A new immune genetic algorithm

The application of genetic algorithm is widely, but it is easy to premature convergence and is inadequate about the local searching optimization ability. In this paper, a new immune genetic algorithm (IGA) is proposed. Experiments are done to compare the proposed algorithm with the standard GA, and the results indicate that the proposed IGA´s optimization results and converging speed are superior and the proposed IGA overcomes the premature convergence and solves the problem of falling into local optimum solution easily. This paper also combines TSP´s encoding characteristics to propose a new crossover operator (DEGX). Experiments shows the DEGX can enhance the local search ability greatly.