Estimation of Distributed Ultrasound Simulation Execution Time Using Machine Learning

Estimation of Distributed Ultrasound Simulation Execution Time Using Machine Learning

Stať ve sborníku v databázi WoS či Scopus

This study introduces a comprehensive system designed to predict the execution time of k-Wave ultrasound simulations, factoring in the domain size and allocated computing resources. The predictive models, developed using symbolic regression and neural networks, were trained on historical performance data acquired from the Barbora supercomputer. For domain sizes with optimal parameters, the symbolic regression model outperformed, achieving an average error of 5.64%. Conversely, the neural network showed commendable efficacy in general domain scenarios, with an average error of 8.25%. Notably, in both instances, the average error remained below the 10% threshold, aligning closely with the uncertainty inherent in the measured data and the execution of real large-scale jobs. Consequently, this predictive system is well-suited for deployment in resource optimization frameworks, significantly enhancing the efficiency of large-scale simulation executions.

This study introduces a comprehensive system designed to predict the execution time of k-Wave ultrasound simulations, factoring in the domain size and allocated computing resources. The predictive models, developed using symbolic regression and neural networks, were trained on historical performance data acquired from the Barbora supercomputer. For domain sizes with optimal parameters, the symbolic regression model outperformed, achieving an average error of 5.64%. Conversely, the neural network showed commendable efficacy in general domain scenarios, with an average error of 8.25%. Notably, in both instances, the average error remained below the 10% threshold, aligning closely with the uncertainty inherent in the measured data and the execution of real large-scale jobs. Consequently, this predictive system is well-suited for deployment in resource optimization frameworks, significantly enhancing the efficiency of large-scale simulation executions.

Prediction of Execution Time, Moldable tasks, Symbolic Regression, Neural Network, Supercomputer, Simulation, k-Wave, Ultrasound, HeuristicLab.

Prediction of Execution Time, Moldable tasks, Symbolic Regression, Neural Network, Supercomputer, Simulation, k-Wave, Ultrasound, HeuristicLab.

JAROŠ, J.; JAROŠ, M.; BUCHTA, M.

2025

08.08.2024

Institute of Electrical and Electronics Engineers

Yokohama

979-8-3503-0836-5

2024 IEEE Congress on Evolutionary Computation (CEC)

1

8

8

https://www.fit.vut.cz/research/publication/13130/

Prediction of Distributed Ultrasound Simulation Execution Time Using Machine Learning