MAP Reduce for Big Data Applications Based on Improving the Network Traffic Performance.
| dc.contributor.author | Divya Bharathi, B | |
| dc.date.accessioned | 2018-10-17T13:37:53Z | |
| dc.date.available | 2018-10-17T13:37:53Z | |
| dc.date.issued | 2018-10-17T13:37:53Z | |
| dc.description.abstract | The Map-Reduce model exploits parallel map tasks and reduces tasks to simplify large-scale data processing on commodity cluster. The network traffic generated in the shuffle phase is ignored even if many efforts have been made to improve the map reduce job's performance. this plays a critical role in performance enhancement. Traditionally, the intermediate data is partitioned among the reduce tasks by utilizing hash function; this is not traffic efficient because the key is associated with network topology and data size which are not taken into consideration. By designing a novel intermediate data partition scheme, the network traffic cost for a map reduce job can be reduced. Additionally there might be a | en_US |
| dc.identifier.uri | http://hdl.handle.net/123456789/9986 | |
| dc.language.iso | en | en_US |
| dc.subject | Divya Bharathi B | en_US |
| dc.subject | 1NZ16MCA72 | en_US |
| dc.subject | MAP Reduce for Big Data Applications Based on Improving the Network Traffic Performance. | en_US |
| dc.subject | MCA Projects 2018 | en_US |
| dc.title | MAP Reduce for Big Data Applications Based on Improving the Network Traffic Performance. | en_US |
| dc.type | Other | en_US |