ICST 2021 (series) / ITEQS 2021 (series) / ITEQS 2021 /
Online GANs for Automatic Performance Testing
We present a novel algorithm for automatic performance testing that uses an online variant of the Generative Adversarial Network (GAN) to optimize the test generation process. The objective is to generate a test suite for a given test budget with a high number of tests revealing performance defects. This is achieved using a GAN to generate the tests and predict their outcome. This GAN is trained online, while generating and executing the tests and it does not require a prior training set or model of the system under test. We consider that the presented algorithm serves as a proof of concept and we hope that it can spark a research discussion on the application of GANs to test generation.
Mon 12 AprDisplayed time zone: Brasilia, Distrito Federal, Brazil change
Mon 12 Apr
Displayed time zone: Brasilia, Distrito Federal, Brazil change
10:30 - 11:30 | |||
10:30 30mFull-paper | Software Defects Rules Discovery ITEQS A: Andreea Vescan Babes-Bolyai University, A: Camelia Serban Department of Computer Science, Babes-Bolyai University, A: Gloria Cerasela Crisan "Vasile Alecsandri" University of Bacau | ||
11:00 30mFull-paper | Online GANs for Automatic Performance Testing ITEQS A: Ivan Porres Åbo Akademi University, Hergys Rexha Åbo Akademi University, Sebastien Lafond Åbo Akademi University |