EVENTO
NAZCA: a machine learning based framework for performance prediction and configuration recommendation of multiscale numerical simulations
Tipo de evento: Defesa de Tese de Doutorado
Multiscale phenomena are observed in nature, which has increasingly attracted the attention of researchers from different areas. Simulations that intend to represent such phenomena should use computationally robust methods. The use of these multiscale methods is often limited to a small group of users who understand the inherent complexity of each method. The overarching objective of this thesis is to help users unfamiliar with the complexity of these methods to configure and run multiscale simulations. With this objective in mind, we propose a framework called NAZCA. This framework is based on machine learning, thereby using a dataset from previous simulations to help users. We have defined several scenarios in which help is needed for users of multiscale simulations. Each of these scenarios is associated with a task, which will be solved with a specific machine learning technique. In this thesis, we consider the multiscale hybrid mixed (MHM) finite element method as our case study. We have used NAZCA to analyze three tasks from three different scenarios involving the MHM method. In the first task, we estimate the execution time and numerical error of an MHM simulation. For this task, we developed a specific tree-based learning technique that explores specific knowledge about the numerical method. We show that this technique obtains smaller errors than other state-of-the-art techniques, and a high level of interpretability. In the second task, we recommend numerical parameters for an MHM simulation, based on the execution time and numerical error targeted by the user. For this task, we employed a distance-based technique on a performance metric space that is formed by predictions obtained by the firsttask. We show that this technique obtains an accuracy of more than 80% in determining the numerical parameters that present execution time and numerical error closest to the user's target. In the third task, we recommend computational configurations for an MHM simulation, based on the numerical parameters desired by the user. For this task, we employed a ranking-based technique that orders the available computational configurations according to the estimated time to run a numerical simulation on them. We show that this technique obtains configuration rankings that approximate the actual ranking obtained with the dataset of previous simulations. We expect it will be possible to use this approach with other numerical methods with similar computational characteristics.Para assistir acesse:meet.google.com/ozp-kzcx-bww
Data Início: 20/12/2022 Hora: 09:00 Data Fim: 20/12/2022 Hora: 12:00
Local: LNCC - Laboratório Nacional de Computação Ciêntifica - Webinar
Aluno: Juan Humberto Leonardo Fábian - -
Orientador: Antônio Tadeu Azevedo Gomes - Laboratório Nacional de Computação Científica - LNCC Eduardo Soares Ogasawara - Centro Federal de Educação Tecnológica Celso Suckow da Fonseca - CEFET-RJ
Participante Banca Examinadora: Antônio Tadeu Azevedo Gomes - Laboratório Nacional de Computação Científica - LNCC Daniel Cardoso Moraes de Oliveira - Universidade Federal Fluminense - UFF Frédéric Gerard Christian Valentin - Laboratório Nacional de Computação Científica - LNCC Lucia Maria de Assunção Drummond - Universidade Federal Fluminense - UFF
Suplente Banca Examinadora: Alvaro Luiz Gayoso de Azeredo Coutinho - Universidade Federal do Rio de Janeiro - COPPE/UFRJ Fabio Andre Machado Porto - Laboratório Nacional de Computação Científica - LNCC
