Automated Performance Testing Based on Active Deep Learning
This addresses the problem of efficient performance testing for software engineers dealing with large, complex systems where source code is inaccessible, though it appears incremental as it builds on existing machine learning approaches.
The paper tackles the challenge of generating tests to reveal performance issues in complex software systems with limited test budgets and black-box access, presenting ACTA, an automated method based on active learning and conditional generative adversarial networks, which was evaluated on a benchmark web application and found to be comparable to random testing and two other machine learning methods.
Generating tests that can reveal performance issues in large and complex software systems within a reasonable amount of time is a challenging task. On one hand, there are numerous combinations of input data values to explore. On the other hand, we have a limited test budget to execute tests. What makes this task even more difficult is the lack of access to source code and the internal details of these systems. In this paper, we present an automated test generation method called ACTA for black-box performance testing. ACTA is based on active learning, which means that it does not require a large set of historical test data to learn about the performance characteristics of the system under test. Instead, it dynamically chooses the tests to execute using uncertainty sampling. ACTA relies on a conditional variant of generative adversarial networks,and facilitates specifying performance requirements in terms of conditions and generating tests that address those conditions.We have evaluated ACTA on a benchmark web application, and the experimental results indicate that this method is comparable with random testing, and two other machine learning methods,i.e. PerfXRL and DN.