Prediction of Reservoir Simulation Jobs Times Using a Real-World SLURM Log

Abstract

Modeling petroleum field behavior provides crucial knowledge for risk quantification regarding extraction prospects. Since their processing requires significant computational power and storage capabilities, oil companies run reservoir simulation jobs on high-performance computing clusters. Efficiently using machine learning algorithms in job schedulers to predict the incoming job execution time can increase the effectiveness of cluster resources, such as improving its resource usage rate and reducing the job queue time. This paper introduces a novel and robust predictor, based on SLURM logs from Petrobras, that classifies with more than 74% accuracy the duration time interval of reservoir simulation jobs. The results reveal that our model exceeded the performance of the EASY++ algorithm-based estimator.