Add to Favourites
To login click here
This thesis presents a modern machine learning-based approach for predicting the execution time of software systems from two angles: workload-independent performance and workload-dependent performance. To do this, a systematic empirical study was conducted across five well-known projects in JMH benchmarking and 126 concrete benchmarks, resulting in a dataset of approximately 1.4 million measurements. The results of the study showed that the proposed approach was able to accurately predict the execution time of the software systems.