The graph coloring problem is one of famous combinatorial optimization problems. Some researchers attempted to solve combinatorial optimization problem with evolutionary algorithm, which can find near optimal solution based on the evolution mechanism of the nature. However, it sometimes requires too much cost to evaluate fitness of a large number of individuals in the population when applying the GA to the real world problems. This paper attempts to solve graph coloring problem using a fuzzy clustering based evolutionary approach to reduce the cost of the evaluation. In order to show the feasibility of the method, some experiments with other alternative methods are conducted.
展开▼