Dynamic Quantum Crossover Based Clonal Selection Algorithm For Solving Traveling Salesman Problem

The applications of Clonal Selection Algorithms (CSAs) in solving combinatorial problems are frequently faced with a premature convergence problem and the maturation processes are trapped into a local optimum. This premature convergence problem occurs when the population of a clonal selection algorithm reaches a suboptimal state that the immune operators can no longer produce new immune cells with high affinities. To overcome this problem, different crossover operators have been investigated and embedded into CSAs. In this research, a dynamic quantum interference crossover is built up during maturation process to effectively accumulate useful receptor editing operation. The proposed crossover operator can be applied to improve the global convergence behavior of CSA. The experimental results focus on Traveling Salesman Problems (TSPs) show that the proposed algorithm is very effective in preventing the premature convergence problem when compared with other approaches.