An efficient framework for ensemble of natural disaster simulations as a service

作     者：Ujjwal KC Saurabh Garg James Hilton Ujjwal KC;Saurabh Garg;James Hilton

作者机构：Discipline of ICTUniversity of TasmaniaHobartAustralia Data61CSIROMelbourneAustralia 

出 版 物：《Geoscience Frontiers》 (地学前缘（英文版）)

年 卷 期：2020年第11卷第5期

页      面：1859-1873页

核心收录：

学科分类：083002[工学-环境工程] 0830[工学-环境科学与工程（可授工学、理学、农学学位）] 08[工学] 

基　　金：supported by Data61,Commonwealth Scientific and Industrial Research Organization(CSIRO) University of Tasmania(Tasmania Graduate Research Scholarship 2018) 

主　　题：Wildfire prediction Ensemble simulation Cloud computing Natural disaster models 

摘      要：Calculations of risk from natural disasters may require ensembles of hundreds of thousands of simulations to accurately quantify the complex relationships between the outcome of a disaster and its contributing *** large ensembles cannot typically be run on a single computer due to the limited computational resources *** Computing offers an attractive alternative,with an almost unlimited capacity for computation,storage,and network ***,there are no clear mechanisms that define how to implement these complex natural disaster ensembles on the Cloud with minimal time and *** such,this paper proposes a system framework with two phases of cost optimization to run the ensembles as a service over *** cost is minimized through efficient distribution of the simulations among the cost-efficient instances and intelligent choice of the instances based on pricing *** validate the proposed framework using real Cloud environment with real wildfire ensemble scenarios under different user *** experimental results give an edge to the proposed system over the bag-of-task type execution on the Clouds with less cost and better flexibility.