Value based PSO Test Case Prioritization Algorithm

Abstract

Regression testing is performed to see if any changes introduced in software will not affect the rest of functional software parts. It is inefficient to re-execute all test cases every time the changes are made. In this regard test cases are prioritized by following some criteria to perform efficient testing while meeting limited testing resources. In our research we have proposed value based particle swarm intelligence algorithm for test case prioritization. The aim of our research is to detect maximum faults earlier in testing life cycle. We have introduced the combination of six prioritization factors for prioritization. These factors are customer priority, Requirement volatility, implementation complexity, requirement traceability, execution time and fault impact of requirement. This combination of factors has not been used before for prioritization. A controlled experiment has been performed on three medium size projects and compared results with random prioritization technique. Results are analyzed with the help of average percentage of fault detection (APFD) metric. The obtained results showed our proposed algorithm as more efficient and robust for earlier rate of fault detection. Results are also revalidated by proposing our new validation equation and showed consistent improvement in our proposed algorithm.