基于智能混合策略的测试集优化

利用基于粒子群和蚁群算法的智能混合优化策略,删除冗余测试向量以解决测试集的优化问题. 利用蚁群算法的并行搜索能力构造初始解集,通过粒子群优化算法将解集维数降低,确定每次迭代的个体最优解和全局最优解,并利用新粒子信息更新信息素,最终通过多次迭代找到一个或多个最优测试集. 通过多组数据实例分析可知: 该智能混合优化策略与蚁群算法等其他测试集优化算法相比,可得到多个可行性最优测试集;与蚁群算法相比可提高收敛速度,并降低蚁群算法参数选取对收敛结果的影响,从而避免次优解的出现.

Optimization of Test Sets Based on Intelligent Hybrid Algorithm

Utilizing the intelligent hybrid optimization algorithm based on Ant Colony Optimization(ACO) and Particle Swarm Optimization(PSO) can delete redundancy test vectors to solve the optimization problem of test sets. First,the initial solution set was constructed by the parallel searching algorithm of ACO,then,the dimensions of the initial solution set were depressed,and the individual optimal solution and global optimum solution of every iteration time were confirmed by PSO,the pheromone of ACO was regenerated by the new particles information.Finally one or more optimal test sets were found through multiple iterations.From many data cases analysis it is known that the intelligent hybrid optimization algorithm can provide one or more optimal test sets compared with other optimal algorithms for test sets,and compared with ACO,the intelligent hybrid optimization algorithm can provide more rapid convergence rate,depress the influence of ACO parameter chosen on the convergence result and accordingly avoid suboptimal solutions.