A Region Reproduction Algorithm for global numerical optimization
Yaou Zhao, Yuehui Chen, Meng Pan, Qiang Zhu · 2008
This paper introduces a novel numerical stochastic optimization algorithm called Region Reproduction Algorithm (RRA) to solve global numerical optimization problems. The algorithm firstly generates some regions in space which the individual in the population exists. Then we evaluate the regions according to the fitness of the individuals in them. The number of offspring in the region is reproduced by the fitness in the regions. With the algorithm goes on, there would be more offspring in the superior regions than the poorer regions. Because the algorithm is more concerned in the superior regions, it has more probability to find the optimal solution than traditional algorithms. Experiments show that the algorithm is more effective and stable in terms of the solution quality and standard deviation compared with other existing methods, such as GA, PSO, Canonical PSO and EO.