An efficient framework for ensemble of natural disaster simulations as a service
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 factors. Such large ensembles cannot typically be run on a single computer due to the limi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2020-09-01
|
| Series: | Geoscience Frontiers |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1674987120300438 |
| _version_ | 1797721492438384640 |
|---|---|
| author | Ujjwal KC Saurabh Garg James Hilton |
| author_facet | Ujjwal KC Saurabh Garg James Hilton |
| author_sort | Ujjwal KC |
| collection | DOAJ |
| description | 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 factors. Such large ensembles cannot typically be run on a single computer due to the limited computational resources available. Cloud Computing offers an attractive alternative, with an almost unlimited capacity for computation, storage, and network bandwidth. However, there are no clear mechanisms that define how to implement these complex natural disaster ensembles on the Cloud with minimal time and resources. As such, this paper proposes a system framework with two phases of cost optimization to run the ensembles as a service over Cloud. The cost is minimized through efficient distribution of the simulations among the cost-efficient instances and intelligent choice of the instances based on pricing models. We validate the proposed framework using real Cloud environment with real wildfire ensemble scenarios under different user requirements. The 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. |
| first_indexed | 2024-03-12T09:34:05Z |
| format | Article |
| id | doaj.art-5774c49c04c64906ba601b96468c1ee8 |
| institution | Directory Open Access Journal |
| issn | 1674-9871 |
| language | English |
| last_indexed | 2024-03-12T09:34:05Z |
| publishDate | 2020-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Geoscience Frontiers |
| spelling | doaj.art-5774c49c04c64906ba601b96468c1ee82023-09-02T13:46:58ZengElsevierGeoscience Frontiers1674-98712020-09-0111518591873An efficient framework for ensemble of natural disaster simulations as a serviceUjjwal KC0Saurabh Garg1James Hilton2Discipline of ICT, University of Tasmania, Hobart, Australia; Corresponding author.Discipline of ICT, University of Tasmania, Hobart, AustraliaData61, CSIRO, Melbourne, AustraliaCalculations 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 factors. Such large ensembles cannot typically be run on a single computer due to the limited computational resources available. Cloud Computing offers an attractive alternative, with an almost unlimited capacity for computation, storage, and network bandwidth. However, there are no clear mechanisms that define how to implement these complex natural disaster ensembles on the Cloud with minimal time and resources. As such, this paper proposes a system framework with two phases of cost optimization to run the ensembles as a service over Cloud. The cost is minimized through efficient distribution of the simulations among the cost-efficient instances and intelligent choice of the instances based on pricing models. We validate the proposed framework using real Cloud environment with real wildfire ensemble scenarios under different user requirements. The 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.http://www.sciencedirect.com/science/article/pii/S1674987120300438Wildfire predictionEnsemble simulationCloud computingNatural disaster models |
| spellingShingle | Ujjwal KC Saurabh Garg James Hilton An efficient framework for ensemble of natural disaster simulations as a service Geoscience Frontiers Wildfire prediction Ensemble simulation Cloud computing Natural disaster models |
| title | An efficient framework for ensemble of natural disaster simulations as a service |
| title_full | An efficient framework for ensemble of natural disaster simulations as a service |
| title_fullStr | An efficient framework for ensemble of natural disaster simulations as a service |
| title_full_unstemmed | An efficient framework for ensemble of natural disaster simulations as a service |
| title_short | An efficient framework for ensemble of natural disaster simulations as a service |
| title_sort | efficient framework for ensemble of natural disaster simulations as a service |
| topic | Wildfire prediction Ensemble simulation Cloud computing Natural disaster models |
| url | http://www.sciencedirect.com/science/article/pii/S1674987120300438 |
| work_keys_str_mv | AT ujjwalkc anefficientframeworkforensembleofnaturaldisastersimulationsasaservice AT saurabhgarg anefficientframeworkforensembleofnaturaldisastersimulationsasaservice AT jameshilton anefficientframeworkforensembleofnaturaldisastersimulationsasaservice AT ujjwalkc efficientframeworkforensembleofnaturaldisastersimulationsasaservice AT saurabhgarg efficientframeworkforensembleofnaturaldisastersimulationsasaservice AT jameshilton efficientframeworkforensembleofnaturaldisastersimulationsasaservice |