SMU Data Science Review
Abstract
Addressing the challenge of computationally intensive OLGA
simulations in the oil and gas industry, a machine learning framework is
developed for accurate runtime prediction. A specialized feature extraction
pipeline identifies key parameters—such as simulation time, time step,
number of branches, and section count—from OLGA input files that serve as
high-impact predictors. Multiple predictive models, including regression,
tree-based ensembles, and neural networks, are implemented to validate
accuracy and robustness. Results reveal that prioritizing simulations based on
predicted runtimes optimizes licensing resources and reduces operational
costs, making real-time scheduling more efficient. This research demonstrates
the effectiveness of data-driven runtime prediction in enhancing both
decision-making and resource allocation for complex engineering
simulations.
Recommended Citation
Yule, Andrew and Taylor, Andrew
(2025)
"Predicting Simulation Times for Multiphase Thermal-Hydraulic Models,"
SMU Data Science Review: Vol. 9:
No.
2, Article 6.
Available at:
https://scholar.smu.edu/datasciencereview/vol9/iss2/6
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License
Included in
Data Science Commons, Digital Communications and Networking Commons, Industrial Technology Commons, Numerical Analysis and Scientific Computing Commons, Other Chemical Engineering Commons, Petroleum Engineering Commons, Process Control and Systems Commons, Systems Architecture Commons, Thermodynamics Commons
