Research on Multi-objective Test Case Generation Based on Cuckoo Search

Automatic test data generation is a key link in the process of test automatic technology. In order to measure the efficiency and effectiveness of test cases from multiple perspectives, a multi-objective test case generation method based on cuckoo search is proposed. This method considers two aspects of error discovery ability and test cost, and selects branch distance and test case size as multiple optimization goals. In order to solve the problem of insufficient local search capability of basic multi-objective cuckoo search, Teaching-learning mechanism was introduced. Part of the better solutions in the evolution process were searched locally through Teaching-Learning-Based optimization. At the same time, the external archives were combined with the idea of crowd distance. Set to speed up the convergence of the algorithm. Experiments result shows that compared with the methods based on NSGA-II algorithm and MOCS algorithm, the proposed method can obtain better Pareto solution set and get higher quality test cases in a shorter time.