| Heuristic water cycle algorithm(WCA) is a meta-heuristic optimization algorithm based on the phenomenon of water cycle in nature. The process of water cycle algorithm is simple, easy to understand. In addition, it has strong search ability. In recent years, the water cycle algorithm has received more and more attention of domestic and foreign scholars, and has been successfully applied to solve various optimization problems. But at the same time, the algorithm still has some shortcomings in accuracy and speed for solving the problem.The goal of this paper is to improve the performance of the algorithm by optimizing the structure and encoding methods. In addition, we apply the improved algorithm to function optimization, engineering optimization,clustering analysis, and extend the application range of the algorithm. The main results of this paper are as follows:(1) The operator of percolation behavior is introduced to accelerate the convergence speed of proposed algorithm. At the same time, the self-adaptive rainfall process increases the diversity of the algorithm, and avoids the local optimum.(2) This paper presents an improved version of the water cycle algorithm based on dual cycle system, and we call it dual-system water cycle algorithm(DS-WCA). This algorithm has faster search speed and better robustness. We apply the algorithm to constrained optimization problems and solve several classical engineering optimization problems.(3) Optimization of the encoding method of the algorithm. A new WCA based on complex-valued encoding(CWCA) is presented, which expands the amount of information contained in the individual, enhances the diversity of population.(4) To simplify the basic water cycle algorithm, a simplified water cycle algorithm is proposed. The evolutionary process is only controlled by the process of flowing and percolation operator and apply the simplified algorithm to clustering analysis, and the simulate results show that the algorithm has good clustering effect. |
PDF Full Text Request