Name
Abstract | ||
|---|---|---|
In this paper, we describe an emergent tool called DAWN (short for \"Distributed Analytics, Workflows and Numeric\") which is a model for simulating, analyzing and optimizing system architectures for executing arbitrary data processing pipelines. As an example, we will apply DAWN to the investigation of a real-life Big Data use case in climate science: the evaluation of simulated rainfall characteristics using high-resolution observational data. We will show how DAWN can help in determining the optimal architecture, and science algorithms, to execute this case study analyzing distributed datasets, as a tradeoff between the overall time cost and the uncertainty of calculated metrics for model evaluation. We will also show how DAWN can guide architectural decisions for future research, specifically impacting how data should be generated and analyzed to cope with future projected data volumes. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1109/BigData.2015.7364002 | Big Data |
Field | DocType | Citations |
Data modeling,Data mining,Data processing,Architecture,Pipeline transport,Computer science,Artificial intelligence,Systems architecture,Analytics,Workflow,Big data,Machine learning | Conference | 0 |
PageRank | References | Authors |
0.34 | 1 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Huikyo Lee | 1 | 3 | 1.85 |
| Luca Cinquini | 2 | 128 | 13.91 |
| Daniel J. Crichton | 3 | 69 | 11.65 |
| Amy Braverman | 4 | 36 | 8.40 |