Adaptive and parallel genetic algorithm based on solving premature convergence
Chunyi Shi · Journal of Tsinghua University(Science and Technology) · 1998
Premature convergence is still the preeminent problem in genetic algorithms (GAs). Some excellent individuals or genes are lost due to premature convergence, which causes local optimum. This paper presents an improved genetic algorithm based on multiple populations evolution and adaptive parameter adjusting. Experimental results show that this method alleviates the problem of premature convergence and improves the efficiency of searching.