Machine-Learning Informed Prediction of Linear Solver Tolerance for Non-Linear Solution Methods in Numerical Simulation

Oladokun, E.; Sheth, Soham; Jönsthövel, T.B.; Neylon, K.

doi:10.3997/2214-4609.202035089

Cited by 4 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The work [27] is the closest work that we could find in the domain of reservoir simulation. They introduce a random forest regression that predicts the linear solver tolerance for each timestep of the simulation.…”

Section: Runtime Predictionmentioning

confidence: 99%

TunaOil: A Tuning Algorithm Strategy for Reservoir Simulation Workloads

Portella,

Prats,

Rodrigues

et al. 2022

Preprint

View full text Add to dashboard Cite

Reservoir simulations for petroleum fields and seismic imaging are known as the most demanding workloads for highperformance computing (HPC) in the oil and gas (O&G) industry. The optimization of the simulator numerical parameters plays a vital role as it could save considerable computational efforts. State-of-the-art optimization techniques are based on running numerous simulations, specific for that purpose, to find good parameter candidates. However, using such an approach is highly costly in terms of time and computing resources. This work presents TunaOil, a new methodology to enhance the search for optimal numerical parameters of reservoir flow simulations using a performance model. In the O&G industry, it is common to use ensembles of models in different workflows to reduce the uncertainty associated with forecasting O&G production. We leverage the runs of those ensembles in such workflows to extract information from each simulation and optimize the numerical parameters in their subsequent runs.To validate the methodology, we implemented it in a history matching (HM) process that uses a Kalman filter algorithm to adjust an ensemble of reservoir models to match the observed data from the real field. We mine past execution logs from many simulations with different numerical configurations and build a machine learning model based on extracted features from the data. These features include properties of the reservoir models themselves, such as the number of active cells, to statistics of the simulation's behavior, such as the number of iterations of the linear solver. A sampling technique is used to query the oracle to find the numerical parameters that can reduce the elapsed time without significantly impacting the quality of the results. Our experiments show that the predictions can improve the overall HM workflow runtime on average by 31%.

show abstract

Section: Runtime Predictionmentioning

confidence: 99%

TunaOil: A Tuning Algorithm Strategy for Reservoir Simulation Workloads

Portella,

Prats,

Rodrigues

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The success of machine learning in different fields has inspired recent applications with the aim of reducing the computational cost in numerical simulations by accelerating the convergence of the numerical solution. Oladokun et al (2020) used a random forest regression to determine the linear convergence tolerance of the nonlinear solver. Random forests is an ensemble method that fits a number of decision trees in sub-samples of the dataset and combine/average their result to improve predictive accuracy and control over-fitting (Breiman, 2001).…”

Section: Introductionmentioning

confidence: 99%

“…Random forests is an ensemble method that fits a number of decision trees in sub-samples of the dataset and combine/average their result to improve predictive accuracy and control over-fitting (Breiman, 2001). The method proposed by Oladokun et al (2020) reduced the number of linear iterations while not compromising the number of nonlinear iterations.…”

Section: Introductionmentioning

confidence: 99%