A Multi-Goal Particle Swarm Optimizer for Test Case Prioritization

Abstract

Regression testing is carried out to test the updated supply code within the constraints of time and sources. Since it is very difficult to run all the updated source code every time, test case prioritization is needed to decrease the fee of regression testing. Various methodologies including extensions of white box and black box prioritization, have been presented considering the prioritization of test instances. In this context, the employment of particle swarm optimization (PSO) is usually recommended for test case prioritization. Single test case prioritization focuses to order test cases to maximize objectives like fault detection rate, execution time, etc. Regression testing for single-objective test suite prioritization can become challenging due to its longer execution time. However, test case prioritization for multi-objective functions is a complex and time-consuming task. A check suite may be organized in a certain order by an appropriate technique, subsequently permitting the detection of flaws as early as possible. Multi-goal particle swarm optimization (MOPSO) is used for case prioritization in regression testing. The purpose of MOPSO in this context is to organize the test suite in a specific order that maximizes fault coverage, provides sufficient coverage of test cases, and minimizes execution time. This study proposes an approach based on MOPSO that focuses on maximum fault coverage, most circumstance insurance, and minimal execution time. Experiments are performed using the average percentage of faults detected (APFD) to evaluate its performance. Performance analysis using APFD consisting of no order, opposite order, and random order indicates that the MOPSO surpasses all the previous techniques and obtains an 85% fault coverage. Moreover, MOPSO is better in terms of execution time, fault detection fee, and early detection capabilities.