Adaptive Computing for Scale-up Problems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912400255483904 |
|---|---|
| author | Griffin, Kevin Patrick Egan, Hilary de Frahan, Marc T. Henry Mueller, Juliane Vaidhynatha, Deepthi Wald, Dylan Chintala, Rohit Doronina, Olga A. Sitaraman, Hariswaran Young, Ethan King, Ryan Sanyal, Jibonananda Day, Marc Larsen, Ross E. |
| author_facet | Griffin, Kevin Patrick Egan, Hilary de Frahan, Marc T. Henry Mueller, Juliane Vaidhynatha, Deepthi Wald, Dylan Chintala, Rohit Doronina, Olga A. Sitaraman, Hariswaran Young, Ethan King, Ryan Sanyal, Jibonananda Day, Marc Larsen, Ross E. |
| contents | Adaptive Computing is an application-agnostic outer loop framework to strategically deploy simulations and experiments to guide decision making for scale-up analysis. Resources are allocated over successive batches, which makes the allocation adaptive to some objective such as optimization or model training. The framework enables the characterization and management of uncertainties associated with predictive models of complex systems when scale-up questions lead to significant model extrapolation. A key advancement of this framework is its integration of multi-fidelity surrogate modeling, uncertainty management, and automated orchestration of various computing and experimentation resources into a single integrated software package. This enables efficient multi-fidelity modeling across multiple computing resources by incorporating real-world constraints such as relative queue times and throughput on individual machines into the multi-fidelity sampling decision. We discuss applications of this framework to problems in the renewable energy space, including biofuels production, material synthesis, perovskite crystal growth, and building electrical loads. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_00053 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Adaptive Computing for Scale-up Problems Griffin, Kevin Patrick Egan, Hilary de Frahan, Marc T. Henry Mueller, Juliane Vaidhynatha, Deepthi Wald, Dylan Chintala, Rohit Doronina, Olga A. Sitaraman, Hariswaran Young, Ethan King, Ryan Sanyal, Jibonananda Day, Marc Larsen, Ross E. Optimization and Control Fluid Dynamics Adaptive Computing is an application-agnostic outer loop framework to strategically deploy simulations and experiments to guide decision making for scale-up analysis. Resources are allocated over successive batches, which makes the allocation adaptive to some objective such as optimization or model training. The framework enables the characterization and management of uncertainties associated with predictive models of complex systems when scale-up questions lead to significant model extrapolation. A key advancement of this framework is its integration of multi-fidelity surrogate modeling, uncertainty management, and automated orchestration of various computing and experimentation resources into a single integrated software package. This enables efficient multi-fidelity modeling across multiple computing resources by incorporating real-world constraints such as relative queue times and throughput on individual machines into the multi-fidelity sampling decision. We discuss applications of this framework to problems in the renewable energy space, including biofuels production, material synthesis, perovskite crystal growth, and building electrical loads. |
| title | Adaptive Computing for Scale-up Problems |
| topic | Optimization and Control Fluid Dynamics |
| url | https://arxiv.org/abs/2404.00053 |