Tunaoil: a tuning algorithm strategy for reservoir simulation workloads
Visualitza/Obre
Estadístiques de LA Referencia / Recolecta
Inclou dades d'ús des de 2022
Cita com:
hdl:2117/346349
Tipus de documentText en actes de congrés
Data publicació2021-05
EditorBarcelona Supercomputing Center
Condicions d'accésAccés obert
Tots els drets reservats. Aquesta obra està protegida pels drets de propietat intel·lectual i
industrial corresponents. Sense perjudici de les exempcions legals existents, queda prohibida la seva
reproducció, distribució, comunicació pública o transformació sense l'autorització del titular dels drets
Abstract
The state-of-the-art techniques to tune the numerical parameters
of reservoir simulators are based on running numerous
simulations, specific for that purpose, to find good candidates.
As the simulations for real petroleum fields require a
considerable amount of time, optimizing parameters using this
approach is costly in terms of time and computing resources.
The main objective of this work, therefore, is to present a
new methodology to optimize the numerical parameters of the
reservoir simulations. It is common in the oil and gas (O&G)
industry to use ensembles of models in different workflows to
reduce the uncertainty associated with the forecasting of O&G
production. We can leverage the runs needed to create such
ensembles, to extract the information we can use to optimize
the numerical parameters in future runs.
To achieve this, we mine past execution logs from many
simulations with different numerical configurations and build
a performance model that is based on features extracted from
the data. This performance model takes general information
about petroleum fields and the simulation parameters as inputs,
allowing it to generalize to different unseen reservoir models.
Experiments show that the presented system can correctly
produce good configurations in a much-reduced time, within
a history matching workflow that generates hundreds of simulations.
CitacióPortella, F.; Berral García, J.L. Tunaoil: a tuning algorithm strategy for reservoir simulation workloads. A: . Barcelona Supercomputing Center, 2021, p. 61-62.
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
BSC_DS-2021-21_TunaOil A Tuning Algorithm.pdf | 157,2Kb | Visualitza/Obre |