基于云计算的蒙特卡罗模拟研究

Monte Carlo Simulation Based on Cloud Computing

为了提高蒙特卡罗模拟算法的运算效率和精确度,需建立一个能满足高精确度、高效率、易扩展、易使用的计算环境。本文根据云计算可弹性增加计算节点的特点,将Symphony DE并行软件搭建在本地私有云环境下,运用在Excel中的编程实现蒙特卡罗模拟,通过增加计算节点数目对比运算效率与计算精度。结果表明:随着计算节点数的增加,运算效率大大提高,计算结果更加精确。

In order to improve operational efficiency and accuracy of Monte Carlo simulation algorithm, we need to establish a computing environment that it has characteristics of high-accuracy, high efficiency, easy to expand, easy to use. In this paper, according to the characteristics that cloud computing can increase flexible compute nodes, building the Symphony DE parallel soft- ware on a private cloud environment in local, achieving Monte Carlo simulation make use of program in Excel, through increasing the number of computing nodes, we can compare computational efficiency with computational accuracy. The results show that op- erational efficiency is greatly improved and calculation results are more accurate calculations.