Uncertainty quantification through Monte Carlo method in a cloud computing setting

TL;DR

This paper introduces a cloud-based, MapReduce parallelization strategy for Monte Carlo uncertainty quantification, significantly reducing computational costs and enabling scalable simulations in structural dynamics.

Contribution

It presents a novel parallelization methodology for Monte Carlo simulations using MapReduce in cloud environments, enhancing scalability and efficiency.

Findings

Efficient distribution of Monte Carlo tasks in the cloud.

Good statistical results with low-order moments.

High scalability and low-cost for large numbers of realizations.

Abstract

The Monte Carlo (MC) method is the most common technique used for uncertainty quantification, due to its simplicity and good statistical results. However, its computational cost is extremely high, and, in many cases, prohibitive. Fortunately, the MC algorithm is easily parallelizable, which allows its use in simulations where the computation of a single realization is very costly. This work presents a methodology for the parallelization of the MC method, in the context of cloud computing. This strategy is based on the MapReduce paradigm, and allows an efficient distribution of tasks in the cloud. This methodology is illustrated on a problem of structural dynamics that is subject to uncertainties. The results show that the technique is capable of producing good results concerning statistical moments of low order. It is shown that even a simple problem may require many realizations for convergence of histograms, which makes the cloud computing strategy very attractive (due to its high scalability capacity and low-cost). Additionally, the results regarding the time of processing and storage space usage allow one to qualify this new methodology as a solution for simulations that require a number of MC realizations beyond the standard.