| On 2023-04-18 at 15:00:00 (Brussels Time) |
Abstract
Database systems play a critical role in modern data-centered applications, and their performance significantly impacts the efficiency of data processing pipelines. In recent years, several methods have been proposed to automatically optimize the parameter configuration of databases. However, many of these methods still have limited effectiveness due to their complexity or ad-hoc nature. In our work, we investigate the potential of irace to automatically determine the optimal parameter configuration for a database, generating configurations for different scenarios. We then extend the use of irace to a more complex scenario, to configure a complete pipeline. Moreover, we demonstrate the importance of a well-designed experimental setup in the tuning process of a database to achieve reliable and consistent results.
Link to Seminar:
https://teams.microsoft.com/l/meetup-join/19%3aYDVRTvS5v-FcnsTJisONwlDTQrEw-hclXJrmwzVxbkg1%40thread.tacv2/1680522516094?context=%7b%22Tid%22%3a%2230a5145e-75bd-4212-bb02-8ff9c0ea4ae9%22%2c%22Oid%22%3a%22dcfe88e1-1c78-4028-8f17-6357145735b2%22%7d
