Performance prediction of ocean color Monte Carlo simulations using multi-layer perceptron neural networks

Abstract A performance modeling method is presented to predict the execution time of a parallel Monte Carlo (MC) radiative transfer simulation code for ocean color applications. The execution time of MC simulations is predicted using a multi-layer perceptron (MLP) neural network regression model trained with past execution time measurements in different execution environments and simulation cases. On the basis of the MLP performance model, a complementary job-environment mapping algorithm enables an efficient utilization of available high-performance computing resources minimizing the total execution time of the simulation jobs distributed in multiple environments.

[1]  J. C. Cunha,et al.  Monte Carlo code for high spatial resolution ocean color simulations. , 2010, Applied optics.

[2]  José C. Cunha,et al.  High-Performance Ocean Color Monte Carlo Simulation in the Geo-info Project , 2009, PPAM.

[3]  Young Hoon Lee,et al.  Scheduling jobs on parallel machines applying neural network and heuristic rules , 2000 .

[4]  Fulya Altiparmak,et al.  Buffer allocation and performance modeling in asynchronous assembly system operations: An artificial neural network metamodeling approach , 2007, Appl. Soft Comput..

[5]  Sally A. McKee,et al.  Efficiently exploring architectural design spaces via predictive modeling , 2006, ASPLOS XII.

[6]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[7]  Roland Doerffer,et al.  Neural network for emulation of an inverse model: operational derivation of Case II water properties from MERIS data , 1999 .

[8]  Ian T. Nabney,et al.  Netlab: Algorithms for Pattern Recognition , 2002 .

[9]  Arif Ghafoor,et al.  Performance modeling of load-balancing algorithms using neural networks , 1994, Concurr. Pract. Exp..

[10]  Sally A. McKee,et al.  An Approach to Performance Prediction for Parallel Applications , 2005, Euro-Par.

[11]  C. Mobley,et al.  Phase function effects on oceanic light fields. , 2002, Applied optics.

[12]  Davide D'Alimonte,et al.  Determination of CDOM and NPPM absorption coefficient spectra from coastal water remote sensing reflectance , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[13]  G. Zibordi,et al.  An Evaluation of Depth Resolution Requirements for Optical Profiling in Coastal Waters , 2004 .

[14]  Davide D'Alimonte,et al.  An Evaluation of Radiometric Products from Fixed-Depth and Continuous In-Water Profile Data from Moderately Complex Waters , 2009 .

[15]  Davide D'Alimonte,et al.  Phytoplankton determination in an optically complex coastal region using a multilayer perceptron neural network , 2003, IEEE Trans. Geosci. Remote. Sens..

[16]  David Doxaran,et al.  Uncertainties associated to measurements of inherent optical properties in natural waters. , 2010, Applied optics.