function optimization problems. In the COMSIADE algorithm, the ergodicity, regularity and internal randomness of the chaotic sequence are used to overcome the shortcoming of premature local optimum to improve the global searching capacity of the DE algorithm. The multi-population with parallel evolution is used to preserve the diversity of the population at the initial generation. The self-adaptive crossover operator probability is used to improve the global convergence ability, the stability and robustness. Finally, in order to test and verify the effectiveness of the COMSIADE algorithm, several benchmark functions are selected in this paper. The experimental results indicate that the proposed COMSIADE algorithm can improve the global searching capacity and avoid falling into local optimum. And it takes on the higher searching precision and faster convergence speed in solving the complex optimization problem.